topic: Artificial Intelligence

topic: Artificial Intelligence

Social media activity version | Lean version

AI model maps global tree canopy heights in hi-res, with carbon counting in mind
- Scientists have used high-resolution satellite images to create a map of global canopy heights, and to also develop an AI model that can predict canopy heights.
- Tech company Meta collaborated with nonprofit organization World Resources Institute to develop the open-source map and model.
- While the map aims to establish and serve as a baseline for conservation initiatives, the AI model could be used to predict canopy heights in areas where high-quality data aren’t available.
- Canopy height is an important indicator of forest biomass and aboveground carbon stock, and is used to measure the progress of forest restoration efforts.

Bioacoustics and AI help scientists listen in on elusive Australian cockatoos
- Researchers in Australia have deployed acoustic recorders and artificial intelligence to study, monitor and protect eastern pink cockatoos (Lophochroa leadbeateri leadbeateri).
- The technology led scientists at the Queensland University of Technology to a previously unknown breeding hollow of the birds.
- Pink cockatoos, with eastern and western subspecies, are endemic to Australia and hard to monitor because they live in remote arid and semiarid ecosystems.
- With the research, scientists say they hope to understand more about where the birds live and how they react to changes in rainfall and temperature.

Unseen and unregulated: ‘Ghost’ roads carve up Asia-Pacific tropical forests
- A new study indicates that significant networks of informal, unmapped and unregulated roads sprawl into forest-rich regions of Southeast Asia and the Pacific.
- Slipping beneath the purview of environmental governance, construction of these “ghost roads” typically precede sharp spikes in deforestation and represent blind spots in zoning and law enforcement, the study says.
- The authors underscore that the relentless proliferation of ghost roads ranks among the gravest of threats facing the world’s remaining tropical forests.
- The findings bolster a growing momentum toward the development of AI-based road-mapping systems to help conservation biologists and resource managers better keep track of informal and illegal road networks and curb associated deforestation rates.

The potential for tracking wildlife health & disease via bioacoustics is great (commentary)
- Bioacoustics is the passive, non-invasive recording of sounds emitted by a wide range of animals.
- Analysis of this information reveals the presence and behavior of wildlife, and can also be valuable indicator of animal health, which can then be used in ecosystem monitoring.
- “As disease prevalence skyrockets in wildlife, we are desperately in need of tools to remotely monitor ecosystem health,” a new op-ed argues.
- This post is a commentary. The views expressed are those of the author, not necessarily Mongabay.

Critics fear catastrophic energy crisis as AI is outsourced to Latin America
- AI use is surging astronomically around the globe, requiring vastly more energy to make AI-friendly semiconductor chips and causing a gigantic explosion in data center construction. So large and rapid is this expansion that Sam Altman, the boss of OpenAI, has warned that AI is driving humanity toward a “catastrophic energy crisis.”
- Altman’s solution is an audacious plan to spend up to $7 trillion to produce energy from nuclear fusion. But even if this investment, the biggest in all of history, occurred, its impact wouldn’t be felt until mid-century, and do little to end the energy and water crises triggered by AI manufacture and use, while having huge mining and toxic waste impacts.
- Data centers are mushrooming worldwide to meet AI demand, but particularly in Latin America, seen as strategically located by Big Tech. One of the largest data center hubs is in Querétaro, a Mexican state with high risk of intensifying climate change-induced drought. Farmers are already protesting their risk of losing water access.
- As Latin American protests rise over the environmental and social harm done by AI, activists and academics are calling for a halt to government rubber-stamping of approvals for new data centers, for a full assessment of AI life-cycle impacts, and for new regulations to curb the growing social harm caused by AI.

Ancient giant river dolphin species found in the Peruvian Amazon
- Paleontologists discovered a fossilized skull of a newly described species of giant freshwater dolphin in the Peruvian Amazon, which lived around 16 million years ago and is considered the largest-known river dolphin ever found.
- The ancient creature, measuring 3-3.5 meters (9.8-11.5 feet), was surprisingly related to South Asian river dolphins rather than the local, living Amazon river pink dolphin and shared highly developed facial crests used for echolocation.
- The discovery comes at a time when the six existing species of modern river dolphins face unprecedented threats, with their combined populations decreasing by 73% since the 1980s due to unsustainable fishing practices, climate change, pollution, illegal mining and infrastructure development.
- Conservation efforts are underway, including the signing of the Global Declaration for River Dolphins by nine countries and successful initiatives in China and Indonesia, highlighting the importance of protecting these critical species that serve as indicators of river ecosystem health.

To detect illegal roads in remote areas, AI comes into play
- Scientists have deployed an artificial intelligence model to identify and detect roads in rural and remote areas.
- The model was trained to analyze satellite images and pick out the roads within them; according to a recent study, it managed to do this accurately eight times out of 10.
- Road construction has increased drastically in recent decades, with 25 million kilometers (15.5 million miles) of paved roads expected to be built by 2050.
- Illegal roads, which fall outside the purview of environmental governance, often cut through dense forests and cause harm to the biodiversity living in fragile ecosystems.

New funding boosts AI-enabled wildlife identification project in Australia
- An artificial intelligence project to identify native species from camera-trap images in Australia has received a A$750,000 ($492,000) grant from the government.
- The project by the conservation nonprofit Australian Wildlife Conservancy has already trained the AI model to identify 44 species from camera-trap images, from native animals such as kangaroos and dingoes, and invasive ones like cats and foxes.
- With the new funding, the team at AWC aims to scale up the model to be able to identify 120 species; the model can also be applied to alert land managers about invasive predators that are harmful to native species.
- Camera traps continue to be one of the most widely used technologies for biodiversity surveys, but the analysis of the thousands of images generated by camera traps remains a major bottleneck.

On Kaho’olawe, new technology could restore a sacred Hawaiian island
- The small Hawaiian island of Kaho‘olawe is a sacred site for Indigenous Hawaiians, who used it for navigational training, religious ceremonies, and fishing.
- But the island has faced decades of ecological destruction due to invasive plants and animals, erosion, and bombings as a test site by the U.S. military.
- A new conservation project has successfully tested a novel method using AI-equipped camera traps and an aerial drone to collect images of invasive cats, which have destroyed the island’s seabird populations, in dangerous and difficult-to-access parts of the island.
- But funding for the work on Kaho‘olawe remains scarce, and the drone project is now on hold as local organizations seek further funding to deal with the feral cats.

Find the manatee: New AI model spots sea cows from images
- A new computer model developed by engineers at the Florida Atlantic University uses deep learning to count manatees in images captured by cameras.
- The model has been trained to identify manatees in shallow waters, and can be used to identify where they aggregate, which can, in turn, be helpful to plan conservation actions and design rules for boaters and divers.
- However, the model can’t yet distinguish between adults and calves, or between males and females, both of which are details that are vital for conservation and research purposes.
- The engineering team says it plans to continue training the model in the months ahead, while also working with biologists to get their feedback on how to improve it further.

‘We’re doing so much with so little’: Interview with WildLabs’ Talia Speaker
- The use of technology for conservation and wildlife monitoring increased in recent years, with camera traps and remote sensing being the most popular tools, a report has found.
- The report by conservation technology network WildLabs also found that artificial intelligence was highly ranked for its potential impact, but was ranked low in terms of current performance because of accessibility issues.
- Marginalized groups, including women and people from lower-income countries, were found to face disproportionate barriers to accessing resources and training.
- “The motivation behind this research was to capture the experiences of the global conservation technology community, and to speak with a united voice,” says Talia Speaker, who led the research.

New AI model helps detect and identify microplastics in wastewater
- A new model developed by researchers at the University of Waterloo in Canada uses advanced spectroscopy and artificial intelligence to identify the presence of microplastics in wastewater.
- Researchers trained PlasticNet to detect microplastics based on how they absorb and transmit different wavelengths of light that they’re exposed to.
- The tool successfully classified 11 types of common plastics with an accuracy of more than 95%; it could potentially be used by wastewater treatment plants and food producers to identify microplastics.
- The team is currently working to make the model work faster and more efficiently, and to also streamline the process of gathering data.

AI and satellite data map true scale of untracked fishing and ocean industry
- A new study shows that more than 75% of industrial fishing activity and almost 30% of transport and energy activity in the oceans has not been tracked by public systems, revealing a significant gap in global observational data.
- The study, led by Global Fishing Watch, used AI to analyze 2 petabytes of satellite imagery collected between 2017 and 2021, providing unprecedented insights into hidden fishing hotspots and offshore energy infrastructure development.
- The research highlighted the potential of combining AI with Earth observation data to gain a more comprehensive understanding of ocean activities, which is needed to manage and improve the sustainability of the $2.5 trillion blue economy.
- The open-source code developed during the study can help inform policy for safeguarding ocean ecosystems, enforcing laws and identifying renewable energy expansion sites, the study authors said.

Conservation X Labs announces merger with AI nonprofit Wild Me
- Conservation technology company Conservation X Labs has announced a merger with Wild Me, a nonprofit that focuses on using artificial intelligence for conservation purposes.
- The two organizations plan to combine their resources and expertise to ramp up the use of artificial intelligence to prevent the sixth mass extinction.
- The merger comes at a time when AI’s role in biodiversity monitoring and conservation has seen rising popularity.
- According to a press statement by Conservation X Labs, the company will “integrate Wild Me’s technology into its product offerings.”

New AI model gives bird’s-eye view of avian distribution at vast scale
- An artificial intelligence model is helping researchers use bird-sighting data to estimate their presence at a given time and location.
- Developed by researchers at Cornell University, the model makes predictions on when and where species of birds in North America might occur throughout the year, providing information that could be vital for conservation purposes.
- The model was trained using billions of data points from eBird, an online portal and database where birders can record the observations they make in the field.
- The researchers are now working to train the model to get estimates on abundance of species as opposed to only getting information on their presence or absence.

To keep track of salmon migrations in real time, First Nations turn to AI
- Partnering with First Nations, a new interdisciplinary study proposes harnessing artificial intelligence and computer-based detection to count and produce real-time data about salmon numbers.
- Monitoring their population when they return to the rivers and creeks is crucial to keep tabs on the health of the population and sustainably manage the stock, but the current manual process is laborious, time-consuming and often error-prone.
- Fisheries experts say the use of real-time population data can help them make timely informed decisions about salmon management, prevent overfishing of stocks, and give a chance for the dwindling salmon to bounce back to healthy levels.
- First Nations say the automated monitoring tool also helps them assert their land rights and steward fisheries resources in their territories.

Sound recordings and AI tell us if forests are recovering, new study from Ecuador shows
- Acoustic monitoring and AI tools were used to track biodiversity recovery in plots of tropical Chocó forest in northwestern Ecuador.
- The study found that species returned to regenerating forests in as little as 25 years, indicating positive progress in forest recovery.
- Acoustic monitoring and AI-based methods proved to be powerful and cost-effective techniques for assessing biodiversity levels in restored forests, including insects and animals that don’t vocalize.
- The authors hope these methods make biodiversity monitoring more transparent, accountable, and accessible to support land managers and market-based conservation mechanisms that rely on forest restoration, such as payments for ecosystem services.

Nepal’s tiger conservation gets tech boost with AI-powered deer tracking
- Endangered tigers in Nepal heavily rely on spotted deer as their primary prey, making their conservation crucial.
- Researchers in Nepal are using vertical cameras and AI technology to track and profile individual spotted deer (Axis axis), similar to the methods used for tigers.
- However, the project has faced challenges, including low recapture rates and difficulty in distinguishing individual deer in the wild.

Climate change detectable in daily rainfall patterns, deep-learning model finds
- Researchers have developed a deep-learning AI model that predicts how global warming is affecting daily precipitation patterns around the world.
- Using the model, scientists found that every year since 2015 daily rainfall deviated from natural variability at least 50% of the time as a result of rising temperatures.
- Research has long focused on climate change’s long-term impacts such as annual temperature increase or precipitation rates.
- However, studies in recent years have observed how rising temperatures are altering daily weather patterns as well.

With fewer birds seen on farms, scientists try listening for them
- Scientists in the U.S. Midwest have piloted a methodology that combines satellite imagery and audio data to study and monitor birds in croplands.
- While remote-sensing technology helped researchers understand the attributes of the habitat, bioacoustic data aided them in identifying the birds that live there.
- Biodiversity monitoring on working lands often doesn’t get a lot of attention due to the logistical hurdles involved in accessing these often privately owned areas.
- The methods used by the scientists involved engaging with farmers and landowners to put up audio recorders in an effort to be more collaborative.

Mongabay Explains: How high-tech tools are used for successful reforestation
- This Mongabay Explains’ episode is part of a four-part Mongabay mini-series that examines the latest technological solutions to help tree-planting projects achieve scale and long-term efficiency.
- Using these innovative approaches could be vital for meeting international targets to repair degraded ecosystems, sequester carbon, and restore biodiversity.
- Advanced computer modeling, machine learning, drones, niche models using data, robotics and other technologies are helping to restore hundreds of millions of hectares of lost and degraded forest worldwide.

In the chain of species extinctions, AI can predict the next link to break
- Scientists at Flinders University in Australia have developed a machine-learning model that predicts which species are at risk of extinction if another species is removed from an ecosystem or an invasive one is introduced.
- Trained on data on how species interact with each other, the model could serve to alert conservation managers on which vulnerable species to focus on, the developers say.
- They tested the model successfully in Australia’s Simpson Desert, where it accurately predicted which species invasive foxes and cats preyed on.
- However, the shortage of data on species interactions, along with the possible biases that arise, are gaps that still need to be filled in the model.

Machine learning helps researchers identify underground fungal networks
- Researchers are using remote-sensing technology and machine-learning algorithms to map and predict the presence of mycorrhizal fungi in ecosystems around the world.
- The Society for the Protection of Underground Networks (SPUN) is an initiative that aims to map the distribution of fungal networks to spread awareness and advocate for their protection.
- Mycorrhizal fungi form symbiotic relationships with plants, serving as a vital interface for transferring water and nutrients from the soil while also storing massive amounts of carbon underground.
- SPUN is also working to provide financial and technical support to researchers and local communities to help them map fungal networks in their home countries.

AI unlocks secrets of Amazon river dolphins’ behavior, no tagging required
- Freshwater dolphins in the Amazon Basin navigate through flooded forests during the wet season using their flexible bodies and echolocation clicks.
- Researchers have combined advanced acoustic monitoring and AI to study the habits of endangered pink river dolphins (boto) and tucuxi in seasonally flooded habitats.
- They used hydrophones to record sounds in various habitats and employed convolutional neural networks (CNN) to classify the sounds as either echolocation clicks, boat engine noises, or rain — with high accuracy.
- Understanding the dolphins’ movements and behaviors can aid conservation efforts to protect these endangered species, as they face various threats such as fishing entanglement, dam construction, mining, agriculture and cattle ranching.

New Tree Tech: Real-time, long-term, high-tech reforestation monitoring
- This four-part Mongabay mini-series examines the latest technological solutions to help tree-planting projects achieve scale and long-term efficiency. Using these innovative approaches could be vital for meeting international targets to repair degraded ecosystems, sequester carbon, and restore biodiversity.
- Many people see reforestation as a quick fix to the climate emergency, but tree-planting projects often fail to put in place the monitoring programs needed to track newly planted forests. Traditionally, forest monitoring has been done by hand, one tree at a time, which is extremely expensive and time-consuming.
- Satellites are mapping and remapping the entire planet daily, providing real-time data that can be used to monitor forests remotely. Drones can fly over or through forests to collect data on tree growth, bridging the gap between on-site measurements and distant satellites.
- Sensors can be installed to monitor individual trees directly, while people can collect and analyze the data electronically from a safer and easier-to-access location. Multiple sensors can form a distributed network that returns detailed information on the growth of each tree within huge reforestation plots.

New Tree Tech: Cutting-edge drones give reforestation a helping hand
- This four-part Mongabay mini-series examines the latest technological solutions to help tree-planting projects achieve scale and long-term efficiency. Using these innovative approaches could be vital for meeting international targets to repair degraded ecosystems, sequester carbon, and restore biodiversity.
- Restoring hundreds of millions of hectares of lost and degraded forest worldwide will require a gigantic effort, a challenge made doubly hard by the fact that many sites are inaccessible by road, stopping manual replanting projects in their tracks.
- Manual planting is labor-intensive and slow. Drone seeding uses the latest in robotic technology to deliver seeds directly to where they’re needed. Drones can drop seeds along a predefined route, working together in a “swarm” to complete the task with a single human supervisor overseeing the process.
- Drone-dropped seed success rates are lower than for manually planted seedlings, but biotech solutions are helping. Specially designed pods encase the seeds in a tailored mix of nutrients to help them thrive. Drones are tech-intensive, and still available mostly in industrialized countries, but could one day help reseed forests worldwide.

New Tree Tech: Data-driven reforestation methods match trees to habitats
- This four-part Mongabay mini-series examines the latest technological solutions to help tree-planting projects achieve scale and long-term efficiency. Using these innovative approaches could be vital for meeting international targets to repair degraded ecosystems, sequester carbon, and restore biodiversity.
- To create healthy, diverse ecosystems, native tree species need to be identified that will thrive at each unique site within a habitat. But with more than 70,000 tree species worldwide, gathering and analyzing the data needed to understand species’ needs, habitat preferences and limitations is no small feat.
- Environmental niche models use data on climate, soil conditions and other characteristics within a species’ range to calculate a tree’s requirements. Artificial intelligence helps sort through vast data sets to make informed predictions about the species suited to an ecosystem, now and in a warmer future.
- Biotechnology company Spades uses laboratory testing of tissue samples from plant species to quantify what growing conditions a species can tolerate and to identify its optimum growing conditions.

New Tree Tech: AI, drones, satellites and sensors give reforestation a boost
- This four-part Mongabay mini-series examines the latest technological solutions to help tree-planting projects achieve scale and long-term efficiency. Using these innovative approaches could be vital for meeting international targets to repair degraded ecosystems, sequester carbon, and restore biodiversity.
- Current forest restoration efforts fall far short of international goals, and behind the hype lies a string of failed projects and unintended environmental consequences that have left a bad taste in the mouths of many investors, politicians and conservationists. Projects are often expensive and labor-intensive.
- Applying cutting-edge technology to the problem is helping: Advanced computer modeling and machine learning can aid tree-planting initiatives in identifying a diverse set of native species best able to thrive in unique local conditions, today and in a warming future.
- Drones are revolutionizing large-scale tree planting, especially in remote and inaccessible locations. Once trees are planted, satellite-based and on-site sensors can help monitor young forests — offering long-term scrutiny and protection often missing from traditional reforestation initiatives, and at a lower cost.

Bioacoustics in your backyard: Q&A with conservation technologist Topher White
- Delta, a new eco-device, allows people to record the sounds of wildlife that live in and visit their backyards.
- Developed by conservation technologist Topher White, Delta combines the tools of bioacoustics and artificial intelligence.
- Delta is part of White’s larger mission to document the drastically changing state of global biodiversity.

To save Hainan gibbons, Earth’s rarest primate, experts roll out the big tech
- As scientists and the Chinese government ramp up efforts to protect the critically endangered Hainan gibbon, technology is playing an important part in helping track and monitor the species better.
- In recent years, bioacoustics, infrared technology and machine learning are among the tools that have been used to make data collection and analysis easier in the study of Hainan gibbons.
- According to estimates, there are only 35 or 36 individuals of the species left, limited to Bawangling National Nature Reserve in China’s Hainan province.

On wildlife and the Metaverse, some ethical considerations (commentary)
- The Metaverse may facilitate even more physical events and activities to take place online, thus cutting down on carbon emissions resulting from travel.
- But it’s also known that AI language processing models this relies on will push Metaverse carbon emissions through the roof, since they require large amounts of electricity.
- A community-driven blockchain provider and cryptocurrency option called Wild Metaverse, for example, will donate a percentage of profits to wildlife conservation. But will that be worth its overall cost to wildlife, a new op-ed wonders?
- This post is a commentary. The views expressed are those of the author, not necessarily of Mongabay.

Can gaming solve a puzzle for camera trap conservationists? (commentary)
- Artificial intelligence programs for camera trap image recognition have become quite good at identifying common wildlife, but they struggle with rare animals.
- Before AI can tell a badger from a raccoon, it needs to be trained with some images, but if a species is rarely seen in camera trap photos, there isn’t enough data for it to learn, and it won’t be very good at recognizing that rare species (‘rare-class categorization’).
- However, a new commentary explains that AI are able to learn from the kind of game engine-generated, hyper-realistic animal images that feature in today’s highly advanced digital games.
- This post is a commentary. The views expressed are those of the author, not necessarily of Mongabay.

Tech companies work to make fishing, aquaculture more sustainable
- Several companies around the world are developing technology to make fishing and aquaculture more sustainable.
- These include the use of artificial intelligence to identify non-native species that disrupt marine food webs and the fisheries they support, and lights that attempt to attract only target species to fishing nets in a bid to reduce the capture of non-targeted species.
- With the rapidly increasing global population underscoring the need to source protein more sustainably, experts say it’s urgent to find ways to make fishing less damaging and more productive.

Road network spreads ‘arteries of destruction’ across 41% of Brazilian Amazon
- A groundbreaking study using satellite data and an artificial intelligence algorithm shows how the spread of unofficial roads throughout the Amazon is driving widespread deforestation.
- One such road is on the verge of cutting across the Xingu Socioenvironmental Corridor, posing a serious risk of helping push the Amazon beyond a crucial tipping point.
- Unprotected public lands account for 25% of the total illegal road network, with experts saying the creation of more protected areas could stem the spread and slow both deforestation and land grabs.
- Officially sanctioned roads, such as the Trans-Amazonian Highway, also need better planning to minimize their impact and prevent the growth of illegal offshoots, experts say.

New tech aims to track carbon in every tree, boost carbon market integrity
- Climate scientists and data engineers have developed a new digital platform billed as the first-ever global tool for accurately calculating the carbon stored in every tree on the planet.
- Founded on two decades of research and development, the new platform from nonprofit CTrees leverages artificial intelligence-enabled satellite datasets to give users a near-real-time picture of forest carbon storage and emissions around the world.
- With forest protection and restoration at the center of international climate mitigation efforts, CTrees is set to officially launch at COP27 in November, with the overall aim of bringing an unprecedented level of transparency and accountability to climate policy initiatives that rely on forests to offset carbon emissions.
- Forest experts broadly welcome the new platform, but also underscore the risk of assessing forest restoration and conservation projects solely by the amount of carbon sequestered, which can sometimes be a red herring in achieving truly sustainable and equitable forest management.

Scientists develop AI that can listen to the pulse of a reef being restored
- Scientists have developed a machine-learning algorithm that can distinguish healthy coral reefs from less healthy ones by the soundscape in the ecosystem.
- Previous studies had established that the sounds of life in a successfully recovered reef are similar to those from a healthy reef, but parsing all the acoustic data was slow and labor-intensive.
- The new algorithm has been hailed as “an important milestone” for efficiently processing acoustic data to answer the basic question of how to determine the progress of a reef restoration program.
- Researchers say follow-up work is still needed, including to check whether the algorithm, tested in the Pacific Coral Triangle, also works in reefs in other parts of the world.

‘Amped-up citizen science’ to save the world: Q&A with Conservation AI Hub’s Grant Hamilton
- Conservation AI Hub uses drones and artificial intelligence to detect koalas that survived the Australian bushfires of 2019 and 2020.
- The initiative is now working with communities in Australia to train them on using the technology by themselves.
- Director Grant Hamilton says it’s imperative to make technology more accessible so that more citizens can engage and participate in global conservation efforts.

In Gabon, camera-trap developers find the ideal proving ground for their craft
- Rich in forests and biodiversity, the Central African country of Gabon has long proved a fruitful testing ground for camera-trap technology.
- Snapshots of species once thought extinct in the country, such as lions, have helped inform conservation policy, including the establishment of national parks and protection of vast swaths of forest.
- The wealth of data generated means there are large data sets from various projects that researchers just don’t have the resources or time to sift through — which is why Gabon has also become a testing ground for artificial intelligence tools to aid in that task.
- Key limitations remain the cost of camera traps and the fact that many forms of data capture and analysis simply can’t be done by camera traps or AI, and still require human involvement.

Hear that? Bioacoustics is having its moment, but the technology still needs tuning
- The use of audio to study, monitor, detect and conserve species has gained popularity in recent years.
- Passive acoustic monitoring has been found to be more efficient than traditional camera traps; however, the use of audio can be data-heavy and laborious to pore through.
- Technological developments such as artificial intelligence have made audio analysis easier, but conservationists say gaps still exist.

New near-real-time tool reveals Earth’s land cover in more detail than ever before
- A new tool co-developed by Google Earth Engine and the World Resources Institute is being billed as the planet’s most up-to-date and high-resolution global land cover mapping data set, giving unprecedented levels of detail about how land is being used around the world.
- The launch of the tool this week marks a big step forward in enabling organizations and governments to make better science-based, data-informed decisions about urgent planetary challenges, the developers say.
- Named Dynamic World, it merges cloud-based artificial intelligence with satellite imagery to give near-real-time global visualizations of nine types of land use and land cover.
- The tool is likely to be important for a variety of purposes, the developers say, such as monitoring the progress of ecosystem restoration goals, assessing the effectiveness of protected areas, creating sustainable food systems, and alerting land managers to unforeseen land changes like deforestation and fires.

Can conservation technology help save our rapidly disappearing species? | Problem Solved
- Humanity knows, in a best-case scenario, only 20% of the total species on Earth.
- Yet humans have, at a minimum, increased species extinction 1,000 times above the natural extinction rate, raising concerns among field monitoring experts who worry they may be “writing the obituary of a dying planet.”
- The establishment of protected areas often depends on the ability of conservationists to effectively monitor and track land-based species — but is this happening fast enough?
- For this episode of “Problem Solved,” Mongabay breaks down three of the most innovative pieces of conservation technology and how they can advance the field of species monitoring, and ultimately, conservation.

AI model shows how Amazon dams can be made less environmentally damaging
- Researchers have developed a model using artificial intelligence to analyze the environmental impacts of 351 hydropower dam projects currently under evaluation in the Amazon Basin.
- The model aims to provide information that would help planners and policymakers optimize the capacity and location of new dams to minimize their negative impacts.
- It also shows, however, that no proposed dam could ever have zero impact across all the environmental criteria, and that social impacts on local communities remain far too complex to model with AI.
- While other researchers have welcomed the new way of modeling the risks, they recommend an end to high-capacity hydropower projects in the Amazon and a greater focus on solar and wind power instead.

Tech revolution holds world of promise for conservation, but challenges persist
- Technology has rapidly changed the face of conservation and is now at a critical juncture where cutting edge tools are available, but aren’t necessarily as accessible or affordable as they need to be.
- A recent survey by WILDLABS, an online platform connecting conservation technology experts, shows that environmental DNA, networked sensors and artificial intelligence tools are the fields that hold the most promise.
- Yet despite the progress that’s been made, there are still many barriers to accessibility for local and Indigenous communities.
- Experts say collaboration and partnerships between conservationists, tech developers and local and Indigenous communities will be key to ensuring that conservation tech can continue having an impact.

Boosting human and machine expertise with conservation tech: Q&A with Sara Beery
- Sara Beery is a computer vision expert with an unlikely path to science: having started out as a ballerina, her goal now is to help solve problems in conservation technology.
- She takes two approaches to conservation tech — a top-down one for solutions that can be applied to a wide range of problems, and a bottom-up one tailored for specific challenges — and works in the field to make sure they actually work.
- Beery helped create Microsoft’s AI for Earth MegaDetector, a model that helps detect animals in camera trap data, and collaborates with the ElephantBook project in Kenya to automate the identification of elephants.
- In an interview with Mongabay, Sara Beery talks about her path to conservation tech, how she combines the best of both human and artificial intelligence to solve problems, and why fieldwork is key to ensuring that tech solutions are usable and accessible.

Collaboration is key to scaling conservation technologies (commentary)
- To tackle conservation challenges, the sector has embraced numerous technologies like GPS, radio telemetry, satellite imagery, camera traps, and software to process and analyze data.
- A new op-ed argues that such tech must be built with the end-user in mind: their voices must be considered to ensure the solutions reflect the real needs on the ground.
- Investors, NGOs, and conservationists should also demand that conservation technology is developed in the field and is both scalable and coalition-based: collaborations like Wildlife Insights and SMART are prime examples.
- This post is a commentary. The views expressed are those of the author, not necessarily of Mongabay.

Indigenous agents fight deforestation with drones and AI in Brazilian Amazon
- The rate of deforestation has increased in recent years in the Brazilian state of Acre, which is now in the top five for deforestation risk, according to a forecast by an artificial intelligence tool developed by Microsoft and Brazilian nonprofit Imazon.
- In a study developed especially for Mongabay, the AI tool shows that Acre has 878 square kilometers (339 square miles) of land that is at high or very high risk of deforestation, including inside, 20 conservation units and 29 Indigenous territories.
- Efforts to combat deforestation include training of Indigenous people to monitor their own territories against agriculture-driven invasions.
- One Indigenous agroforestry agent told Mongabay that he and his peers rely on technology such as drones and GPS to monitor forest fires, guard against poaching, and thwart illegal invasions.

New artificial intelligence tool helps forecast Amazon deforestation
- A new tool co-developed by Microsoft using artificial intelligence to predict deforestation hotspots has identified nearly 10,000 square kilometers of the Brazilian Amazon that’s in imminent danger.
- Called PrevisIA, it uses artificial intelligence to analyze satellite imagery from the European Space Agency, and an algorithm developed by the Brazilian conservation nonprofit Imazon to find the areas most prone to deforestation.
- The tool, which the developers say could potentially be applied to any forested area on Earth, will be used for preventive actions, in partnerships with local governments, corporations and nonprofits.
- The next step of the project is to build partnerships with local governments and institutions to act on preventing deforestation, which is the most challenging phase of the project, according to Imazon researcher Carlos Souza Jr.

Betting big on bioacoustics: Q&A with philanthropist Lisa Yang
- Lisa Yang is an investor and philanthropist who donated $24 million last month to establish the K. Lisa Yang Center for Conservation Bioacoustics at the Cornell Lab of Ornithology.
- Yang told Mongabay that she focused on bioacoustics due to the great potential for scaling the effectiveness of conservation efforts: “The technology can provide an effective way of assessing conservation practices.”
- Yang’s philanthropic interests extend to translational neuroscience and fostering opportunities and respect for people who’ve been historically marginalized by society, including the “neurodiverse and individuals with disabilities.”
- Yang spoke about opportunities to scale impact in conservation during a conversation with Mongabay founder Rhett A. Butler.

Big bioacoustics boost: Cornell University program receives $24 million donation
- The field of bioacoustics has been a game changer when it comes to monitoring and discovering new things about animals and ecosystems, both on land and at sea.
- Still a relatively new discipline, one of the leading programs in the field globally was founded in the 1980s at Cornell University, which has just announced a donation of $24 million to support its bioacoustics work.
- The K. Lisa Yang Center for Conservation Bioacoustics will use the funds to accelerate its training of researchers, facilitate development of new tools and partnerships, and build a global network of people who can share bioacoustics best practices.

How to transform systems: Q&A with WRI’s Andrew Steer
- Between the pandemic, rising food insecurity and poverty, and catastrophic disasters like wildfires, storms and droughts, 2020 was a year of challenges that prompted widespread calls for systemic change in how we interact with one another, with other species, and with the environment. Bringing about such changes will require transforming how we produce food and energy, how we move from one place to another, and how we define economic growth.
- But it’s a lot easier to talk about transforming systems than to actually do it. Because real change is hard, we’re more likely to slip back into old habits and return to business as usual than embrace paradigm shifts.
- Recognizing this limitation, World Resources Institute (WRI), a Washington, D.C.-based organization that operates in 60 countries, works across sectors by creating tools that increase transparency, create a common understanding, and provide data and analysis that enable action.
- WRI’s development of these platforms and tools has grown by leaps and bounds since the early 2010s when Andrew Steer joined the organization as president and CEO from the World Bank. Steer spoke with Mongabay during a December 2020 interview.

Bold sustainability commitments: An interview with Microsoft’s Lucas Joppa
- One of the boldest climate commitments in 2020 came from the tech giant Microsoft, which in January pledged to be carbon negative by 2030 and to address its legacy emissions–all the carbon the company has emitted since its founding in 1975–by 2050.
- Microsoft has also committed to replenish more water than it consumes and produce zero net waste by 2030, while protecting more land than it uses by 2025. Further, the company said it would lend its computing power toward efforts to combat biodiversity loss and use its voice to advocate for public policies that “measure and manage ecosystems.”
- Heading up these ambitious sustainability initiatives is Microsoft’s chief environmental officer Lucas Joppa, a Ph.D. ecologist who also conceived of Microsoft’s AI for Earth platform.
- Joppa spoke with Mongabay Founder Rhett A. Butler in a December 2020 interview.

Where to patrol next: ‘Netflix’ of ranger AI serves up poaching predictions
- The PAWS AI system, developed out of Harvard University, uses data about past poaching and game theory to predict where rangers are most likely to find poaching activity next.
- PAWS has been field tested in Cambodia and Uganda, and will soon roll out worldwide, available with the next update of a global data tool called SMART.
- Subsequent versions of the system will also feature a tool that recommends the best route for rangers to travel in their patrols.

New artificial intelligence could save both elephant and human lives
- RESOLVE recently debuted the WildEyes AI system, a tiny camera imbued with artificial intelligence that can be trained to recognize specific animals in the field.
- The first version of WildEyes is trained to recognize elephants, which often come into conflict with humans when they raid crops and enter villages.
- RESOLVE says WildEyes can sound an early alarm to help prepare villagers to repel elephants.
- In the future, it may also be used to notify biologists of rare or invasive species, stop poachers, or prevent illegal logging.

Facial recognition tech for chimps looks to bust online ape trafficking
- Much of the illegal trade in apes now takes place online, with traffickers posting pictures of baby animals for sale.
- ChimpFace, a newly developed software, uses an algorithm to determine if chimpanzee faces in images posted by traffickers match up with images later posted to social media accounts.
- Its creators hope the matches the program turns up will aid Interpol or local law enforcement in tracking and prosecuting people illegally buying and selling wildlife.

Audio: Shah Selbe on how open source technology is creating new opportunities for conservation
- On today’s episode of the Mongabay Newscast, we speak with Shah Selbe, an engineer and technologist who founded Conservify, a conservation tech lab that uses open-source technologies to empower local communities and solve some of the most pressing conservation challenges of our time.
- Selbe is literally a rocket scientist who spent a decade building and launching satellites with Boeing before getting into conservation tech. These days he’s helping deploy technologies like drones, sensor networks, smartphone apps, and acoustic monitoring buoys to stop illegal poaching, monitor protected areas, and protect biodiversity.
- Selbe joins us today to talk about his journey from rocket science to conservation science, the open-source hardware and online platform Conservify is developing called FieldKit, and the conservation tech he’s most excited about.

Success of Microsoft’s ‘moonshot’ climate pledge hinges on forest conservation
- One mechanism by which the 2015 Paris Climate Agreement incentivizes greenhouse gas reductions is via carbon offsets, payments that compensate nations, states and private landowners who agree to keep forests intact in order to preserve carbon storage capacity and biodiversity.
- But problems exist with forest carbon offset initiatives: corrupt landowners, lack of carbon accounting transparency, and low carbon pricing have caused wariness among investors, and failed to spur forest preservation.
- Now, in a landmark move, Microsoft has pledged to go “carbon negative” by 2030, and erase all the company’s greenhouse gas emissions back to its founding in 1975 by 2050. A big part of achieving that goal will come via the carbon storage provided by verified global forest conservation and reforestation projects around the globe.
- To achieve its goal, Microsoft has teamed with Pachama, a Silicon Valley startup, that seeks to accurately track forest carbon stocks in projects in the Brazilian and Peruvian Amazon, the U.S. and elsewhere using groundbreaking advanced remote-sensing technology including LiDAR, artificial intelligence and satellite imaging.

Tree-planting programs turn to tech solutions to track effectiveness
- Governments and organizations around the world have carried out massive tree-planting initiatives, but to date there’s been no reliable way to track how effective these programs have been.
- Now, some groups are embracing cutting-edge technology solutions such as QR codes, drone surveillance and blockchain to keep tabs on every tree planted.
- But they also recognize the importance of bringing local communities on board to improve the effectiveness of these efforts, and the need for old-fashioned field surveys to complement the high-tech monitoring methods.

Conservation tech prize with invasive species focus announces finalists
- The Con X Tech Prize announced its second round will fund 20 finalists, selected from 150 applications, each with $3,500 to create their first prototypes of designs that use technology to address a conservation challenge.
- Seven of the 20 teams focused their designs on reducing impacts from invasive species, while the others addressed a range of conservation issues, from wildlife trafficking to acoustic monitoring to capturing freshwater plastic waste in locally-built bamboo traps.
- Conservation X Labs (CXL), which offers the prize, says the process provides winners with very early-stage funding, a rare commodity, and recognition of external approval, each of which has potential to motivate finalists and translate into further funding.
- Finalists can also compete for a grand prize of $20,000 and product support from CXL.

Earth’s hidden tree-microbe network mapped for the first time ever
- For the first time ever, researchers have mapped the underground network of microbes connecting forest trees around the world using an enormous data set of more than 1.1 million forest plots.
- Mapping the forest microbe network required global collaboration and high computing capabilities.
- The new maps confirm patterns that have been long suspected. For example, arbuscular mycorrhizal fungi dominate forests in the warmer tropics while ectomycorrhizal fungi are more widespread in colder boreal and temperate forests.
- The predicted maps are, however, limited by the geographic coverage and sampling density of trees across the world. While the coverage is good in developed countries, it is relatively poor in developing countries like India, China and countries in the tropical region, the researchers say.

Models, maps, and citizen scientists working to save the Great Barrier Reef
- As global warming drives more events that impact coral reefs, managing the Great Barrier Reef’s resilience demands comprehensive and detailed mapping of the reef bed.
- Available surveys and maps with geographically referenced field data have been limited and fragmented.
- A diverse research team recently demonstrated a successful approach, applying statistics to image data to build predictive models, integrate diverse datasets on reef conditions, and provide a comprehensive map of the Reef that informs reef management decisions.

Lift-off for thermal-imaging system to estimate wildlife populations
- A research team hailed a breakthrough in their imaging system’s ability to detect and identify orangutans in tropical rainforest.
- They now plan for computer algorithms to report back what a thermal camera has seen in real time.
- The researchers believe the system could also be used to spot poachers targeting rare species.

Combining artificial intelligence and citizen science to improve wildlife surveys
- Migratory species play a key role in the health of the Serengeti ecosystem in East Africa, but monitoring their populations is a time- and labor-intensive task.
- Scientists studying these wildebeest populations compared expert observer counts of aerial imagery to corresponding counts by both volunteer citizen scientists and deep learning algorithms.
- Both novel methods were able to produce accurate wildebeest counts from the images with minor modifications, the algorithms doing so faster than humans.
- Use of automated object detection algorithms requires prior “training” with specific data sets, which in this case came from the volunteer counts, suggesting that the two methods are both useful and complementary.

AI and drone-based imagery improve power to survey cryptic animals
- Developing effective management strategies for threatened species like koalas requires knowing where and how many are in a target area, but surveying cryptic low-density animals can lead to variable estimates.
- A recent study has introduced a new automated method for wildlife detection using a pair of object detection machine learning algorithms to detect animals’ heat signatures in drone-derived thermal imaging.
- By understanding error rates of different survey methods and including appropriate technology, the researchers say, wildlife monitoring can become more efficient and effective.

AI and public data identify fishing behavior to protect hungry seabirds
- In an effort to reduce albatross deaths as bycatch of longline fishing, Global Fishing Watch (GFW) and Birdlife International researchers are using machine learning models to determine if fishing vessels are setting their lines at night, a recommended technique to avoid accidentally killing albatrosses.
- Mapping fishing vessel behavior involved training new models to recognize when a long-line ship is setting its line.
- This new application broadens the range of GFW’s toolkit to combine machine learning and public data to protect marine wildlife and better manage fisheries.
- Results of the new algorithm formed the basis of a January 2019 regulatory decision by the South Pacific Regional Management Organization.

Audio: The sounds of a rare New Zealand bird reintroduced to its native habitat
- On today’s episode, we speak with Oliver Metcalf, lead author of a recent study that used bioacoustic recordings and machine learning to track birds in New Zealand after they’d been reintroduced into the wild.
- In this Field Notes segment, Metcalf plays some of the recordings of the hihi, also known as the stitchbird, that informed his research and explains how bioacoustic monitoring can help improve reintroduction programs.

How do you assess if a reintroduced species is thriving? Listen for it
- Researchers in New Zealand combined sound data from acoustic monitoring devices with species occupancy models to assess the success of translocating an endangered New Zealand bird, the hihi, to invasive species-free locations.
- The scientists say in their paper that advances in acoustic monitoring and statistical techniques have made it possible to infer spatial and temporal changes in population dynamics without needing to track individual animals.
- As wildlife managers increasingly release animals back to their historic ranges, cost-effective, non-invasive data collection, automated pattern recognition, and analysis techniques that predict the likelihood of species occupying a given location over time could improve the success of the reintroduction process.

Machine learning tool helps prioritize plants for conservation
- In a first global plant conservation assessment, a multi-institutional research team used the power of open-access databases and machine learning to predict the conservation status of more than 150,000 plants.
- They paired geographic, environmental, climatic, and morphological trait information of plant species of known risk of extinction from the IUCN Red List with information on plants of unknown risk in a machine learning model. The model calculated the likelihood that a given unassessed plant species was actually at risk of extinction and identified the variables that best predicted conservation risk.
- More than 15,000 of the species–roughly 10 percent of the total assessed by the team—had characteristics similar to those already categorized as at least near-threatened by IUCN and thus at a high likelihood of extinction.
- The protocol could provide a first cut in identifying unassessed species likely at risk of extinction and suggest how to allocate scarce conservation resources.

Top camera trapping stories of 2018
- Camera traps, remotely installed cameras triggered by motion or heat of a passing person or animal, have helped research projects document the occurrence of species, photograph cryptic and nocturnal animals, or describe a vertebrate community in a given area.
- Camera trapping studies are addressing new research and management questions, including document rare events, assess population dynamics, detect poachers, and involve rural landowners in monitoring.
- And with projects generating ever-larger image data sets, they are using volunteers and, more recently, artificial intelligence to analyse the information.

10 ways conservation tech shifted into auto in 2018
- Conservation scientists are increasingly automating their research and monitoring work, to make their analyses faster and more consistent; moreover, machine learning algorithms and neural networks constantly improve as they process additional information.
- Pattern recognition detects species by their appearance or calls; quantifies changes in vegetation from satellite images; tracks movements by fishing ships on the high seas.
- Automating even part of the analysis process, such as eliminating images with no animals, substantially reduces processing time and cost.
- Automated recognition of target objects requires a reference database: the species and objects used to create the algorithm determine the universe of species and objects the system will then be able to identify.

Drone 3D models help assess risk of turtle nesting beaches to sea level rise
- In a recent study, researchers took drone-based images to map the structure of sea turtle nesting beaches in northern Cyprus to determine their susceptibility to flooding from sea level rise.
- Automated drone flights with on-board cameras can record sequences of photos of the surface below, which can be merged in a process called photogrammetry to construct three-dimensional models of the survey area.
- The fast pace of innovation and versatility of drones can improve sea turtle conservation efforts through cheaper, more efficient monitoring.

Photos highlight evolving roles of AI, citizen science in species research
- A recent observation by an amateur naturalist of a fiddler crab species hundreds of kilometers north of its known range challenged the complementary strengths of computer vision and human expertise in mapping species distributions.
- The naturalist uploaded this record to the iNaturalist species database used by amateurs and experts to document sightings; expert input correctly identified the specimen after the platform’s computer vision algorithms did not acknowledge the species outside its documented range.
- Citizen naturalist observations can be used to document rapid changes in species distributions. They also can improve modeling and mapping work conducted by researchers and play an increasing prominent role in building environmental databases.

A monitoring network in the Amazon captures a flood of data
- Cameras and microphones are capturing images and sounds of the world’s largest rainforest to monitor the Amazon’s species and environmental dynamics in an unprecedented way.
- The Providence Project’s series of networked sensors is aimed at complementing remote-sensing data on forest cover change by revealing ecological interactions beneath the forest canopy.
- Capable of continuously recording, processing and transmitting information to a database in real time, this high-tech experiment involves research institutions from three countries and the skills of biologists, engineers, computer scientists and other experts.
- The monitoring system will connect to a website to disseminate the forest biodiversity data interactively, which the researchers hope will contribute to more effective biodiversity conservation strategies.

Virtual meetup highlights networked sensor technology for parks
- To encourage communication between the conservation community and technology developers, the WILDLABS platform began a series of virtual meetups earlier this month.
- Speakers in the first meetup represented three groups developing and deploying networked sensors for improving wildlife security and reducing human-wildlife conflict.
- The three tech developers described lessons they’ve learned on meeting the needs of rangers and reserve managers, using drones to fight poaching, and adapting technology to function in remote areas under difficult conditions.

Pod-cast: New app streams whale songs for web users in real time
- Researchers have developed a web application to enable citizen scientists to listen for the sounds of a population of killer whales off North America’s northeast Pacific coast in real time.
- A network of underwater microphones will stream sounds from under the sea to citizen scientists, who can then report any unusual noises and help decode orca language.
- The researchers have found that human listeners can readily detect unusual sounds amid a stream of underwater noise, and their participation can complement machine-learning algorithms being developed.

AI simplifies statewide study of leopards in south India
- A six-year study of leopards in the wildlife-rich southern Indian state of Karnataka, using grids of motion-sensor camera traps across the state, suggests the big cats are thriving in a variety of habitats and land uses.
- The researchers’ use of machine-learning algorithms significantly reduced the workload needed to identify 363 individual leopards from the sample’s 1.5 million camera-trap images. The figure indicates there are an estimated 2,500 leopards living in Karnataka.
- Although a forest department official said the state was unlikely to expand its protected forests in the foreseeable future, the researchers said such a policy was necessary for leopard conservation, stressing that the proximity of natural landscapes to agricultural fields allows leopards to use those unprotected areas.

Machine-learning app to fight invasive crop pest in Africa
- To monitor the invasive fall armyworm caterpillar in Africa, the UN’s Food and Agriculture Organization and Pennsylvania State University have collaborated on an AI add-on to FAO’s existing phone app to help farmers detect agricultural pests.
- The fall armyworm, an invasive pest of over 80 plant species, is native to the Americas but reached Africa in early 2016 and has wreaked havoc on their maize, threatening food security.
- The add-on, called Nuru, identifies leaf damage in photos taken by farmers and sends information to authorities to help monitor the presence of the pest.
- Detecting the pest quickly can help reduce unnecessary pesticide use that can damage human and ecosystem health.

The iNaturalist species data sharing platform reaches one million users
- The iNaturalist species data-sharing platform reached a milestone earlier this month with its one millionth observer.
- The 10-year-old platform and mobile app use several smartphone technologies, crowd-sourced data, and artificial intelligence to help observers identify the species of plants and animals they see.
- Co-founder Scott Loarie highlighted the rapid progress in computer vision technology as a surprisingly helpful technology that complements crowdsourcing to speed the image identification process for a large number of photos, though it has also introduced other concerns, including how to maintain high data quality.

Tech prize finalists promote collaboration to fight extinction
- Conservation X Labs recently announced 20 finalists for the Con X Tech Prize. As finalists, each project receives $3,500 seed money to develop ideas that may be early stage or broad in scope.
- Among the finalists, the Wild N.O.S.E technology will use olfactory data to detect animals or animal parts and help stem trafficking, and the Right Whale Auto-Detect project listens for and identifies whale calls and then warns ships of whales in the area.
- These projects express Con X Tech values, such as collaboration, working across disciplines and thinking big enough to deliver transformative conservation solutions with “exponential impact.” One finalist will be selected in November 2018 to receive the $20,000 grand prize.

Decoding the language of bats key to their conservation
- Uruguayan scientists have developed a new artificial intelligence algorithm and reference library of bat ultrasound pulses to enable the use of acoustic monitoring of this understudied regional fauna.
- Bats in the Southern Cone are threatened by wind turbines, but their species and sonar emissions differ from other areas, requiring the scientists to build their own acoustic library and predictive algorithms.
- The scientists are collaborating with wind farm companies and international academics to help expand the reference library and improve the algorithm’s accuracy and speed.

Managing the data deluge: Twitter as a tool for ecological research
- Access to constant streams of observational data from 60 or 70 million Twitter users is a potential trove for scientists, but extracting the target data is a challenge.
- A big advantage of social media data mining is the ability to turn data into usable information on a short timetable. The question is, how does quick, retrospective data compare to data from painstakingly prepared collection processes?
- A recent study compared the results from three published citizen science studies to data sets mined retrospectively from Twitter for the same time periods. It confirmed that mining Twitter could yield reliable baseline data (when, where). As for testing causal relationships or hypotheses involving dependent variables, the jury is still out.
- Twitter shows promise for ecological study, particularly studies around seasonal phenomena such as the annual emergence of flying ants. But filtering out the noise of random human observation is a still-evolving science.

Automating drone-based wildlife surveys saves time and money, study finds
- Reserve managers have begun to survey wildlife in savanna ecosystems by analyzing thousands of images captured using unmanned aerial vehicles (UAVs, or drones), a time-consuming process.
- A research team has developed machine learning models that analyze such aerial images and automatically identify those images most likely to contain animals, which, according to the authors, is usually a small fraction of the total number of images taken during a UAV survey effort.
- The new algorithms reduced the number of images that needed human verification to less than one-third of that using earlier models, and they highlight the patterns in those images that are most likely to be animals, making the technique useful for image-based surveys of large landscapes with animals in relatively few images.

Citizen science makes easy work of penguin time-lapse image bounty
- A multinational research team has deployed time-lapse cameras at various penguin breeding colonies to enable a widespread, long-term study of these top predators in the Antarctic ecosystem.
- Volunteers have played a critical role in processing the millions of images resulting from the multi-year study to better understand reproductive behavior and nest success rates across the Antarctic Peninsula, South Shetland Islands, and South Georgia.
- Citizen scientists can help produce large data sets needed to train artificial intelligence algorithms.

Cool birds don’t sing: Study automates acoustic monitoring of songbird migration
- Researchers have developed machine learning techniques to identify bird song from thousands of hours of field recordings, using the information to uncover variations in migratory songbirds’ arrival to their Arctic breeding grounds.
- They deployed automated listening devices during spring over five years, analyzed vocal activity to estimate when birds arrived at their breeding sites, and assessed relationships between vocal activity and environmental conditions.
- They found that the acoustically derived estimates of the birds’ arrival dates were similar to those determined using standard field surveys.
- Temperature and presence of snow affected the birds’ calling patterns, suggesting that collecting corresponding weather data could help avoid bias in using acoustic monitoring to assess population dynamics.

Species recognition shifts into auto with neural networks
- Scientists have shown that a cutting-edge type of artificial intelligence can automatically count, identify, and describe the behaviors of 48 animal species in camera trap images taken in the Serengeti ecosystem.
- The team used a dataset of 3.2 million wildlife images to train and test deep convolutional neural networks to recognize not only individual animals but also what the animals are doing in each image.
- The models performed as well as human volunteers in identifying, counting, and describing the behavior of animals in nearly all the Serengeti camera trap images and also identified those images that required human review.
- The widespread use of motion-sensor camera traps for wildlife research and conservation, coupled with the inefficiency of manual image processing, means successful automation of some or all of the image analysis process is likely to save researchers time and money, as well as catalyze new uses of remote camera photos.

Mongabay discusses technology’s role in conservation at Seattle event [VIDEO]
- A team from Mongabay discussed new applications of technology for conservation with representatives of Seattle Audubon and Acate Amazon Conservation during an event at Seattle Central College, Washington.
- In this video recording, the panelists discuss topics ranging from bioacoustics to remote sensing and AI and answer questions from the audience.

A global coral reef monitoring system is coming soon
- Coral reef conservation efforts will soon get a major boost with a global monitoring system that will detect physical changes in coral cover at high resolution on a daily basis.
- The satellite-based system will enable researchers, policy makers, and environmentalists to track severe bleaching events, reef dynamiting, and coastal development in near-real time.
- The system will leverage Planet’s daily high resolution satellite imagery, running the data through cloud computing-based algorithms to map reefs and chart changes over time.

This tiny camera aims to catch poachers — before they kill
- A Tanzanian game reserve has successfully tested the TrailGuard cryptic camera and 24/7 electronic surveillance system to detect and capture wildlife poachers and their snares.
- The system uses image recognition algorithms and real-time image transmission to help the often limited patrolling staff of many protected areas identify and respond to potential poachers along trails before they kill their target animals.
- Despite some difficulties with installation and the algorithms, the TrailGuard units in Tanzania have photographed 40 reserve intruders, including poachers or trespassers, resulting in the arrests of 13 suspects.
- The designers are currently developing a new, lower-cost version of the system to be built later this year that they expect will address the difficulties and be more widely available.

Scientists tackling conservation problems turn to artificial intelligence
- Grantees of Microsoft’s AI for Earth, a program aimed at helping groups address complex environmental problems, met at Microsoft headquarters recently to learn new ways to apply artificial intelligence and cloud computing to their respective projects.
- The program awards grants of access to and training in the company’s cloud-based data storage, management, and analysis to address challenges in four thematic areas: addressing climate change, protecting biodiversity, improving agricultural yields, and lessening water scarcity.
- Grant recipients include teams working on game theory to predict poaching patterns; mining social media photos to determine distributions of particular species; and using machine learning and animals’ acoustic activity to determine effectiveness of conservation interventions.

Cities worldwide use photo app technology to compete in nature observation challenge
- The third-annual City Nature Challenge takes place this weekend, April 27-30, 2018, giving nature lovers in cities around the globe a chance to compete against other cities to see who can make the most observations and find the most species of local plants and animals.
- Residents and visitors from nearly 70 cities will use their smartphones and the iNaturalist app to share photos of their findings over the 4-day period; experts will verify the identifications in early May.
- Organizers hope the event will connect more people to their local urban biodiversity and uncover threatened and invasive species in new locations, to assist local resource managers.

From galaxies far, far away to endangered species just over the hill
- Astrophysicists and conservation ecologists have teamed up to apply the heat-detection software and machine-learning algorithms used to find stars to automatically identify people and different animal species.
- The system detects warm, living objects from drone-derived thermal video footage and uses a reference database to identify the various objects efficiently and reliably.
- The research team is refining the system to overcome challenges of variable environmental conditions, as well as hot rocks and other “thermally bright” but uninteresting objects, while building a reference database of multiple target species.

You don’t need a bigger boat: AI buoys safeguard swimmers and sharks
- A new tech-driven device may help reduce harmful interactions with sharks and improve people’s tolerance of one of the ocean’s top predators.
- The system, called Clever Buoy, combines sonar to detect a large object in the water, artificial intelligence to determine that the object is a shark close enough to threaten beachgoers, and automated SMS alerts to lifeguards that enable them to take action.
- Local governments have deployed the system at popular beaches and surfing sites to test its capacity to protect swimmers and surfers without harming marine wildlife.

AI can ‘help us move mountains’ for people and planet, Watson developer says
- IBM Master Developer Neil Sahota believes artificial intelligence (AI) can help humanity ‘move mountains’ in terms of improving lives and the environment.
- Sahota helped develop Watson, the supercomputer which is now being used in a variety of useful ways, like predicting crop yields for farmers in Africa.
- In this interview with Mongabay, he shares multiple examples of AI being used by actors ranging from the UN to NASA and NGOs, for good.

Coral reef monitoring takes to the skies: drone-mounted hyperspectral cameras help scientists assess health of coral reefs
- Hyperspectral images taken from cameras on unmanned aerial vehicles (UAVs) are helping scientists survey the composition and health of coral reefs under the water.
- These images capture information from visible (light) and non-visible sections of the electromagnetic spectrum thereby offering information the human eye can’t see.
- When paired with UAVs or satellites, hyperspectral images allow researchers to survey the reef habitats–including coral, sand, and algae–over large areas as well as monitor the health of individual corals.

Drones enable fast, accurate wildlife counts, study shows
- Unmanned aerial vehicles (UAVs) have great potential for surveying wildlife, especially species that assemble in large numbers and that are easily disturbed by human presence.
- Scientists creatively combined high-tech UAVs and computer-vision algorithms with rubber ducks to assess the potential of aerial imagery to count seabirds relative to traditional survey methods.
- They found that both human and semi-automated computer counts of colony-nesting birds from UAV-derived images were more accurate and less variable than counts made by observers on the ground.
- Combining UAV-derived imagery with artificial intelligence can help scientists more accurately estimate population sizes with less variability.

Data fusion opens new horizons for remote imaging of landscapes
- Scientists use remotely sensed data from satellites to map and analyze habitat extent, vegetation health, land use change, and plant species distributions at various scales.
- Open-source data sets, analysis tools, and powerful computers now allow scientists to combine different sources of satellite-based data.
- A new paper details how combining multispectral and radar data enables more refined analyses over broader scales than either can alone.

10 top conservation tech innovations from 2017
- The increased portability and reduced cost of data collection and synthesis tools have transformed how we research and conserve the natural world.
- Devices from visual and acoustic sensors to DNA sequencers help us better understand the world around us, and they combine with online mapping platforms to help us monitor it.
- New online and mobile apps have democratized data collection, inspiring a brave new world of citizen scientists to learn about the species around them, contribute to conservation and scientific discovery, and feel part of a learning community.
- Here, we present 10 tech trends we covered in 2017, in no particular order, that have helped us better understand nature, monitor its status, and take action to protect it.

Combining computing power and people power to identify key deforestation hotspots
- Technology now allows us to remotely locate and monitor areas of forest loss, creating the challenge of responding to areas with rampant deforestation.
- The Global Forest Watch platform has launched Places to Watch, a feature that highlights key areas of recent deforestation, especially near intact and protected forests.
- An automated process selects deforestation hotspots, which are then filtered and prioritized by experts using satellite imagery and locally-derived reports to select 10 “Places” each month.
- The GFW team aims to provide journalists, activists, and concerned citizens and government, with curated deforestation information to encourage action that prevents further loss in priority areas.

Can technology drive conservation? Experts discuss in Mongabay forum (video)
- A recent tech-based event offered the extensive experience of three panelists on the frontlines of applying technology to conserve a key ecosystem.
- Directors of Global Forest Watch, Rainforest Connection, and Protected Seas discussed how technology’s role expands, as its precision, reach, and cost-effectiveness continue to improve.
- Panelists stressed the need for technology to connect people to each other and to the species and ecosystems in need of conservation support.
- Nevertheless, the panelists agreed, information is not enough; achieving conservation outcomes requires “accounting for the human factor” in maintaining transparency and good governance.

Author Steven Kotler on tackling the biodiversity crisis with technology
- Steven Kotler is a leading thinker on how technology can be employed to halt the global loss of biodiversity.
- Recently the prolific author and journalist convened a weekend forum for environmentalists and technologists in California called Creating Equilibrium, to bring these disciplines into conversation.
- Mongabay interviewed Kotler about his views on the biodiversity crisis and how advanced technology and creative thinking can help avert it.

USAID Wildlife Crime Tech Challenge awards Acceleration Prizes for rapid tech developments
- The Wildlife Crime Tech Challenge announced three winners of a $100,000 Acceleration Prize for rapid progress in developing a wildlife crime solution system.
- The winning devices were: an artificial sea turtle egg to track illegal movements of eggs and identify transit routes; a genetic reference map of pangolin poaching hotspots; and a camera-ground sensor system to monitor and communicate illegal human activity in remote reserves.
- The poaching, trafficking, and consumption of meat, scales, tusks, skin, fur, feathers, and horns of many hundreds of species has depleted populations worldwide and caused local extinctions.

Audio: Technologies that boost conservation efforts right now and in the future
- On this episode of the Mongabay Newscast, we take a look at the role technology is playing — and might play in the future — in conservation efforts.
- Our first guest is Topher White, the founder of Rainforest Connection, a nonprofit based in San Francisco that has deployed upcycled cell phones in tropical forests around the world to provide real-time monitoring of forests and wildlife.
- Our second guest is Matthew Putman, an applied physicist with a keen interest in conservation. Putman is CEO of Nanotronics, a company headquartered in Brooklyn, NY that makes automated industrial microscopes used by manufacturers of advanced technologies like semiconductors, microchips, hard drives, LEDs, and aerospace hardware.

App combines computer vision and crowdsourcing to explore Earth’s biodiversity, one photo at a time
- The nearly 500,000 users in the iNaturalist network have uploaded over 6.5 million photo observations of more than 120,000 species of plants, animals, insects and fungi.
- The network provides a platform for collaboration and discussion among users, while also generating a stream of research quality biodiversity data.
- A recent update to the smartphone app utilizes computer vision to provide immediate taxonomic identifications for user-submitted photos, with varying degrees of specificity.
- The computer vision network requires a large database of identified images to learn the distinctive features of each species; every photo observation uploaded to iNaturalist and identified by the community helps to improve the coverage and accuracy of the automatic identification feature.

Wildbook: a social network for wildlife
- Wildbook is an open-source software platform that helps collaborative projects store and manage wildlife data. The user-friendly interface makes it easy for citizen scientists to contribute animal photos to be used as data for scientific studies.
- Wildbook uses the Image Based Ecological Information System (IBEIS) to semi-automatically analyze the photos and determine, based on an animal’s unique markings, if it is a new individual or an animal already in the database.
- The compiled images can help scientists assess species distributions, movement patterns and human-wildlife interactions, which, in turn, can support management and conservation decisions.

In defining plantations as forest, FAO attracts criticism
- The FAO lumps non-oil palm tree plantations into its definition of forest cover when conducting its Global Forest Resource Assessments. The assessments analyze land cover change in countries around the world using largely self-reported data.
- Nearly 200 organizations have signed an open letter authored by the NGO World Rainforest Movement to change how they define forest.
- Remote sensing technology currently doesn’t provide the ability to differentiate the canopies of forests and tree plantations. But researchers say that within a decade, technological advances will make this a reality.
- A representative of FAO said the organization is unlikely to change its definition since it is already well established and accepted by governments and other stakeholders.

Drones and artificial intelligence image processing improving the ‘koality’ of wildlife monitoring
- Unmanned aerial vehicles (UAVs) paired with artificial intelligence image processing can provide data that helps researchers evaluate the health and conservation status of Australia’s koala population.
- Programming UAVs with a complex hierarchy of algorithms, designed to identify and differentiate between individual animals in the wild, allows researchers to automatically classify data while conducting aerial surveys.
- Researchers continue to advance the program’s algorithms to make this monitoring method more accurate, powerful, and widely applicable.

EGI: Filling in the gaps in law enforcement for the online wildlife trade
- Enforcement Gaps Interface (EGI) uses a computational algorithm to mine hundreds of commercial sites for ads potentially containing illegal wildlife and wildlife products.
- EGI aims to help law enforcement agencies, retailers and nongovernmental organizations reduce and ultimately eliminate rampant online wildlife trafficking.
- EGI’s creators are further developing it to incorporate more languages and image recognition into its searches.

Discarded cell phones to help fight rainforest poachers, loggers in real-time

A technology that uses discarded mobile phones to create a real-time alert system against logging and poaching will soon be deployed in the endangered rainforests of Central Africa. Rainforest Connection (RFCx), a San Francisco-based non-profit startup, is partnering with the Zoological Society of London (ZSL) to install its real-time anti-deforestation technology at sites in Cameroon. […]

Feeds: news | india | latam | brasil | indonesia