A001
Advanced AI/ML for high-impact weather prediction and observation
Session ID#: 246829
Session Description:
Advanced artificial intelligence (AI) and machine learning (ML) models are rapidly transforming the field of meteorology, particularly in the domains of high-impact weather prediction and analysis. This session welcomes in-depth exploration of the state-of-the-art AI/ML methodologies applied to enhance the accuracy and timeliness of forecasts for severe weather events such as hurricanes, tornadoes, extreme rainfall, snow blizzard, wildfire, etc. AI-based projection of those events’ responses to climate change is also welcomed. The session will discuss how AI/ML techniques facilitate the extraction of intricate patterns and relationships within the data that traditional models may overlook or misrepresent, leading to improved predictive capabilities. Furthermore, we highlight innovative approaches to leverage AI's ability to interpolate sparse data and assimilate multimodal data, thereby better representing fine-grained atmospheric dynamic processes. This includes but is not limited to novel AI/ML model/algorithm development for severe weather prediction, numerical model enhancement using AI/ML methods, and climate change projection.
Index Terms:
1817 Extreme events [HYDROLOGY]
1821 Floods [HYDROLOGY]
3305 Climate change and variability [ATMOSPHERIC PROCESSES]
3314 Convective processes [ATMOSPHERIC PROCESSES]
Primary Convener: Jiaxi Hu, State University of New York, University at Albany, Atmospheric Sciences Research Center, Albany, United States
Conveners: Hui Su, Hong Kong University of Science and Technology, Hong Kong, Hong Kong, Xiaoming Shi, The Hong Kong University of Science and Technology, Hong Kong, China and Yixin Wen, University of Florida, Department of Geography, Ft Walton Beach, FL, United States
Skillful Joint Probabilistic Weather Forecasting From Marginals (Invited) (1892253)
Ferran Alet1, Ilan Price1, Tom Andersson2, Andrew El-Kadi1, Remi Lam3, Alvaro Sanchez1, Dominic Masters1, Peter Battaglia1, Stratis Markou1, Jacklynn Stott1, Matthew Willson1 and Google DeepMind, (1)Google DeepMind, London, United Kingdom, (2)British Antarctic Survey, Cambridge, United Kingdom, (3)Google, Mountain View, United States
Generative Data Assimilation for CONUS-wide High-Resolution Weather State Estimation (1951089)
Conor Lewellyn1, Nick Silverman2, Nick Krall3, Noah Brenowitz4, Simon Byrne5, Karthik Kashinath4, Chris Miller6, Matt Bender3 and Neal Pan5, (1)MITRE Corporation Mclean, Mclean, VA, United States, (2)The MITRE Corporation, Missoula, United States, (3)The MITRE Corporation, McLean, United States, (4)NVIDIA Corporation, Santa Clara, CA, United States, (5)NVIDIA, Santa Clara, United States, (6)MITRE Corporation, McLean, United States
Predicting Ambient Air Temperature of Bangladesh Using Machine Learning and Remote Sensing (1952081)
Rezaul Islam1, Md. Noor Tushar1, Subrata Dey1, Syed Irfan Uddin1, . Shampa2, Ahmed Ishtiaque Amin Chowdhury1, Sonia Binte Murshed2, Shammi Haque3 and Mashfiqus Salehin1, (1)Bangladesh University of Engineering and Technology, Institute of Water and Flood Management, Dhaka, Bangladesh, (2)Bangladesh University of Engineering and Technology (BUET), Institute of Water and Flood Management (IWFM), Dhaka, Bangladesh, (3)Bangladesh University of Engineering and Technology, Institute of Water and Flood Management (IWFM), Dhaka, Bangladesh
Enhancing Spatiotemporal Aerosol Optical Depth Data Continuity by Leveraging Geostationary ABI Aerosol Retrievals and Deep Learning Techniques (1953508)
Jeffrey Lee1, Sandra Marcela Loria Salazar1, Heather Holmes2 and Andrew M Sayer3, (1)University of Oklahoma, School of Meteorology, Norman, United States, (2)Department of Chemical Engineering, University of Utah, Salt Lake City, United States, (3)Universities Space Research Association (USRA), Columbia, United States
Distributional Regression U-Nets for Postprocessing Precipitation Forecasts Over India (1961475)
Chandni Thakur, University of Birmingham, Geography, Earth and Environmental Sciences, Birmingham, United Kingdom and Martin Widmann1, Kelvin Ng2, Raghavendra Ashrit3, Marc Girona-Mata3, Noemi Gonczol2, Andrew Orr4, Gregor C. Leckebusch1, Ruth Geen1 1University of Birmingham, UK; 2UK Met Office; 3National Centre for Medium Range Weather Forecasting, Noi
A PMP-Inspired Evaluation Framework for Assessing the fit-for-purpose of Deep-Learning Weather Prediction Models (1981571)
Shiheng Duan1, Giuliana Pallotta1, Celine Bonfils1, Jiwoo Lee2 and Paul Ullrich2, (1)Lawrence Livermore National Laboratory, Livermore, CA, United States, (2)Lawrence Livermore National Laboratory, Livermore, United States
Uncertainty Estimation and Explanation for Convective Initiation Nowcasting Using Bayesian Deep Learning (1990433)
Da Fan, Columbia University, Learning the Earth with Artificial Intelligence and Physics (LEAP), a National Science Foundation (NSF) Science and Technology Center, New York, United States, David John Gagne II, NCAR/MMM, Boulder, United States; NSF National Center for Atmospheric Research, Computational and Information Systems Lab, Boulder, United States, Steven J Greybush, Pennsylvania State University Main Campus, Meteorology and Atmospheric Science, University Park, United States, Eugene Edmund Clothiaux, Penn State, Meteorology and Atmospheric Science, University Park, United States, John Schreck, NSF National Center for Atmospheric Research, Computational & Information Systems Lab, Boulder, United States and Chaopeng Shen, Pennsylvania State University Main Campus, Department of Civil and Environmental Engineering, University Park, United States
Tropical Cyclone Wind Field Reconstruction Using AI (1997563)
Hui Su1, Enze Zhang2, Pak-Wai Chan3, Wensheng Zhou2 and Chengxing Zhai1, (1)Hong Kong University of Science and Technology, Hong Kong, Hong Kong, (2)Hong Kong University of Science and Technology, Civil and Environmental Engineering, Hong Kong, Hong Kong, (3)Hong Kong Observatory, Kowloon, Hong Kong
Enhancing Radar Reflectivity Prediction for Rainfall Nowcasting Using a CSI-Optimized Loss Function (2004997)
Chengxing Zhai1, Wangjiang Gong2, Kuai Dai3 and Hui Su2, (1)Hong Kong University of Science and Technology, Hong Kong, Hong Kong, (2)The Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong, (3)The Hong Kong University of Science and Technology, Civil and Environmental Engineering, Clear Water Bay, Hong Kong
Comprehensive evaluation of diffusion model based precipitation downscaling (1946981)
Yixin Wen, University of Florida, Department of Geography, Ft Walton Beach, FL, United States, Weikang Qian, East China Normal University, Shanghai, China, Chugang Yi, University of Maryland, College Park, College Park, United States, Zhi Li, University of Oklahoma, Norman, United States, Dr. Lingcheng Li, PhD, Pacific Northwest National Laboratory, Richland, WA, United States, Songkun Yan, University of Oklahoma, School of Civil Engineering and Environmental Science, Norman, United States and Siyu Zhu, Tsinghua University, Department of Hydraulic Engineering, Beijing, China
Deep Learning-Based Convective Initiation Detection Using GK-2A/AMI Satellite Data (1938444)
in Chae Chung1, Sihyun Lee1, Haneul Cho2, Minki Choo1 and Jungho Im1, (1)Ulsan National Institute of Science and Technology, Department of Civil, Urban, Earth, and Environmental Engineering, Ulsan, South Korea, (2)Ulsan National Institute of Science and Technology, Graduate School of Carbon Neutrality, Ulsan, South Korea
Performance Comparison of AI-Based Weather Models in Forecasting Strong Landfalling Typhoon (1936728)
Xiaotian Zhang1, Feng Hu2, Lue Wang1 and Fei Wang1,3, (1)The Hong Kong Polytechnic University, Department of Civil and Environmental Engineering, Kowloon, Hong Kong, (2)City University of Hong Kong, Department of Architecture and Civil Engineering, Kowloon, Hong Kong, (3)The Hong Kong Polytechnic University, Joint Research Centre for Marine Infrastructure, Kowloon, Hong Kong
Prediction of Semidiurnal Precipitation in an Urban Forest Using Meteorological Observations at High Temporal Resolution and Machine Learning Tools: An Application of Convolutional Neural Network (1918075)
Dr. Zheng Dong1, Jingxuan Lyu2,3, Tianjian Xu2,4, Yuhe Shi2, Yanxi Han2, Zhenghao Ruan2 and Xikai Wang2, (1)Beijing Haidian Kaiwen Academy, Beijing, United States, (2)Beijing Haidian Kaiwen Academy, Beijing, China, (3)University of California Berkeley, Berkeley, United States, (4)University of California San Diego, La Jolla, United States
Supporting AI/ML Weather Prediction in NOAA: A Flexible Verification Pipeline with wxvx (1949421)
David Burrows1, Anil Kumar2, Mariah Pope2, Paul Madden3, Isidora Jankov4 and Sergey Frolov5, (1)NOAA EPIC, Albany, United States, (2)NOAA EPIC, College Park, United States, (3)NOAA, Boulder, United States, (4)NOAA/Global Systems Laboratory, Boulder, United States, (5)NOAA/PSL, Boulder, United States
Observational (Ground-Based and Satellite) and Atmospheric Modeling capabilities at the Environmental and Geophysical Sciences (ENGEOS) Lab – Khalifa University for weather and climate applications (1871843)
Hanif Shaikh1, Diana Karam Francis2, Narendra Reddy Nelli2, Ricardo Morais Fonseca2, Yesobu Yarragunta3 and Charfeddine Cherif4, (1)Khalifa University of Science and Technology, Abu Dhabi, Abu Dhabi, UNITED ARAB EMIRATES, (2)Environmental and Geophysical Sciences (ENGEOS) Lab, Earth Science Department, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates, (3)Khalifa University of Science and Technology, Environmental and Geophysical Sciences (ENGEOS) Lab, Earth Science Department,, Abu Dhabi, United Arab Emirates, (4)Khalifa University of Science and technology, Environmental and Geophysical Sciences (ENGEOS) Lab, Earth Science Department,, Abu Dhabi, United Arab Emirates
The NOAA Anemoi Experience: scalable and user-friendly tools for training AI weather prediction models (1949787)
David Burrows1, Mariah Pope1, Timothy Smith2, Sergey Frolov2, Daniel Abdi3, Isidora Jankov4 and Anil Kumar1, (1)NOAA EPIC, College Park, United States, (2)NOAA/PSL, Boulder, United States, (3)CIRES/NOAA, Boulder, United States, (4)NOAA/Global Systems Laboratory, Boulder, United States
Physics-Informed Machine Learning for Sub-SeasonalPrediction of Tropical Cyclone Genesis (1894482)
Aren Russ, Georgia Institute of Technology, Atlanta, Georgia, UNITED STATES, Shijie Xiao, Georgia Institute of Technology, Atlanta, United States, Thomas Ehrmann, Sandia National Laboratories, Albuquerque, NM, United States and Ali Sarhadi, Department of Civil and Environmental Engineering, University of Waterloo, Waterloo, Ontario, Canada N2L-3G1, Waterloo, ON, Canada
Bias Correction of MPAS-A Forecasts Using a Diffusion Model-Based Deep Learning Framework (1893198)
Ming Fan1, Zezhong Zhang2, Mr. Hyungyu Kang, PhD3, Wei Zhang3, Dan Lu3 and Guannan Zhang3, (1)Oak Ridge National Laboratory, Oak Ridge, TN, United States, (2)Oak Ridge National Laboratory, Knoxville, United States, (3)Oak Ridge National Laboratory, Oak Ridge, United States
Spatial Clustering of heat wave Regimes Through ConvAE Latent Space Analysis and Teleconnection Linkages (1856911)
Mostafa Rezaali, University of Florida, Ft Walton Beach, FL, United States, David Keellings, University of Florida, Department of Geography, Ft Walton Beach, FL, United States, Corene J Matyas, University of Florida, Department of Geography, Gainesville, FL, United States and Shuolin Li, Columbia University, Data Science Institute, NY, United States
Leveraging Machine Learning to Assess Santa Ana Wind-Driven Wildfire Risk in Southern California (1880047)
Raymond Sukhdeo1, Karandeep Singh1, Chad William Thackeray2, James T. Randerson3, Alexander D Hall2 and Rebecca Scholten3, (1)University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, United States, (2)University of California Los Angeles, Atmospheric and Oceanic Sciences, Los Angeles, CA, United States, (3)University of California Irvine, Earth System Science, Irvine, United States
Successes and challenges in storm prediction integrating physics-based models with AI/ML (1884143)
Marina Astitha, University of Connecticut, Department of Civil and Environmental Engineering, Groton, CT, United States, Ummul Khaira, University of Connecticut, School of Civil and Environmental Engineering, Storrs, United States and Israt Jahan, IUCN Bangladesh, Dhaka, Bangladesh
Low-Level Wind Shear Prediction at Jeju International Airport Using Tree-Based Machine Learning Algorithm (1890305)
JaeHyeok Seok, National Institute of Meteorological Sciences, Seogwipo-si, South Korea, Hee-Wook Choi, National Institute of Meteorological Sciences, Jeju, South Korea and Sangsam Lee, National Institute of meteorological sciences, Jeju, Korea, Republic of (South)
Monte Carlo-enhanced machine learning regression for filling urban air pollution gaps: a case study for Delhi, India (1872079)
Ms. Sedra Shafi, University of Naples Federico II, Department of Earth Sciences, Environment and Resources, Naples (ITALY), Italy and Nicola Scafetta, University of Naples Federico II, Department of Earth Sciences, Environment and Resources, Naples, Italy
Nowcasting 4D Cloud Fields with Satellite Data and Deep Learning (1913734)
James Gibbons, MyRadar, Washington DC, United States, Ryan Lagerquist, MyRadar, Ward, CO, UNITED STATES and Sarvesh Garimella, Massachusetts Institute of Technology, Earth, Atmospheric and Planetary Sciences, Cambridge, United States
