How Much Did it Rain? Predicting Real Rainfall Totals Based on Radar Data

2016/08/06 by Adam Lesnikowski, Lesnikowski, Adam
Computer Science · Earth and Planetary Sciences · Environmental Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Meteorological Phenomena and Simulations #Precipitation Measurement and Analysis #Soil Moisture and Remote Sensing #cs.LG

paper · pdf · doi:10.48550/arxiv.1608.02126

arxiv created 2016/08/06 · openalex publication_date 2016/08/06 · arxiv updated 2016/08/09 · openalex created_date 2016/09/30 · openalex updated_date 2026/07/28

Abstract

We applied a variety of parametric and non-parametric machine learning models to predict the probability distribution of rainfall based on 1M training examples over a single year across several U.S. states. Our top performing model based on a squared loss objective was a cross-validated parametric k-nearest-neighbor predictor that took about six days to compute, and was competitive in a world-wide competition.

Related

• Predicting Rainfall using Machine Learning Techniques
• Further analysis of cGAN: A system for Generative Deep Learning Post-processing of Precipitation
• Regional Rainfall Prediction Using Support Vector Machine Classification of Large-Scale Precipitation Maps
• IowaRain: A Statewide Rain Event Dataset Based on Weather Radars and Quantitative Precipitation Estimation
• RainPro-8: An Efficient Deep Learning Model to Estimate Rainfall Probabilities Over 8 Hours