topic: Big Data

topic: Big Data

Social media activity version | Lean version

Gundi tool gets conservation hardware and software talking the same language
- A new open-source platform aims to help conservationists and protected-area managers seamlessly integrate data between hardware and software tools.
- Currently being used at 600 sites, Gundi takes data from different sources — wildlife trackers, camera traps, acoustic monitors — transforms them into a common format, and sends them to different destinations for analysis.
- Gundi was developed with the goal of helping reduce the time and effort required to figure out compatibility issues between different conservation technology tools.

Mongabay Data Studio: Revealing nature’s hidden stories through data (commentary)
- High-quality data journalism serves as a powerful tool in revealing complex environmental issues, transforming raw data into compelling narratives that illuminate the hidden stories behind the numbers.
- Ultimately, high-quality data journalism empowers citizens, policymakers and activists with the information needed to make informed decisions, driving meaningful action towards environmental sustainability and conservation. Through meticulous data analysis and creative storytelling, environmental journalism can thus significantly amplify its reach and impact, guiding society towards a more informed and conscientious stewardship of the natural world.
- To this end, last month we announced Mongabay Data Studio which aims to strengthen our data journalism capabilities.
- The initiative supports data journalism across all of Mongabay’s languages, bureaus, and formats, including investigations, news reporting, videos, and social media visualizations. It is structured to operate across various topics and geographies, enabling comprehensive data journalism integration in all our work. It aims to elevate our storytelling by incorporating and utilizing more data as a foundational element for new stories.

A new tool to peer into fishing networks: Q&A with Austin Brush of C4ADS
- Washington, D.C.-based think tank C4ADS is launching Triton, a web tool to visually display the corporate structures behind fishing vessels.
- The initial cache of data focuses on the industrial fishing fleets of five key flag states: China, Taiwan, South Korea, Spain, and Japan, which together account for most high-seas fishing.
- Understanding who owns these vessels ultimately reveals the factors driving a vessel’s movements at sea and fishing activity, according to C4ADS analyst Austin Brush.

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.

Climate change isn’t fueling algal blooms the way we think, study shows
- A team of international researchers recently published the first global assessment of harmful algal blooms (HABs) — events in which toxic algae proliferate and cause harm to marine life and humans — based on nearly 10,000 recorded events between 1985 and 2018.
- The study found that there are no global trends that would suggest that climate change is having a uniform impact on HABs throughout the world, although this is a commonly held belief.
- The researchers were able to detect clearer regional trends that showed increases, decreases or no significant changes in HABs in certain parts of the world.
- It also found that there was a perceived increase in HABs amid the booming aquaculture industry, although the study does not necessarily suggest that aquaculture is causing an increase in HABs.

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.

A warming Arctic is changing animal migrations, decades of tracking shows
- The newly launched Arctic Animal Movement Archive (AAMA) includes 28 years of terrestrial and marine animal tracking studies on more than 96 species across the Arctic, Arctic marine, and subarctic (including boreal forests and taiga).
- “The Arctic is undergoing some of the most rapid climate change on the planet,” one author said. The resulting warmer winters, earlier spring snowmelt, and the loss of ice are affecting animal movement.
- Researchers conducted their first case studies using the AAMA and found large-scale patterns in the way caribou, moose, wolves, golden eagles, and bears are responding to climate change. The findings were published in the journal Science.
- In their analyses, researchers found that the northernmost herds of caribou have begun giving birth earlier in the spring. After mild winters, immature golden eagles arrived earlier in the spring to breeding grounds than adult birds.

A new dawn: The story of deforestation in the next decade must be different to the last (commentary)
- 2020 was to be the year when the bold commitment made by hundreds of companies to eliminate deforestation from their supply chains was met. Instead, the failure to achieve this goal can be measured by the sharp rise in deforestation since 2014.
- Yet despite this bleak picture – and the need to act being more urgent than ever – there’s another story to tell about the last decade.
- It’s the story of how the pledge to eliminate deforestation from supply chains by 2020 was doomed to fail. It’s also – perhaps surprisingly – about the immense journey some companies, NGOs, and institutions have made in that time and how the path to remove the stain of deforestation from the products we consume is now clearer than ever.
- This post is a commentary. The views expressed are those of the author, not necessarily Mongabay.

Rare plant species are especially vulnerable to climate change, and rarity is more common than previously understood
- Researchers from around the world spent 10 years compiling a database that now includes 20 million observational records of plant species occurrence, which they say is the largest dataset on botanical biodiversity ever created.
- They found that there are about 435,000 unique land plant species on planet Earth, and that a large fraction of them, 36.5% or some 158,535 species, can be considered “exceedingly rare,” meaning that they have only been observed and recorded anywhere in the world up to five times. In fact, 28.3% of the world’s plants, or 123,149 species, have been observed just three times or less, per the study.
- The research team found that rare species are clustered in a handful of rarity hotspots, and that global warming and the impacts of human land use are already disproportionately impacting the regions that harbor most of these rare plant species.

New assessment method finds close to one-third of tropical Africa’s plants are potentially facing extinction
- A new study, published today in the journal Science Advances, uses a novel methodology based on key components of the IUCN Red List’s assessment process to discern the potential conservation status of tropical flora at the continental scale.
- Researchers tested the new assessment method using the recently developed RAINBIO database, which consists of over 600,000 geo-referenced occurrence records of more than 20,000 vascular plant species in tropical Africa.
- The research team found that 17.3 percent of the 22,036 vascular plant species included in the study are likely threatened, while 14.4 percent are potentially threatened. That means that nearly one-third — 31.7 percent — of tropical Africa’s vascular plant species might be at risk of going extinct.

Sea Around Us: Global fisheries data and the goose that laid the golden egg (commentary)
- How did we get into a situation where fisheries are allowed to destroy the fish populations from which, given prudent management, high catches could be extracted on a sustainable basis?
- Having more boats in the water doesn’t produce more fish, and neither do subsidies, which enable fishing operations to break even as they overexploit the populations upon which they depend. It is as if we encouraged hunters to kill more geese and replaced their golden eggs with a subsidy (a.k.a. tax money diverted from the funding of our schools and hospitals).
- Many of the major trends in fisheries, notably the massive increase of their capacity and their geographic expansion, which for a long time compensated for the international, subsidy-driven competition for the fish that are left, can be seen only when fisheries are studied globally. With the Sea Around Us data set, it becomes possible for fisheries scientists working in developing countries to perform stock assessments of their major exploited species, and thus for fisheries departments throughout the world to meet the requirements that politicians have with regard to fisheries.
- This post is a commentary. The views expressed are those of the author, not necessarily Mongabay.

July 2019 was the hottest month ever recorded on Earth
- UN secretary general António Guterres announced that July 2019 was the hottest month on record in a press conference yesterday.
- In his remarks to the press, Guterres noted that the record-breaking July temperatures follow the hottest June ever recorded, adding: “This is even more significant because the previous hottest month, July 2016, occurred during one of the strongest El Niño’s ever. That is not the case this year. All of this means we are on track for the period from 2015 to 2019 to be the five hottest years on record.”
- The impacts of global climate change are being felt around the globe, perhaps nowhere more dramatically than in the Arctic, where high temperatures have caused sea ice levels to collapse. June 2019 saw near-record lows in Arctic sea ice extent.

On public interest in conservation and internet data (commentary)
- Conservationists can capture data and use it to generate useful insights for conservation on the relationship between humans and nature. Research in this area falls within the scope of the field of conservation culturomics, the study of human culture through the quantitative analysis of digital data.
- Several studies have used internet search-engine data to evaluate public interest in conservation. These studies were subjected to a few criticisms, however, including the fact that raw data are unavailable due to proprietary constraints. In response to these criticisms, a recent study proposed a methodological work-around — an important contribution that merits praise but should be interpreted with caution.
- Does this mean we should forfeit any hopes that internet data and digital methods can provide useful insights for conservation? Certainly not! The application of digital methods to conservation has immense potential, but also faces challenges inherent to any new development.
- This post is a commentary. The views expressed are those of the author, not necessarily Mongabay.

The world lost a Belgium-size area of old growth rainforest in 2018
- Newly released data indicate the tropics lost around 120,000 square kilometers (around 46,300 square miles) of tree cover last year – or an area of forest the size of Nicaragua.
- The data indicate 36,400 square kilometers of this loss – an area the size of Belgium – occurred in primary forest. This number is an increase over the annual average, and the third-highest amount since data collection began.
- Indonesia primary forest loss dropped to the lowest level recorded since 2002. Brazil’s numbers are also down compared to the last two years, but still higher than the 18-year average.
- Meanwhile, primary rainforest deforestation appears to be on the rise elsewhere. Colombia recorded the highest level since measurement began at the beginning of the century. Madagascar had the highest proportion of its tropical forest lost in 2018; Ghana experienced the biggest proportional change over 2017.

Wikipedia searches reveal how people’s interests in wildlife change
- By analyzing Wikipedia pages corresponding to nearly 32,000 species across 245 Wikipedia language editions, researchers have found that pageviews for more than a quarter of the species show seasonal patterns. This suggests people are paying attention to the animals and plants around them, researchers say.
- The study also found that views for species-related pages showed a lot more seasonality than random, non-species-related pages, suggesting that people tend to interact with wildlife in a more seasonal way than other aspects of their lives.
- The study, while identifying some interesting patterns, does not dig into the potential causes driving those patterns.
- What it does uncover are patterns of when, where and how people interact with nature, which, researchers say, can help guide conservation education and marketing campaigns.

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.

For conservationists, crowdfunding sites raise both funds and awareness
- A new study analyzes the use of online crowdfunding platforms for conservation efforts across the globe.
- Low-income countries are benefiting from supplementary funds for the conservation of biodiversity as a result of crowdfunding efforts thousands of miles away.
- As with traditional sources of conservation funding, however, much of the capital raised through crowdfunding goes toward a handful of “charismatic” species, including elephants and wolves.

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.

It’s time to strengthen the macroecology–conservation practice interface (commentary)
- Imagine being able to know how many individual organisms occur at any given time across areas as large as whole continents or even the entire globe. Though satellites may one day enable us to obtain this information directly, a sub-discipline of ecology — macroecology — currently represents the main tool to generate those estimates.
- With biodiversity under increasing pressure from human activities, macroecology can contribute greatly to the scientific evidence base for national and international decisions aimed at conserving biodiversity and ensuring a safe future for our planet.
- Yet, examples of macroecological research directly supporting conservation decisions remain rare. Why does a sizeable macroecology-conservation practice gap persist?
- This post is a commentary. The views expressed are those of the author, not necessarily Mongabay.

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.

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.

Online citizen science data platforms help scientists predict species ranges
- Researchers paired museum collection information for two species of spiders, dating back several decades, with more recent information from online citizen science databases and compared them to climate data to find areas with conditions suitable for each species.
- They developed maps of predicted geographic distributions for each species and, despite limited data, their findings suggest ranges of both species have shifted northward over time.
- The researchers highlight the importance of citizen science data in generating long-term data sets on species distributions.

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.

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.

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.

Making mountains out of molehills: system builds public-access big data from many sources
- How and where to store, manage, and share increasingly large data sets challenges scientists across disciplines.
- Like a library network for scientific data, the Data Observation Network for Earth (DataONE) links member data repositories to ensure open and secure access to well-described and easily discovered Earth observational data.
- The network provides guidelines and tools for researchers to document and preserve their data and make them available for future users to expand studies across time periods and locations.

Where one predator meets another: tracking sharks and fishing effort
- Fishing boats kill over 100 million sharks each year, many of which are caught unintentionally (bycatch) and may be discarded at sea without being recorded, so data on their mortality are poor.
- Researchers used satellite telemetry and publicly available global fishing locations in Global Fishing Watch to compare movements of 10 blue sharks to fishing activity in the northwest Atlantic Ocean.
- Within a 110-day period, two of the 10 tagged sharks surfaced near three different boats that were likely fishing, based on their movement patterns.
- The research team wants to better understand how fishing fleets can limit fishing in areas when and where sharks and other non-target species gather or migrate each year.

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.

GDELT: Mining and mapping global wildlife crime news
- The GDELT Project is a vast open-access tool that scours and live translates news media in 65 languages to quantify, describe and map broad societal trends worldwide.
- GDELT will harness data from even minor information sources to track and understand the incidents, players and networks of wildlife crime as it happens globally.
- This iteration of the platform, set to launch this fall, will eventually incorporate information from wildlife crime literature and wildlife protection organizations on the ground.

Wildlife biology in the 21st century
- Mark Hebblewhite studies the intersection of predator-prey dynamics and human impacts.
- Merging animal tracking data with remote-sensing information from satellites is “perhaps the most productive tool to answer large-scale questions about human impact on the planet.”
- Collecting and synthesizing information from many tracking studies allows researchers to quickly draw robust conclusions about large-scale ecological processes and human impacts.

Feeds: news | india | latam | brasil | indonesia