Timezone: »

Short-range forecasts of global precipitation using deep learning-augmented numerical weather prediction
Manmeet Singh · Vaisakh SB · Nachiketa Acharya · Aditya Grover · Suryachandra A. Rao · Bipin Kumar · Zong-Liang Yang · Dev Niyogi
Event URL: https://www.climatechange.ai/papers/neurips2022/64 »

Precipitation drives the hydroclimate of Earth and its spatiotemporal changes on a day to day basis have one of the most notable socioeconomic impacts. The success of numerical weather prediction (NWP) is measured by the improvement of forecasts for various physical fields such as temperature and pressure. Large biases however exist in the precipitation predictions. Pure deep learning based approaches lack the advancements acheived by NWP in the past two to three decades. Hybrid methodology using NWP outputs as inputs to the deep learning based refinement tool offer an attractive means taking advantage of both NWP and state of the art deep learning algorithms. Augmenting the output from a well-known NWP model: Coupled Forecast System ver.2 (CFSv2) with deep learning for the first time, we demonstrate a hybrid model capability (DeepNWP) which shows substantial skill improvements for short-range global precipitation at 1-, 2- and 3-days lead time. To achieve this hybridization, we address the sphericity of the global data by using modified DLWP-CS architecture which transforms all the fields to cubed-sphere projection. The dynamical model outputs corresponding to precipitation and surface temperature are ingested to a UNET for predicting the target ground truth precipitation. While the dynamical model CFSv2 shows a bias in the range of +5 to +7 mm/day over land, the multivariate deep learning model reduces it to -1 to +1 mm/day over global land areas. We validate the results by taking examples from Hurricane Katrina in 2005, Hurricane Ivan in 2004, Central European floods in 2010, China floods in 2010, India floods in 2005 and the Myanmar cyclone Nargis in 2008.

Author Information

Manmeet Singh (The University of Texas at Austin)
Vaisakh SB (Indian Institute of Tropical Meteorology)
Nachiketa Acharya (CIRES, University of Colorado Boulder & NOAA Physical Sciences Laboratory, Boulder, Colorado, USA)
Nachiketa Acharya

Nachiketa Acharya is a statistical climatologist with specialties in statistical and machine learning modeling in climate science, especially sub-seasonal to seasonal climate forecasting.He is a CIRES/University of Colorado Research Scientist III working with the NOAA Earth System Research Laboratories's Physical Sciences Laboratory. Previously, he has held influential positions at the Department of Meteorology and Atmospheric Sciences at the Pennsylvania State University, the International Research Institute for Climate and Society at Columbia University, the Institute for Sustainable Cities at the City University of New York, the National Centre for Medium-Range Weather Forecasting in India, the Indian Institute of Technology Delhi, and Bhubaneswar. He received his Ph.D. in Statistics from Utkal University, India in 2014 which focused on statistical techniques for extended range prediction of the Indian monsoon. Till date he has published more than 45 scientific papers with about 800 citations.

Aditya Grover (University of California, Los Angeles)
Suryachandra A. Rao (Indian Institute of Tropical Meteorology)
Bipin Kumar (Indian Institute of Tropical Meteorology)
Zong-Liang Yang (The University of Texas at Austin)
Dev Niyogi (The University of Texas at Austin)
Dev Niyogi

Professor and William Stamps Farish Chair in Geoscience, with appointments in the Department of Geological Science, Jackson School of Geosciences, and Department of Civil, Architectural and Environmental Engineering, Cockrell School of Engineering, The University of Texas at Austin. Lab director for the The University of Texas Extreme weather and Urban Sustainability (TExUS ) Lab. Also Professor Emeritus and former State Climatologist at Purdue University, Indiana. Research seeks to significantly contribute to our understanding of the Earth system, particularly the urban and agricultural landscapes, and the dynamic role of coupled land surface processes on regional hydroclimatic extremes. Translate the scientific work undertaken into decision tools and portals with a particular focus on sustainable climate-ready/resilient coastal, cities, and agricultural systems using Digital Twins framework. Editor for American Meteorological Society's Journal of Applied Meteorology and Climatology, and Topic Editor for Computational Urban Sciences journal. Member of the U.S. Department of Energy Biological and Environmental Research Advisory Committee (BERAC). Was the most recent chair of the American Meteorological Society (AMS) Board of Urban Environment and elected advisory board member of the International Association of Urban Climate. He is currently serving on the AMS Committee on Applied Climatology,

More from the Same Authors