A Machine Learning Approach to Model Over-Ocean Tropical Cyclone Precipitation

Abstract

Abstract Extreme rainfall found in tropical cyclones (TCs) is a risk for human life and property in many low- to midlatitude regions. Probabilistic modeling of TC rainfall in risk assessment and forecasting can be computationally expensive, and existing models are largely unable to model key rainfall asymmetries such as rainbands and extratropical transition. Here, a machine learning–based framework is developed to model overwater TC rainfall for the North Atlantic basin. First, a catalog of high-resolution TC precipitation simulations for 26 historical events is assembled for the North Atlantic basin using the Weather Research and Forecasting (WRF) Model. The simulated spatial distribution of rainfall for these historical events are then decomposed via principal component analysis (PCA), and quantile regression forest (QRF) models are trained to predict the conditional distributions of the first five principal component (PC) weights. Conditional distributions of rain-rate levels are estimated separately using historical satellite data and a QRF model. With these models, probabilistic predictions of rainfall maps can be made given a set of storm characteristics and local environmental conditions. The model is able to capture storm total rainfall compared to satellite observations with a correlation coefficient of 0.96 and r2 value of 0.93. Additionally, the model shows good accuracy in modeling hourly total rainfall compared to satellite observations. Rain-rate maps predicted by the model are also compared to historical satellite observations and to the WRF simulations during cross validation, and the spatial distribution of estimates captures rainfall variability consistent with TC rainbands, wavenumber asymmetries, and possibly extratropical transition.