Download Research Tools
Big Data: these words are on the lips of researchers everywhere these days. But it’s more than a catch phrase—it’s a reality in the burgeoning world of eScience, as investigators strive to make sense of the seemingly endless flow of new information. Nowhere is the push to understand Big Data stronger than in Brazil, where scientists have been working to better understand tropical ecosystems, human impact on the environment, biogenetics, and biodiversity. These efforts are providing new opportunities to improve our capabilities in data-intensive research and strengthen Latin America’s eScience research community. To further these efforts, FAPESP—the São Paulo Research Foundation—and Microsoft Research Connections are jointly hosting a special eScience Workshop from May 13 to 15, 2013, in the city of São Paulo, Brazil. The event will bring together more than 150 participants—including students and researchers from around the world—to explore collaboration and research opportunities in the environmental sciences, bioenergy, biodiversity, health, and digital humanities.
Along with informative sessions on such topics as data mining, computational ecology, the genetic basis of disease, eScience in the cloud, and computer vision, the workshop will feature tutorials on Layerscape, FetchClimate, and Filzbach, Microsoft Research’s “killer apps” for data visualization and storytelling in the earth sciences, environmental modeling, and Bayesian analysis. Keynote speakers will include Maria Cristina Ferreira de Oliveira of the University of São Paulo, who will discuss the challenges of making sense of multidimensional data, and Carole Goble of the University of Manchester, who will explore the reproducibility of experimental findings in the computational sciences.
Another keynote speaker, Drew Purves of Microsoft Research Cambridge, will talk about predicting the future of life on Earth. And apropos of that topic, the workshop will also feature a presentation on LiveANDES (Advanced Network for the Distribution of Endangered Species), the new tool designed to collect, house, and analyze data about Latin America’s threatened wildlife.
All of this, plus demos of the latest eScience tools and findings from FAPESP and Microsoft Research, are certain to make the Latin America eScience Workshop 2013 a memorable and informative event. I hope to see you there!
–Juliana Salles, Senior Research Program Manager in Brazil, Microsoft Research Connections
Standing on the banks of the Seine, I found myself marveling at the beauty of “April in Paris” (cue the 1930s song). Perhaps it was the scent of the flowers in bloom in the Jardin du Luxembourg or the warmth of the Continental spring. But, most likely, my contentment stemmed from the success of the just-completed Microsoft Research Machine Learning Summit, which took place April 22 to 24 in the “City of Light” on Le Campus de Microsoft France.
The event brought together more than 230 attendees and presenters, including thought leaders from computer science, engineering, statistics, and mathematics. Through keynotes, demos, and panel discussions, we highlighted some of the key challenges in this new era of machine learning and explored the next generation of approaches, techniques, and tools that researchers and scientists need to exploit the information revolution for the benefit of society.
As exciting as the in-person event was, I was equally enthused by the reception of our streaming broadcast of key presentations and interviews, which was viewed by some 3,000 people around the globe. The live, online presentation not only made it possible for many more people to view the summit, it gave a broader group of students and researchers an opportunity to engage directly with some of the top experts in the field of machine learning, including Andrew Blake, director of Microsoft Research Cambridge, and Judea Pearl, professor emeritus at UCLA. I was pleased that many from the online audience posed questions about computer vision to Professor Blake, and difficult questions about probability and causality to Professor Pearl.
There was hardly an area of machine learning that wasn’t explored in depth at the summit—from the aforementioned topics of computer vision and causality, to insightful presentations on Bayesian statistics and the use of machine learning techniques in the realm of social media and large-scale learning.
Of course the food was outstanding (it was Paris, after all), and meals were made all the more enjoyable by the stimulating conversation of our companions and the spectacular views of Paris from the thirty-fourth floor of our hotel. But for me, the most exciting moments were the intense discussions I observed taking place during breaks and the social events, and the sense that seeds of exciting new ideas were being planted that would germinate in the months and years ahead.
—Chris Bishop, Distinguished Scientist, Microsoft Research Cambridge
Watch the video with Spanish subtitles
In the late 1800s, the guanaco, a close relative of the llama, was hunted to near extinction. As we mark this year’s Earth Day (April 22), I want to share my excitement about a new tool that looks to make the future a little brighter for the guanaco and other threatened species in Latin America. That new tool is LiveANDES (Advanced Network for the Distribution of Endangered Species).
Developed by a partnership among researchers at the Pontifical Catholic University of Chile, the LACCIR (Latin American and Caribbean Collaborative ICT Research) Virtual Institute, and Microsoft Research, LiveANDES is designed to collect, house, and analyze data about Latin America’s wildlife—data that could prove vital to the preservation of the region’s rich but increasingly threatened biodiversity, which has suffered grievously from loss of habitat and climate change.
Mariano de la Maza, a wildlife officer in Chile’s Parks and Protected Areas Service, sees this decline on a daily basis. “The main problems of the Chilean forest are habitat loss and the fragmentation and degradation of native forests,” he says.
LiveANDES begins with field observations, made not just by wildlife biologists and park rangers but by “citizen scientists,” including hikers, eco-tourists, and other nature enthusiasts. As Cristian Bonacic, director of the wildlife laboratory at Pontifical Catholic University, notes, “When people go to the wild, they can encounter an endangered animal by chance.” These chance encounters can provide extremely valuable information about the location and status of threatened and endangered wildlife.
All that’s needed is a smartphone equipped with the LiveANDES app. Imagine you’re hiking in the Chilean countryside, and you think you’ve spotted a rare species. You simply take its picture with your smartphone and upload the picture and any sighting comments into LiveANDES. Your photo and annotations, along with the phone’s recognition of your geographical location and a time stamp, are then logged into the LiveANDES database, ready for parsing by the university team.
Once processed, the data becomes available to scientists locally and around the world, as well as to the public, in both Spanish and English. Bonacic praises LiveANDES for the way it helps researchers “share that information with the scientific community, park rangers, and people at large.”
Knowing where and under what circumstances a threatened species is living can help biologists devise strategies to stabilize and, one hopes, restore these vulnerable populations. Moreover, the information gathered in LiveANDES also will help keep the International Union for Conservation of Nature (IUCN) red list of endangered and threatened species accurate, complete, and up-to-date.
The LiveANDES platform was built by using Microsoft technologies, including Windows Phone, Microsoft SQL Server data management software, and Bing Maps for locating and visualizing the animals, and the Microsoft .NET Framework for programming. It not only houses data about Latin America’s wildlife, including photographs, audio and video recordings, and location and sighting data, but it also makes parsing huge volumes of data manageable for researchers. According to Ignacio Casas, the executive director of LACCIR, LiveANDES integrates with the fourth paradigm, a foundational concept of eScience, in which data-intensive computing facilitates scientific discovery. LiveANDES is designed to make parsing the huge volumes of data recorded manageable for researchers.
Bonacic and his colleagues look forward to receiving a barrage of wildlife data from rangers, biologists, and, of course, citizen scientists. Thanks to LiveANDES, this data deluge will be manageable and actionable.
I am inspired by this project, as it tackles an extremely challenging environmental problem, which is the rapid decline of important elements of our natural heritage. Each animal species is an important piece of a puzzle, and each citizen scientist and researcher can play a crucial role in the preservation of endangered species for the next generation. I’m hopeful that LiveANDES will help the guanaco and other vulnerable species survive to see Earth Day 2113!
—Jaime Puente, Director, Latin America and the Caribbean, Microsoft Research Connections