Earth Day at KDD
Earth is home to all of us as well as millions of species. However, our beloved planet and civilization is facing major challenges from climate change and environmental degradation, growing demands for food, energy, and water, among other challenges. Extreme events are becoming more severe and more frequent. Surface and groundwater have more pollution, and greenhouse gases have increased in the atmosphere. Moreover, the largest freshwater source on Earth, polar ice-caps and glaciers, are melting and leading to sea-level rise.
Knowledge discovery and data mining (KDD) is crucial to addressing these and other challenges facing our changing planet. Earth data have unique characteristics that are pushing new research in challenges such as spatiotemporal autocorrelation, spatial variability, scale- dependence, modifiable areal unit problems, etc.
The 2020 KDD Earth Day will focus on the impact of these advances on climate, ecosystems, food production, energy, and water, and the broader effects on health, safety, urban environments, transportation, and other areas of societal importance.
The 2020 KDD Earth Day will bring together thought leaders in academia, industry, and government to explore these topics and discuss opportunities to overcome the challenges that Earth faces today.
The program features two keynote sessions, each with two speakers and a closing discussion with Q/A. The program also includes workshop sessions on related research on time series and spatiotemporal data as well as applications to sustainability, policy, and urban areas.
8:00am - 10am Earth Day Keynote Session I
08:00-08:05 am Earth Day welcome and overview
08:05-08:50 am Keynote Talk: Carla Gomes, Cornell University
- Computational Sustainability: Computing for a Better World and a Sustainable Future AI for Advancing Scientific Discovery for a Sustainable Future
08:55-09:40 am Keynote Talk: George Karniadakis, Brown University
- Physics-Informed Neural Networks (PINNs)
09:40-10:00 am Panel Q&A with Carla Gomes and George Karniadakis
10:00-03:00 pm Break to attend Earth-Day-related talks at other workshops (please see below*)
3:00pm-5:00pm Earth Day Keynote Session II
03:00-03:45 pm Keynote Talk: David Hall, NVIDIA
- Machine Learning and the Earth Applying AI to address some of the world greatest challenges
03:50-04:35 pm Keynote Talk: Marta Gonzalez, UC Berkeley
- Unraveling the interplay of the urban form, mobility and social mixing in the light of the COVID19 pandemic
04:35-04:55 pm Panel Q&A with David Hall and Marta Gonzalez
04:55-05:00 pm Earth Day summary and closing
Earth Day Recommended Workshop Sessions
* Earth Day 2020 is primarily affiliated with the workshop: Fragile Earth: Data Science for a Sustainable Planet. We also encourage Earth Day attendees to check out relevant talks at the following KDD workshops:
- Humanitarian Mapping: Harnessing Data and Human-Machine Intelligence for Actionable Policy Decisions
- 1st KDD Workshop on Deep Learning for Spatiotemporal Data, Applications, and Systems (DeepSpatial)
- The 9th SIGKDD International Workshop on Urban Computing
- 6th Workshop on Mining and Learning from Time Series
Plenary Keynote Speaker
Computational Sustainability: Computing for a Better World and a Sustainable Future
Artificial Intelligence (AI) is a rapidly advancing field. Novel machine learning methods combined with reasoning and search techniques have led us to reach new milestones: from computer vision, machine translation, and Go and Chess world-champion level play using pure self-training strategies, to self-driving cars. These ever-expanding AI capabilities open up new exciting avenues for advances in new domains. I will discuss our AI research for advancing scientific discovery for a sustainable future. In particular, I will talk about our research in a new interdisciplinary field, Computational Sustainability, which has the overarching goal of developing computational models and methods to help manage the balance between environmental, economic, and societal needs for a sustainable future. I will provide examples of computational sustainability problems, ranging from biodiversity and wildlife conservation, to multi-criteria strategic planning of hydropower dams in the Amazon basin and materials discovery for renewable energy materials. I will also highlight cross-cutting computational themes and challenges for AI at the intersection of constraint reasoning, optimization, machine learning, multi-agent reasoning, citizen science, and crowd-sourcing.
Bio: Carla Gomes is the Ronald C. and Antonia V. Nielsen Professor of Computing and Information Science and the director of the Institute for Computational Sustainability at Cornell University. Gomes received a Ph.D. in computer science in the area of artificial intelligence from the University of Edinburgh. Her research area is Artificial Intelligence with a focus on large-scale constraint reasoning, optimization, and machine learning. Recently, Gomes has become deeply immersed in research on scientific discovery for a sustainable future and more generally in research in the new field of Computational Sustainability. Computational Sustainability aims to develop computational methods to help solve some of the key challenges concerning environmental, economic, and societal issues in order to help put us on a path towards a sustainable future. Gomes is the lead PI of an NSF Expeditions in Computing award Gomes has (co-)authored over 150 publications, which have appeared in venues spanning Nature, Science, and a variety of conferences and journals in AI and Computer Science, including five best paper awards. Her research group has been supported by over $50M in basic research funds. Gomes is a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI), a Fellow of the Association for Computing Machinery (ACM), and a Fellow of American Association for the Advancement of Science (AAAS).
Physics-Informed Neural Networks (PINNs)
We will present a new approach to develop a data-driven, learning-based framework for predicting outcomes of physical and geophysical systems and for discovering hidden physics from noisy data. We will introduce a deep learning approach based on neural networks (NNs) and generative adversarial networks (GANs). We also introduce new NNs that learn functionals and nonlinear operators from functions and corresponding responses for system identification. Unlike other approaches that rely on big data, here we “learn” from small data by exploiting the information provided by the physical conservation laws, which are used to obtain informative priors or regularize the neural networks. We will also make connections between Gauss Process Regression and NNs, and discuss the new powerful concept of meta- learning. We will demonstrate the power of PINNs for several inverse problems, and we will demonstrate how we can use multi-fidelity modeling in monitoring ocean acidification levels in the Massachusetts Bay.. There are many versions of PINNs, e.g., variational (VPINNs), stochastic (sPINNs), conservative (cPINNs), nonlocal (nPINNs), generalized (xPINNs), etc, and we will provide some highlights. In addition, we will present our recent theoretical results on the convergence and generalization of PINNs.
Bio: George Karniadakis is from Crete. He received his S.M. and Ph.D. from Massachusetts Institute of Technology (1984/87). He was appointed Lecturer in the Department of Mechanical Engineering at MIT and subsequently he joined the Center for Turbulence Research at Stanford / Nasa Ames. He joined Princeton University as Assistant Professor in the Department of Mechanical and Aerospace Engineering and as Associate Faculty in the Program of Applied and Computational Mathematics. He was a Visiting Professor at Caltech in 1993 in the Aeronautics Department and joined Brown University as Associate Professor of Applied Mathematics in the Center for Fluid Mechanics in 1994. After becoming a full professor in 1996, he continues to be a Visiting Professor and Senior Lecturer of Ocean/Mechanical Engineering at MIT. He is an AAAS Fellow (2018-), Fellow of the Society for Industrial and Applied Mathematics (SIAM, 2010-), Fellow of the American Physical Society (APS, 2004-), Fellow of the American Society of Mechanical Engineers (ASME, 2003-) and Associate Fellow of the American Institute of Aeronautics and Astronautics (AIAA, 2006-). He received the Alexander von Humboldt award in 2017, the Ralf E Kleinman award from SIAM (2015), the J. Tinsley Oden Medal (2013), and the CFD award (2007) by the US Association in Computational Mechanics. His h-index is 101 and he has been cited over 50,000 times.
Machine Learning and the Earth: Applying AI to address some of the world greatest challenges
Machine learning allows us to build tools and applications that were previously beyond the reach of even the most skillful software engineer. With these new capabilities, we can build most anything we want. But how should we use them? In this talk, I describe my personal perspective on this question. Forging a positive future means tackling many important global problems simultaneously including, but not limited to: minimizing climate change, dealing with the impacts of extreme weather events, monitoring the biosphere, ensuring an adequate food supply, and achieving global consensus. Machine learning can contribute materially to each of these challenges, and I will present an overview of some of the recent research in these areas. Finally, I address the potential risks and rewards of machine learning itself, as the risks of machine learning are as great as its potential rewards.
Bio: David Hall has been employed as a Data Scientist at NVIDIA since January 2018. Previously, Dr. Hall has worked as an Assistant Professor of Research in Computer Science at CU Boulder, as a Research Scientist at NCAR, and as a software engineer for several companies. Dr. Hall has technical expertise in theoretical physics, computational fluid dynamics, remote sensing, numerical methods, weather and climate modeling, and artificial intelligence. Before joining NVIDIA, Dr. Hall spent much of the previous decade developing numerical techniques to improve the atmospheric components of the CESM and E3SM global climate models. In his current position, his primary role is to translate the latest breakthroughs in artificial intelligence into practical solutions for science, and to help train and educate researchers in the use of these techniques. Dr. Hall earned a PhD in Soft Condensed-Matter Physics from the University of Santa Barbara, CA and a BA in Physics from CU Boulder.
Unraveling the interplay of the urban form, mobility and social mixing in the light of the COVID19 pandemic
I present how to use data science to support urban planning decisions in the covid19 era. First, via mobile phone data for twenty cities around the world, we study how the distance covered by individuals (r g ) varies as the location of their residences moves away from the central business district (CBD). We show that the changes in the statistical distribution of r g between the inner city and the residents of the suburbs classify the centrality of cities better than the population distributions alone. In turn, we propose metrics of urban form and mobility based on r g . We then show how these different urban metrics based on density, mobility, and mixing patterns help to predict the infective reproduction number (R 0 ) of COVID-19 in eleven Spanish cities, before and during the changing percentages of mobility lock-down. I close mentioning other promising research lines that use informed by approaches of data science in the covid19 era, such as planning the growth of bicycle infrastructures, and the use of credit card transactions to identify behavioral groups.
Bio: Marta Gonzalez works in the urban science space, with a focus on the intersections between people within social networks and the built and natural environments. Her goal is to design urban solutions through new technologies. To that end, she has developed tools that impact transportation research and discovered novel approaches to model human mobility and the adoption of energy technologies. Her scientific approach is informed by the statistical physics of complex systems and network science. Gonzalez’s research includes the application of big data to understanding human network behavior, with applications in transportation networks, energy efficiency planning and characterization of disease proliferation. Gonzalez was a Scientific Advisory Board member of PTV AG. She was the recipient of a U.N. Foundation award to study consumption patterns of women and girls in the developing world and of a Bill and Melinda Gates Foundation award to study access to financial services in the developing world.
How can we assist you?
We'll be updating the website as information becomes available. If you have a question that requires immediate attention, please feel free to contact us. Thank you!
Please enter the word you see in the image below: