A014
Advancing Precipitation Predictions with Physical Models and Artificial Intelligence
Session ID#: 252047
Session Description:
Accurately predicting precipitation across multiple time scales—ranging from short-term to subseasonal-to-seasonal, decadal, and climate scales—is essential for advancing our understanding of the water cycle and supporting sustainable water resource management. Reliable spatial and temporal analyses of precipitation patterns and mechanisms can benefit critical sectors such as energy, transportation, agriculture, and disaster preparedness. Artificial intelligence (AI)–based weather prediction is rapidly emerging alongside traditional numerical weather and climate models, offering new opportunities for innovation. This session highlights interdisciplinary research that integrates physical modeling and AI to deepen our understanding of precipitation and expand its practical applications. We welcome abstracts that explore, but are not limited to: AI and physical model–based precipitation prediction and analysis; the use of diverse observational data and AI to assess precipitation predictability; and the challenges and opportunities of forecasting precipitation in the era of AI. Contributions from atmospheric and hydrological sciences, and data/AI science are especially encouraged.
Co-Sponsor(s):
Index Terms:
1655 Water cycles [GLOBAL CHANGE]
1854 Precipitation [HYDROLOGY]
1942 Machine learning [INFORMATICS]
3354 Precipitation [ATMOSPHERIC PROCESSES]
Primary Convener: Xiaodong Chen, University of Oklahoma, School of Meteorology, Norman, United States
Conveners: Ming Pan, Center for Western Weather and Water Extremes (CW3E), Scripps Institution of Oceanography, University of California San Diego, La Jolla, United States, Kelly M Mahoney, Cooperative Institute for Research in Environmental Sciences, Boulder, United States and Tiantian Yang, University of Oklahoma Norman Campus, School of Civil Engineering and Environmental Science, Norman, United States
Student/Early Career Convener: Nana Liu, CIWRO/OU, NOAA/NSSL, Norman, United States
Advancing Rainfall Nowcasting in Tropical Southeast Asia with Physics-Informed Deep Generative Models (1863926)
Zhixiao Niu1, Htet Naing2, Song Chen2, Zhihuo Xu2, Joshua Lee2, Kalli Furtado2, Hugh Zhang2, Xinyue Liu1 and Xiaogang He1, (1)National University of Singapore, Department of Civil and Environmental Engineering, Singapore, Singapore, (2)Centre for Climate Research, Singapore, Singapore, Singapore
Skillful seasonal predictions of continental East-Asian summer rainfall by integrating its spatio-temporal evolution (1880575)
Jieru Ma1, Hong-Li Ren1, Ming Cai2 and Yi Deng3, (1)Chinese Academy of Meteorological Sciences, Beijing, China, (2)Florida State University, Tallahassee, United States, (3)Georgia Institute of Technology, School of Earth and Atmospheric Sciences, Atlanta, GA, United States
Moving beyond parameterized precipitation processes using holistic machine learning and satellite observations (1894192)
Raul Moreno, University of Washington Seattle Campus, Atmospheric Sciences, Seattle, United States, Dale R Durran, University of Washington Seattle Campus, Atmospheric Sciences, Seattle, WA, United States and Nathaniel Cresswell-Clay, University of Washington Seattle Campus, Seattle, United States
Evaluating AI-Based Numerical Weather Prediction Models for Precipitation Type Classification Using Crowd-Sourced Observations (1897373)
Stanley Akor1, Alejandro N Flores2, Charlie Becker3, John Schreck3 and David John Gagne II4, (1)Boise State University, Department of Geosciences, Boise, United States, (2)Boise State University, Department of Geosciences, Boise, ID, United States, (3)NSF National Center for Atmospheric Research, Computational & Information Systems Lab, Boulder, United States, (4)NCAR/MMM, Boulder, United States
Analyzing AI-NWP Performance for Extreme Flood Events in Kentucky and Texas (1897606)
Anna Varholak, Stonehill College, Environmental Science and Studies, Easton, United States, Steven J Greybush, Pennsylvania State University Main Campus, Meteorology and Atmospheric Science, University Park, United States and Christian Spallone, Pennsylvania State University, Meteorology and Atmospheric Science, State College, United States
The efficacy of ten snow-liquid ratio algorithms to predict snowfall for impactful winter storms in the Northeast United States (1920891)
Mr. Brian Filipiak1,2, Ummul Khaira1,3, Michael Walters1,3 and Marina Astitha1,3,4, (1)Eversource Energy Center, University of Connecticut, Storrs, United States, (2)University of Connecticut, School of Civil and Envrionmental Engineering, Storrs, United States, (3)University of Connecticut, School of Civil and Environmental Engineering, Storrs, United States, (4)National Center for Atmospheric Research (NCAR), Research Applications Laboratory, Boulder, United States
Investigating Historical Precipitation Trends in Models and Observations: Forced Signals and Atmospheric Internal Variability (1922942)
Wengui Liang, Princeton University, Princeton, NJ, United States; Louisiana State University, Baton Rouge, United States, Ming Zhao, NOAA/OAR/Geophysical Fluid Dynamics Laboratory, Princeton, United States, Zhihong Tan, NOAA Geophysical Fluid Dynamics Laboratory, Princeton, NJ, United States, Thomas R Knutson, NOAA/ Geophysical Fluid Dynamics Laboratory, Princeton, United States, Wenhao Dong, Center for Earth System Science, Tsinghua University, Princeton, United States and Bosong Zhang, Princeton University, Princeton, United States
Data-Driven Discovery of Thermodynamic Controls on South Asian Monsoon Precipitation (1931497)
Savannah Lee Ferretti1, Mike S Pritchard1,2, Fiaz Ahmed3, Tom Beucler4, Sara Shamekh5 and Jane Wilson Baldwin1,6, (1)University of California, Irvine, Department of Earth System Science, Irvine, United States, (2)NVIDIA Corporation, Santa Clara, United States, (3)University of California, Los Angeles, Department of Atmospheric and Oceanic Sciences, Los Angeles, United States, (4)University of Lausanne, Switzerland, Faculty of Geosciences and Environment, Institute of Earth Science Dynamics, Lausanne, Switzerland, (5)New York University, Center for Atmosphere Ocean Science, Courant Institute of Mathematical Sciences, New York, United States, (6)Lamont-Doherty Earth Observatory, Palisades, United States
Analysis of Precipitation Forecast Characteristics of the 8 km High-Resolution Korean Integrated Model (KIM) in Summer and Winter Seasons (1945184)
Bonyang Ku1, Seungbo Choi1, Hyun-Joo Choi2, Kyoungmi Cho2, Jeong-Ock LIM2 and Ik-Hyun Cho2, (1)Numerical Modeling Center, KMA, Seoul, South Korea, (2)Numerical Modeling Center, KMA, Daejeon, South Korea
Derived and Crowdsourced Observational Precipitation Phase Compared to the Atmospheric Conditions of HRRR Forecast Simulations in the Western CONUS (1955622)
Savanna Wolvin, University of Utah, Department of Atmospheric Sciences, Salt Lake City, UT, United States, Courtenay Strong, University of Utah, Department of Atmospheric Sciences, Salt Lake City, United States and Simon Brewer, University of Utah, School of Environment, Society, and Sustainability, Salt Lake City, United States
Investigating and Attributing Nonlinear Drivers of Extreme Precipitation Events through Deep-Learning Approaches (1958798)
Jeremy Corner, University of Virginia, Charlottesville, VA, United States, Antonios Mamalakis, University of Virginia, Department of Environmental Sciences, Charlottesville, VA, United States and Kathleen A. Schiro, University of Virginia, Department of Environmental Sciences, Charlottesville, United States
Global seasonal precipitation forecasts using model-analogs (1972661)
Dillon J Amaya1, Ho-Hsuan Wei2, Matthew Newman1, Joseph J Barsugli3,4 and Stephen G Yeager5, (1)NOAA Physical Sciences Laboratory, Boulder, United States, (2)Cooperative Institute for Research in Environmental Sciences, Boulder, United States, (3)NOAA Boulder, ESRL, Boulder, CO, United States, (4)CIRES, Boulder, United States, (5)NSF National Center for Atmospheric Research, Boulder, United States
Differentiable Downscaling Model for GCMs Precipitation (1987258)
Kamlesh Sawadekar, Pennsylvania State University Main Campus, Civil and Environmental Engineering, University Park, PA, United States, Peijun Li, Pennsylvania State University Main Campus, Civil and Environmental Engineering, University Park, United States, Seth A McGinnis, National Center for Atmospheric Research, Boulder, CO, United States and Chaopeng Shen, Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, United States
Lightweight 3-D Convolutional Framework for Radar Rainfall Nowcasting in Data- and Resource-Limited Settings (1995162)
Ahmed Abdelhalim1,2, Miguel Angel Rico-Ramirez1, Weiru Liu3 and Dawei Han1, (1)School of Civil, Aerospace and Design Engineering, University of Bristol, Bristol, United Kingdom, (2)Geology Department, Faculty of Science, Minia University, Minia, Egypt, (3)Department of Engineering Mathematics, University of Bristol, Bristol, United Kingdom
