GC006
AI and Machine Learning for Climate and Extreme Weather Prediction
Session ID#: 81937
Session Description:
A core geoscience challenge is to connect changing climate to the frequency and magnitude of extreme events across a range of spatio-temporal scales. To that end, there is an opportunity to leverage increasingly high-resolution data from remote-sensing (e.g. Sentinel, GOES-R) and simulations (NWP forecasts, GCMs), new machine learning algorithms (e.g. deep neural networks, generative models) and GPU and cloud-based computing. This session encourages contributions that address data-driven and machine learning approaches to extreme events in a changing climate, including the statistics of specific hazards (tropical cyclones, precipitation, flooding, wildfire), new methods (risk estimation, extreme event statistics, data assimilation, forecasting and prediction, statistical downscaling, GCM subgrid-scale parameterization), and new data and computational architectures/workflows.
Index Terms:
1942 Machine learning [INFORMATICS]
3305 Climate change and variability [ATMOSPHERIC PROCESSES]
3315 Data assimilation [ATMOSPHERIC PROCESSES]
4313 Extreme events [NATURAL HAZARDS]
Primary Convener: Brian L White, University of North Carolina at Chapel Hill, Marine Sciences, Chapel Hill, NC, United States
Conveners: Adrian Albert, Lawrence Berkeley National Laboratory, Berkeley, CA, United States and Antonia Sebastian, Texas A&M University at Galveston, Marine Sciences, Galveston, TX, United States
Primary Liaison: Brian L White, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States
Random Forrest Classification for Flood Hazard Mapping at Large Spatial Scales (554047)
William Mobley, Texas A&M University at Galveston, Galveston, United States, Antonia Sebastian, Texas A&M University at Galveston, Marine Sciences, Galveston, TX, United States, Russell Blessing, Texas A&M University College Station, College Station, TX, United States, Wesley HighField, Texas A&M-Galveston Bldg 3029, Marine Sciences, Galveston, TX, United States and Andrew Juan, Rice University, Civil and Environmental Engineering, Houston, TX, United States
Downscaling Numerical Weather Models with GANs (559430)
Alok Singh, Berkeley, CA, United States, Brian L White, University of North Carolina at Chapel Hill, Chapel Hill, NC, United States and Adrian Albert, Lawrence Berkeley National Laboratory, Berkeley, CA, United States
Graph-Guided Regularization for Improved Forecasting of Southwestern US Winter Precipitation (560425)
Abby Stevens1, Rebecca Willett2, Antonios Mamalakis3, Efi Foufoula-Georgiou3, James T. Randerson4, Stephen Wright5, Padhraic Smyth6 and Alejandro Tejedor7, (1)Chicago, IL, United States, (2)University of Chicago, Computer Science, Chicago, IL, United States, (3)University of California Irvine, Department of Civil and Environmental Engineering, Irvine, CA, United States, (4)University of California Irvine, Department of Earth System Science, Irvine, CA, United States, (5)University of Wisconsin - Madison, Madison, WI, United States, (6)University of California Irvine, Computer Science, Irvine, CA, United States, (7)Saint Anthony Falls Laboratory, Minneapolis, MN, United States
Applicability of Long Short Term Memory Network to Flow Discharge Modeling at Watershed in Kyushu Region, Japan (563372)
Takeyoshi Nagasato1, Kei Ishida2, Ali Ercan3, Masato Kiyama2 and Motoki Amagasaki2, (1)Kumamoto University, Department of Civil and Environmental Engineering, Kumamoto, Japan, (2)Kumamoto University, Kumamoto, Japan, (3)University of California Davis, Davis, CA, United States
Investigation of Precipitation Trends Across Northern Virginia (567122)
Ishrat Jahan Dollan1, Viviana Maggioni2, Tasnuva Rouf2 and Yiwen Mei2, (1)George Mason University, Sid and Reva Dewberry Dept. of Civil, Environmental & Infrastructure Engineering, Fairfax, VA, United States, (2)George Mason University Fairfax, Sid and Reva Dewberry Dept. of Civil, Environmental & Infrastructure Engineering, Fairfax, VA, United States
Leveraging Machine Learning and Twitter Data to Identify High Hazard Areas during Hurricane Harvey (567622)
Antonia Sebastian, Texas A&M University at Galveston, Marine Sciences, Galveston, TX, United States, Wesley HighField, Texas A&M-Galveston Bldg 3029, Marine Sciences, Galveston, TX, United States, Samuel Brody, Texas A&M University College Station, College Station, TX, United States and William Mobley, Texas A&M University at Galveston, Galveston, United States
Deep learning for automated feature detection in climate, weather, and space (594163)
David Hall1, Craig C. Tierney2, Stan Posey3 and Jim Hooks3, (1)NVIDIA, Lafayette, CO, United States, (2)NVIDIA, Santa Clara, CO, United States, (3)NVIDIA, Santa Clara, United States
Assessing Changes in Tropical Cyclone Genesis under Varying Climate Scenarios (596227)
Arturo Fernandez1,2, Karthik Kashinath2, Jon McAuliffe3,4, Deborah Nolan3, Christina M Patricola5, Mr. Prabhat2 and Michael F Wehner2, (1)Uber Technologies, Inc., New York, CA, United States, (2)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (3)University of California Berkeley, Statistics, Berkeley, CA, United States, (4)The Voleon Group, Berkeley, CA, United States, (5)Lawrence Berkeley National Laboratory, Climate and Ecosystem Sciences Division, Berkeley, CA, United States
Using Deep Learning to Predict Yearly Wildfire Potential from Antecedent Land Surface and Meteorological Data (596235)
Andrew White, University of Alabama in Huntsville, Huntsville, AL, United States, Christopher Hain, NASA Marshall Space Flight Center, Huntsville, AL, United States, Christopher J Schultz, NASA Marshall Space Flght Ctr, Huntsville, AL, United States, Jonathan Case, ENSCO, Inc./NASA Marshall Space Flight Center, Huntsville, AL, United States and Kristopher White, NOAA National Weather Service Huntsville, Huntsville, AL, United States
Using Self-Organizing Maps to Identify Coherent CONUS Precipitation Regions: Application to Extremes Aggregation (599315)
Leif M Swenson, University of California Davis, Land, Air and Water Resources, Davis, CA, United States and Richard Grotjahn, University of California Davis, Davis, CA, United States
Deep Learning Semantic Segmentation for Climate Change Precipitation Analysis (622012)
Andrew Lou1, Eshvar Chandran2, Mr Prabhat3, Jim Biard4, Kenneth Kunkel5, Michael F Wehner3 and Karthik Kashinath3, (1)University of California Berkeley, Berkeley, CA, United States, (2)Rice University, Houston, United States, (3)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (4)Cooperative Institute for Climate and Satellite North Carolina State, Asheville, NC, United States, (5)University of Illinois at Urbana Champaign, Urbana, IL, United States
Topological Data Analysis and Machine Learning methods for pattern detection in spatiotemporal climate data (626804)
Grzegorz Muszynski1, Karthik Kashinath2, Michael F Wehner2, Jan Balewski3 and Mr Prabhat2, (1)University of Liverpool, Computer Science, Liverpool, L69, United Kingdom, (2)Lawrence Berkeley National Laboratory, Berkeley, CA, United States, (3)Lawrence Berkeley National Laboratory, Berkeley, United States
Machine Learning Approach to Identify Aerosol and Geophysical Variable Influence on Southwest Pacific Ocean Tropical Cyclone Development (631854)
Rupsa Bhowmick, Louisiana State University, Baton Rouge, LA, United States, Jill C. Trepanier, Louisiana State University, Geography & Anthropology, Baton Rouge, LA, United States and Alex M Haberlie, Louisiana State University, Geography and Anthropology, Baton Rouge, LA, United States
