CompSustNet

Ranveer Chandra and Sudipta Sinha, Microsoft Research

Fri Feb 16, 2018, 1:30–2:30pm EST (UTC-5)

• video

Title: FarmBeats: AI & IoT for Agriculture

Abstract: Data-driven techniques can boost agricultural productivity by increasing yields, reducing losses and cutting down input costs. However, these techniques have seen low adoption due to high costs of sensors, manual data collection and limited connectivity solutions. We are developing an end-to-end IoT platform for agriculture called FarmBeats. Our system enables seamless data collection from various sensors, cameras and drones. Our system design explicitly accounts for weather related power and Internet outages, which has enabled six month long deployments in two US farms.

Bio: Ranveer Chandra is a Principal Researcher at Microsoft Research where he is leading an Incubation on IoT Applications. His research has shipped as part of multiple Microsoft products, including VirtualWiFi & low power Wi-Fi in Windows since 2009, Energy Profiler in Visual Studio, and the Wireless Controller Protocol for XBOX One. Ranveer is leading the FarmBeats, battery research, and TV white space projects at Microsoft Research. He has published over 80 papers, and filed over 100 patents, with over 80 granted by the USPTO. He has won several awards, including best paper awards at ACM CoNext 2008, ACM SIGCOMM 2009, IEEE RTSS 2014, USENIX ATC 2015, and Runtime Verification 2016 (RV'16), the Microsoft Research Graduate Fellowship, the Microsoft Gold Star Award, the MIT Technology Review's Top Innovators Under 35, TR35 (2010) and Fellow in Communications, World Technology Network (2012). Ranveer has an undergraduate degree from IIT Kharagpur, India and a PhD from Cornell University.

Sudipta Sinha is a researcher at Microsoft Research. He received his M.S. and Ph.D. degrees in Computer Science from the University of North Carolina at Chapel Hill in 2005 and 2009, respectively. His research interests lie broadly in computer vision and robotics. He works on topics related to 3D scene reconstruction from images and video such as structure from motion, SLAM, stereo, optical flow, scene flow, multi-view stereo, photometric stereo, image-based localization and 6D object detection and tracking. He is interested in applications ranging from dense 3D scanning, augmented reality (AR) and UAV-based aerial photogrammetry and dense 3D mapping. He was a member of the UNC Chapel Hill team that received the best demo award at CVPR 2007 for one of the first scalable, real-time, vision-based urban 3D reconstruction systems. He has served as a program co-chair for 3DV 2017, was/is an area chair for 3DV 2016, ICCV 2017 and 3DV 2018 and has served on program committees at computer vision conferences. He is also an associate editor for the Computer Vision and Image Understanding (CVIU) Journal.

Tanya Berger-Wolf, University of Illinois

Fri Mar 2, 2018, 1:30–2:30pm EST (UTC-5)

• video

Title: Computational Behavioral Ecology

Abstract: Computation has fundamentally changed the way we study nature. New data collection technology, such as GPS, high definition cameras, UAVs, genotyping, and crowdsourcing, are generating data about wild populations that are orders of magnitude richer than any previously collected. Unfortunately, in this domain as in many others, our ability to analyze data lags substantially behind our ability to collect it. In this talk I will show how computational approaches can be part of every stage of the scientific process of studying animals, from intelligent data collection (crowdsourcing photographs and identifying individual animals from photographs by stripes and spots) to hypothesis formulation (by designing a novel computational framework for analysis of dynamic social networks), and provide scientific insight into collective behavior of zebras, baboons, and other social animals.

Bio: Dr. Tanya Berger-Wolf is a Professor of Computer Science at the University of Illinois at Chicago, where she heads the Computational Population Biology Lab. As a computational ecologist, her research is at the unique intersection of computer science, population biology, and social sciences. Berger-Wolf is also a co-founder of the conservation software non-profit Wildbook, which recently enabled a historic complete species census of the endangered Grevy's zebra, using photographs taken by ordinary citizens in Kenya.

Berger-Wolf holds a Ph.D. in Computer Science from the University of Illinois at Urbana-Champaign. She has received numerous awards for her research and mentoring, including the US National Science Foundation CAREER Award, Association for Women in Science Chicago Innovator Award, and the UIC Mentor of the Year Award.

John Selker, Oregon State University

Fri Mar 16, 2018, 1:30–2:30pm EDT (UTC-4)

• video

Title: The TAHMO Model for African Climate Observation. The Science, Politics, and Business of Sustainable Observation

Abstract: Current weather forecasts in Africa are largely unavailable and otherwise unreliable. Selker will discuss his work to establish real-time reporting weather stations in sub-Saharan Africa, including the instrumentation of 500 stations in 20 African countries. TAHMO aspires to place 20,000 low-cost weather stations across Africa to make it the most densely observed continent on earth. Selker also will review the TAHMO.org school-to-school educational program (School2School.net) designed to help inspire the next generation of climate scientists in Africa through observations made directly at their school, while providing a safe place to locate the weather stations.

Bio: John Selker, OSU Distinguished Professor of Biological and Ecological Engineering (27 years) and co-Director of both CTEMPs.org and TAHMO.org, and PI of the OPEnS Lab (Open-Sensing.org) has worked USA, Kenya, Somalia, Sri Lanka, Canada, Chile, and England and carried out research in Chile, Ghana, Senegal, Israel, China, and 10 European countries. He served as editor of Water Resources Research. Published 185 peer-reviewed articles on hydrological science, with expertise in physical hydrology and instrumentation. In 2013 he was elected Fellow of the American Geophysical Union, and 2013 received the John Hem Award for Science and Technology from the American Groundwater Association.

Scott Worland, U.S. Geological Survey

Fri Apr 13, 2018, 1:30–2:30pm EDT (UTC-4)

• video

Title: Exploring the drivers of municipal water use in the U.S. using hierarchical-Bayesian models

Abstract: Population growth and climate change are often cited as the likely drivers of future increases in municipal water withdrawals in the U.S. Are there other important explanatory variables? Are the relationships between water-use and explanatory variables uniform across the nation? This talk explores these questions by analyzing the relationship between municipal water-use and multiple environmental, social, economic, behavioural, and policy variables in addition to population growth and changes in the local climate. These additional variables include, among others, water yield, income inequality, regional price parity, education attainment, voting habits, water price, and water conservation policies. We also explore how three different grouping variables (climate region, urban class, and primary economic sector) affect the associations between water-use and the explanatory variables. The results indicate that most important explanatory variables are average precipitation, person per household, partisan voting, water price, and regional price parity. Although, the results also suggests that the controls on water use are not uniform across the contiguous U.S., and national-scale water use assessments must account for regional variability in order to understand the present drivers of water use, and project likely changes for the future.

Bio: Scott Worland is a statistical hydrologist with the U.S. Geological Survey. His research interests include interdisciplinary research, machine learning, and Bayesian statistics.

Vipin Kumar, University of Minnesota

Fri Apr 27, 2018, 1:30–2:30pm EDT (UTC-4)

• video

Title: Big Data in Climate and Earth Sciences: Challenges and Opportunities for Machine Learning

Abstract: The climate and earth sciences have recently undergone a rapid transformation from a data-poor to a data-rich environment. In particular, massive amount of data about Earth and its environment is now continuously being generated by a large number of Earth observing satellites as well as physics-based earth system models running on large-scale computational platforms. These massive and information-rich datasets offer huge potential for understanding how the Earth's climate and ecosystem have been changing and how they are being impacted by human actions. This talk will discuss various challenges involved in analyzing these massive data sets as well as opportunities they present for both advancing machine learning as well as the science of climate change in the context of monitoring the state of the tropical forests and surface water on a global scale.

Bio: Vipin Kumar is a Regents Professor and holds William Norris Chair in the department of Computer Science and Engineering at the University of Minnesota. His research interests include data mining, high-performance computing, and their applications in Climate/Ecosystems and health care. He is currently leading an NSF Expedition project on understanding climate change using data science approaches. His research has resulted in the development of the concept of isoefficiency metric for evaluating the scalability of parallel algorithms, as well as highly efficient parallel algorithms and software for sparse matrix factorization (PSPASES) and graph partitioning (METIS, ParMetis, hMetis). He has authored over 300 research articles, and co-edited or coauthored 10 books including the widely used text book "Introduction to Parallel Computing", and "Introduction to Data Mining". Kumar has served as chair/co-chair for many international conferences and workshops in the area of data mining and parallel computing, including 2015 IEEE International Conference on Big Data, IEEE International Conference on Data Mining (2002), and International Parallel and Distributed Processing Symposium (2001). Kumar is a Fellow of the ACM, IEEE, AAAS, and SIAM. Kumar's research has been honored by the ACM SIGKDD 2012 Innovation Award, which is the highest award for technical excellence in the field of Knowledge Discovery and Data Mining (KDD), and the 2016 IEEE Computer Society Sidney Fernbach Award, one of IEEE Computer Society's highest awards in high performance computing.