Machine Learning Algorithms for Climate Informatics and Sustainability
Monday, April 3, 2017 11:00:00 AM - Monday, April 3, 2017 12:00:00 PM
Rm. 1210, Bahen Centre, 40 St. George Street
Invited Research Seminar
CLAIRE MONTELEONI, George Washington University
ABSTRACT: Despite the scientific consensus on climate change, drastic uncertainties remain. Crucial questions about regional climate trends, changes in extreme events, such as heat waves and mega-storms, and understanding how climate varied in the distant past, must be answered in order to improve predictions, assess impacts and vulnerability, and inform sustainable strategies for mitigation and adaptation. Machine learning can help answer such questions and shed light on climate change. I will give an overview of our climate informatics research: machine learning for the study of climate science. Similar to the case of bioinformatics, climate informatics provides a data-rich scientific domain in which machine learning can make a major impact. Further, questions in climate science give rise to new challenges for the design of machine learning algorithms. More broadly, any real-world data source can be massive, high-dimensional, streaming, time-varying, raw (unlabeled), sparse, or private; or combine these and other attributes. I will survey my research program on developing machine learning algorithms to address such challenges, and applying them to societally impactful problems, with an emphasis on environmental sustainability. I will center the discussion on our contributions to improving predictions of climate change trends from ensembles of climate model simulations, and improving the understanding of climate extremes. Along the way, I will describe our work on machine learning algorithms for non-stationary spatiotemporal data, and scaling up unsupervised learning to big data. BRIEF BIO: Claire Monteleoni is an assistant professor of Computer Science at George Washington University. Previously, she was research faculty at the Center for Computational Learning Systems, at Columbia University. She did a postdoc in Computer Science and Engineering at the University of California, San Diego, and completed her PhD and Master’s in Computer Science at MIT. She holds a Bachelor’s in Earth and Planetary Sciences from Harvard. Her research focuses on machine learning algorithms and theory for learning from data streams, spatiotemporal data, raw (unlabeled) data, and private data, and applications with societal benefit. Dr. Monteleoni’s research is supported by several grants from the National Science Foundation. Her research on machine learning for the study of climate science received the Best Application Paper Award at NASA CIDU 2010, and helped launch the interdisciplinary field of climate informatics. In 2011, she co-founded the International Workshop on Climate Informatics, which is now in its seventh year, attracting climate scientists and data scientists from over 19 countries and 30 U.S. states. She gave an invited tutorial on climate informatics at NIPS 2014. She has co-organized workshops on Machine Learning for Global Challenges, at ICML 2011, and Data Science for Social Good, at KDD 2014. In 2017, she is serving as a Senior Area Chair for NIPS, on the Senior Program Commitees for AISTATS and UAI, on the Editorial Board of the Machine Learning Journal, as a Senior Advisory Member of the Executive Board of the Workshop for Women in Machine Learning, and on the Steering Committee of the Climate Informatics Workshop.