Indris located on Madagascar. Credit: Cornell University
What a face! And, it introduces you to the latest from Cornell University’s College of Agriculture and Life Sciences’ (CALS), from a February 26, 2018 news item on phys.org,
Musicians have long drawn inspiration from nature, but a new online game is taking that connection one step further. “Beastbox” takes sound clips from real wild animals, transforms them into loops, and allows users to mix and match them into an endless variety of beats, breaks and drops. Along the way, players learn about the animals and the ecosystems they belong to.
The free game is the result of a collaboration among the Cornell Lab of Ornithology, the Cornell Hip Hop Collection and Ben Mirin, a sound artist and beatboxer whose career as a “wildlife DJ” inspired the project.
“‘BeastBox’ is a surprise mashup brought to you by scientists, musicians, designers, animators and coders,” says Mya Thompson, leader of the Cornell Lab of Ornithology’s Bird Academy project. “It’s dedicated to the idea that we could all use a few minutes to appreciate our musical planet. When I first met Ben Mirin, I knew we could take his wildlife DJ concept to a new level – and ‘BeastBox’ is what came out.”
By bringing animals from the same ecosystem together on the virtual stage, players can unlock “Beastmode” and control the moves of animal characters as they dance to Mirin’s music. Each bonus track is created exclusively from sounds recorded in six ecosystems including the Madagascar rainforest, the Great Barrier Reef and the Sonoran desert. Fun for all ages, “BeastBox” celebrates the musicality and biodiversity of our planet and encourages fans of music to become fans of wildlife.
“BeastBox” highlights two of Cornell’s world-renowned collections: The Cornell Lab of Ornithology’s Macaulay Library and the Cornell Hip Hop Collection. The Macaulay Library is the world’s premier scientific archive of natural history audio, video and photographs. Many of the sounds players encounter in the game are archived in the library. Players who complete at least one ecosystem puzzle win the opportunity to download 20 wild animal sounds from the Macaulay Library collection.
Founded in 2007, Cornell’s Hip Hop Collection is the largest research archive on hip-hop culture in the world and is part of Cornell University Library’s Division of Rare and Manuscript Collections. “BeastBox” players are encouraged to browse the archive to better understand the cultural roots of beatboxing and hip-hop.
Here’s an April 11, 2015 TEDxNYU (New York University) talk by Ben Mirin (published on YouTube June 5, 2017),
After all these years of writing about geckos and their adhesive properties (they can hang off a wall or ceiling by a single toe), I’ve developed a mild interest in them. From a Feb. 7, 2017 posting by Dirk Steinke for the One species a day blog,
The new species was found in northern Madagascar and its name was build [sic] from the two Greek stems mégas, meaning ‘very large’ and lepís, meaning ‘scale’, and refers to the large size of the scales of this species in comparison to other geckos.
Caption: The new fish-scale gecko, Geckolepis megalepis, has the largest body scales of all geckos. This nocturnal lizard was discovered in the ‘tsingy’ karst formations in northern Madagascar Credit: F. Glaw
Many lizards can drop their tails when grabbed, but one group of geckos has gone to particularly extreme lengths to escape predation. Fish-scale geckos in the genus Geckolepis have large scales that tear away with ease, leaving them free to escape whilst the predator is left with a mouth full of scales. Scientists have now described a new species (Geckolepis megalepis) that is the master of this art, possessing the largest scales of any gecko.
The skin of fish-scale geckos is specially adapted to tearing. The large scales are attached only by a relatively narrow region that tears with ease, and beneath them they have a pre-formed splitting zone within the skin itself. Together, these features make them especially good at escaping from predators. Although several other geckos are able to lose their skin like this if they are grasped really firmly, Geckolepis are apparently able to do it actively, and at the slightest touch. And while others might take a long time to regenerate their scales, fish-scale geckos can grow them back, scar-free, in a matter of weeks.
This remarkable (if somewhat gruesome) ability has made these geckos a serious challenge to the scientists who want to study them. Early researchers described how it was necessary to catch them with bundles of cotton wool, to avoid them losing almost all of their skin. Today, little has changed, and researchers try to catch them without touching them if possible, by luring them into plastic bags. But once they are caught, the challenges are not over; identifying and describing them is even harder.
“A study a few years ago showed that our understanding of the diversity of fish-scale geckos was totally inadequate,” says Mark D. Scherz, lead author of the new study and PhD student at the Ludwig Maximilian University of Munich and Zoologische Staatssammlung München, “it showed us that there were actually about thirteen highly distinct genetic lineages in this genus, and not just the three or four species we thought existed. One of the divergent lineages they identified was immediately obvious as a new species, because it had such massive scales. But to name it, we had to find additional reliable characteristics that distinguish it from the other species.” A challenging task indeed: one of the main ways reptile species can be told apart is by their scale patterns, but these geckos lose their scales with such ease that the patterns are often lost by the time they reach adulthood. “You have to think a bit outside the box with Geckolepis. They’re a nightmare to identify. So we turned to micro-CT to get at their skeletons and search there for identifying features.” Micro-CT (micro-computed tomography) is essentially a 3D x-ray of an object. This method is allowing morphologists like Scherz to examine the skeletons of animals without having to dissect them, opening up new approaches to quickly study the internal morphology of animals.
By looking at the skeletons of the geckos, the team was able to identify some features of the skull that distinguish their new species from all others. But they also found some surprises; a species named 150 years ago, Geckolepis maculata, was confirmed to be different from the genetic lineage that it had been thought to be. “This is just typical of Geckolepis. You think you have them sorted out, but then you get a result that turns your hypothesis on its head. We still have no idea what Geckolepis maculata really is–we are just getting more and more certain what it’s not.”
The new species, Geckolepis megalepis, which was described by researchers from the US, Germany, and Columbia [sic] in a paper published today in the open access journal PeerJ, is most remarkable because of its huge scales, which are by far the largest of any gecko. The researchers hypothesize that the larger scales tear more easily than smaller scales, because of their greater surface area relative to the attachment area, and larger friction surface. “What’s really remarkable though is that these scales–which are really dense and may even be bony, and must be quite energetically costly to produce–and the skin beneath them tear away with such ease, and can be regenerated quickly and without a scar,” says Scherz. The mechanism for regeneration, which is not well understood, could potentially have applications in human medicine, where regeneration research is already being informed by studies on salamander limbs and lizard tails.
For anyone unfamiliar with ‘gecko research’, scientists are fascinated by their abilities and have been researching them (in a field known as biomimicry or bioinspired engineering or biomimetics) for years with the hope of mimicking those abilities for new applications. You can check out a March 19, 2015 posting or this July 10, 2014 posting for examples or you can search ‘gecko’ on this blog for more examples.
A century ago, more than 60,000 tigers roamed the wild. Today, the worldwide estimate has dwindled to around 3,200. Poaching is one of the main drivers of this precipitous drop. Whether killed for skins, medicine or trophy hunting, humans have pushed tigers to near-extinction. The same applies to other large animal species like elephants and rhinoceros that play unique and crucial roles in the ecosystems where they live.
Human patrols serve as the most direct form of protection of endangered animals, especially in large national parks. However, protection agencies have limited resources for patrols.
With support from the National Science Foundation (NSF) and the Army Research Office, researchers are using artificial intelligence (AI) and game theory to solve poaching, illegal logging and other problems worldwide, in collaboration with researchers and conservationists in the U.S., Singapore, Netherlands and Malaysia.
“In most parks, ranger patrols are poorly planned, reactive rather than pro-active, and habitual,” according to Fei Fang, a Ph.D. candidate in the computer science department at the University of Southern California (USC).
Fang is part of an NSF-funded team at USC led by Milind Tambe, professor of computer science and industrial and systems engineering and director of the Teamcore Research Group on Agents and Multiagent Systems.
Their research builds on the idea of “green security games” — the application of game theory to wildlife protection. Game theory uses mathematical and computer models of conflict and cooperation between rational decision-makers to predict the behavior of adversaries and plan optimal approaches for containment. The Coast Guard and Transportation Security Administration have used similar methods developed by Tambe and others to protect airports and waterways.
“This research is a step in demonstrating that AI can have a really significant positive impact on society and allow us to assist humanity in solving some of the major challenges we face,” Tambe said.
PAWS puts the claws in anti-poaching
The team presented papers describing how they use their methods to improve the success of human patrols around the world at the AAAI Conference on Artificial Intelligence in February .
The researchers first created an AI-driven application called PAWS (Protection Assistant for Wildlife Security) in 2013 and tested the application in Uganda and Malaysia in 2014. Pilot implementations of PAWS revealed some limitations, but also led to significant improvements.
Here’s a video describing the issues and PAWS,
For those who prefer to read about details rather listen, there’s more from the news release,
PAWS uses data on past patrols and evidence of poaching. As it receives more data, the system “learns” and improves its patrol planning. Already, the system has led to more observations of poacher activities per kilometer.
Its key technical advance lies in its ability to incorporate complex terrain information, including the topography of protected areas. That results in practical patrol routes that minimize elevation changes, saving time and energy. Moreover, the system can also take into account the natural transit paths that have the most animal traffic – and thus the most poaching – creating a “street map” for patrols.
“We need to provide actual patrol routes that can be practically followed,” Fang said. “These routes need to go back to a base camp and the patrols can’t be too long. We list all possible patrol routes and then determine which is most effective.”
The application also randomizes patrols to avoid falling into predictable patterns.
“If the poachers observe that patrols go to some areas more often than others, then the poachers place their snares elsewhere,” Fang said.
Since 2015, two non-governmental organizations, Panthera and Rimbat, have used PAWS to protect forests in Malaysia. The research won the Innovative Applications of Artificial Intelligence award for deployed application, as one of the best AI applications with measurable benefits.
The team recently combined PAWS with a new tool called CAPTURE (Comprehensive Anti-Poaching Tool with Temporal and Observation Uncertainty Reasoning) that predicts attacking probability even more accurately.
In addition to helping patrols find poachers, the tools may assist them with intercepting trafficked wildlife products and other high-risk cargo, adding another layer to wildlife protection. The researchers are in conversations with wildlife authorities in Uganda to deploy the system later this year. They will present their findings at the 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016) in May.
“There is an urgent need to protect the natural resources and wildlife on our beautiful planet, and we computer scientists can help in various ways,” Fang said. “Our work on PAWS addresses one facet of the problem, improving the efficiency of patrols to combat poaching.”
There is yet another potential use for PAWS, the prevention of illegal logging,
While Fang and her colleagues work to develop effective anti-poaching patrol planning systems, other members of the USC team are developing complementary methods to prevent illegal logging, a major economic and environmental problem for many developing countries.
The World Wildlife Fund estimates trade in illegally harvested timber to be worth between $30 billion and $100 billion annually. The practice also threatens ancient forests and critical habitats for wildlife.
Researchers at USC, the University of Texas at El Paso and Michigan State University recently partnered with the non-profit organization Alliance Vohoary Gasy to limit the illegal logging of rosewood and ebony trees in Madagascar, which has caused a loss of forest cover on the island nation.
Forest protection agencies also face limited budgets and must cover large areas, making sound investments in security resources critical.
The research team worked to determine the balance of security resources in which Madagascar should invest to maximize protection, and to figure out how to best deploy those resources.
Past work in game theory-based security typically involved specified teams — the security workers assigned to airport checkpoints, for example, or the air marshals deployed on flight tours. Finding optimal security solutions for those scenarios is difficult; a solution involving an open-ended team had not previously been feasible.
To solve this problem, the researchers developed a new method called SORT (Simultaneous Optimization of Resource Teams) that they have been experimentally validating using real data from Madagascar.
The research team created maps of the national parks, modeled the costs of all possible security resources using local salaries and budgets, and computed the best combination of resources given these conditions.
“We compared the value of using an optimal team determined by our algorithm versus a randomly chosen team and the algorithm did significantly better,” said Sara Mc Carthy, a Ph.D. student in computer science at USC.
The algorithm is simple and fast, and can be generalized to other national parks with different characteristics. The team is working to deploy it in Madagascar in association with the Alliance Vohoary Gasy.
“I am very proud of what my PhD students Fei Fang and Sara Mc Carthy have accomplished in this research on AI for wildlife security and forest protection,” said Tambe, the team lead. “Interdisciplinary collaboration with practitioners in the field was key in this research and allowed us to improve our research in artificial intelligence.”
Moreover, the project shows other computer science researchers the potential impact of applying their research to the world’s problems.
“This work is not only important because of the direct beneficial impact that it has on the environment, protecting wildlife and forests, but on the way that it can inspire other to dedicate their efforts into making the world a better place,” Mc Carthy said.
The curious can find out more about Panthera here and about Alliance Vohoary Gasy here (be prepared to use your French language skills). Unfortunately, I could not find more information about Rimbat.