H082
Precipitation Through the Eyes of Machine Learning and Advanced Statistics - Remote Sensing, Uncertainties and Variability
Session ID#: 156517
Session Description:
Precipitation processes are among the most complex manifestations of Earth’s hydrometeorological system. Understanding of rain and snow variability across the scales are crucial challenges of hydrological science and applications. As our ability to accurately monitor and model precipitation processes is improving, it has become clear in recent years that advanced approaches including AI/ML have the potential to meet increasing requirements for a wide range of hydrometeorological studies. This session welcomes contributions on precipitation-related advanced statistical and AI/ML approaches seeking physical implications, model interpretations, remote sensing applications and uncertainty analyses that can identify novel elements in understanding and applications of precipitation processes and their variability. We call for studies that can link the information content of observational/modeled datasets to the physical causes, materializations and variability of precipitation processes across various scales. These include, but are not limited to, studies on radiative-, hydrometeor-, cloud-, extremes- and hydrological-responses to precipitation processes.
Index Terms:
1854 Precipitation [HYDROLOGY]
1855 Remote sensing [HYDROLOGY]
3314 Convective processes [ATMOSPHERIC PROCESSES]
3354 Precipitation [ATMOSPHERIC PROCESSES]
Primary Convener: Veljko Petković, University of Maryland, ESSIC / CISESS / College Park, College Park, United States
Conveners: Pierre Kirstetter, University of Oklahoma Norman Campus, School of Meteorology and School of Civil Engineering and Environmental Science, Norman, OK, United States, Ardeshir Ebtehaj, University of Minnesota Twin Cities, Minneapolis, United States and Shruti Ashok Upadhyaya, University of Oklahoma, Advanced Radar Research Center (ARRC), Norman, OK, United States
Student/Early Career Convener: Shruti Ashok Upadhyaya, University of Oklahoma, Advanced Radar Research Center (ARRC), Norman, OK, United States
Towards Trusting Synthetic Microwave Retrievals: Introducing Uncertainty Quantification in a New Bayesian Convolutional Neural Network Architecture (1155040)
Eleanor Casas, Naval Postgraduate School, Monterey, CA, United States, Marko Orescanin, Navy Postgraduate School, Department of Computer Science, Monterey, United States, Scott W Powell, University of Washington, Seattle, WA, United States, Veljko Petković, Colorado State University, Dept. of Atmospheric Science, Fort Collins, United States and Pedro Ortiz, Naval Postgraduate School, Monterey, United States
Statistical Downscaling of GCM Precipitation Over the Northeast US Based on Deep Learning (1156322)
Makduma Badhan1, Guiling Wang1, Tasnim Zaman1, Yelin Jiang1, Marina Astitha1, Qingyu Dai2 and Carlos Gómez-Gonzalez3, (1)University of Connecticut, Department of Civil and Environmental Engineering, Storrs, United States, (2)University of Connecticut, Mansfield, United States, (3)Barcelona Supercomputing Center, Barcelona, Spain
CHALLENGES AND SUCCESSES OF SNOWFALL FORECASTING USING MACHINE LEARNING AND NUMERICAL PREDICTION FOR THE NORTHEAST UNITED STATES (1171697)
Ummul Khaira, University of Connecticut, Civil and Environmental Engineering, Groton, CT, United States, Diego Cerrai, University of Connecticut, Department of Civil and Environmental Engineering, Groton, CT, United States, Gregory Thompson, National Center for Atmospheric Research, Boulder, CO, United States and Marina Astitha, University of Connecticut, Department of Civil and Environmental Engineering, Storrs, United States
Framework for Quantifying Simulated Precipitation Distributions at Regional Scales (1199026)
Min-Seop Ahn1, Paul Aaron Ullrich2, Peter J Gleckler1, Jiwoo Lee3 and Ana Cristina Ordonez3, (1)Lawrence Livermore National Laboratory, Livermore, CA, United States, (2)University of California Davis, Land, Air & Water Resources, Davis, CA, United States, (3)Lawrence Livermore National Laboratory, Livermore, United States
A Support Vector Machine-based Method for Improving Real-time Hourly Precipitation Forecast in Japan (1058029)
Gaohong Yin1, Takao Yoshikane1, Kosuke Yamamoto2, Takuji Kubota3 and Kei Yoshimura1, (1)The University of Tokyo, Institute of Industrial Science, Kashiwa, Japan, (2)Japan Aerospace Exploration Agency, Earth Observation Research Center, Tsukuba, Japan, (3)Japan Aerospace Exploration Agency, Tsukuba, Japan
Towards Optimal Precipitation Retrieval: Complementing Satellite Products (1074083)
Vesta Afzali Gorooh1, Veljko Petković2, Phu Nguyen1, Kuo-lin Hsu3, Soroosh Sorooshian1, Malarvizhi Arulraj4 and Ralph R Ferraro5, (1)University of California, Irvine, Department of Civil and Environmental Engineering, Irvine, United States, (2)University of Maryland College Park, ESSIC/CISESS, College Park, United States, (3)University of California Irvine, Department of Civil and Environmental Engineering, Irvine, CA, United States, (4)University of Maryland, Earth System Science Interdisciplinary Center (ESSIC) / CISESS, College Park, MD, United States, (5)NOAA College Park, College Park, United States
Characterizing Precipitation Patterns Over High Mountain Asia Using an Ensemble Product (1099113)
Ishrat Jahan Dollan, George Mason University Fairfax, Sid and Reva Dewberry Dept of Civil, Environmental & Infrastructure Engineering, Fairfax, VA, United States and Viviana Maggioni, George Mason University Fairfax, Sid and Reva Dewberry Department of Civil, Environmental, and Infrastructure Engineering, Fairfax, VA, United States
Gaining Insights into Sub-Daily Precipitation through a High-Density Rain Gage Network and Space-Time Stochastic Simulations (1104447)
Giuseppe Mascaro, Arizona State University, School of Sustainable Engineering and the Built Environment, Tempe, United States, Simon Michael Papalexiou, University of Calgary, Civil Engineering, Calgary, Canada and Daniel Wright, University of Wisconsin-Madison, Madison, United States
Precipitation Type from PMW Observations: Constellation Retrieval with Uncertainty Estimates (1111795)
Veljko Petković, University of Maryland College Park, ESSIC/CISESS, College Park, United States, Marko Orescanin, Naval Postgraduate School, Department of Computer Science, Monterey, United States, Pedro Ortiz, Naval Postgraduate School, Monterey, United States, Scott W Powell, Naval Postgraduate School, Department of Meteorology, Monterey, United States, Ralph Ferraro, University of Maryland College Park, College Park, United States and Huan Meng, Natl Oceanic & Atmospheric Adm, College Park, MD, United States
Operational Partitioning of Precipitation Phase Using Machine Learning (1114619)
Alexis Bédard-Therrien1, Fanny Payette2, Alexandre Vidal2, Julie M Theriault3, Francois Anctil4 and Daniel Nadeau4, (1)Laval University, Quebec City, QC, Canada, (2)Hydro-Québec, Montreal, Canada, (3)Université du Québec Montréal, Montréal, QC, Canada, (4)Laval University, Civil and Water Engineering, Quebec City, QC, Canada
Exploring the bias in satellite-based passive-microwave retrievals from vertical structure perspective (1127222)
Malarvizhi Arulraj, University of Maryland College Park, Cooperative Insititute for Satellite Earth System Studies, College Park, MD, United States, Veljko Petković, University of Maryland College Park, ESSIC/CISESS, College Park, United States, Huan Meng, Natl Oceanic & Atmospheric Adm, College Park, MD, United States and Ralph Ferraro, University of Maryland College Park, College Park, United States
