Postprocessing Next-Day Ensemble Probabilistic Precipitation Forecasts Using Random Forests

Abstract

Most ensembles suffer from underdispersion and systematic biases. One way to correct for these shortcomings is via machine learning (ML), which is advantageous due to its ability to identify and correct nonlinear biases. This study uses a single random forest (RF) to calibrate next-day (i.e., 12–36-h lead time) probabilistic precipitation forecasts over the contiguous United States (CONUS) from the Short-Range Ensemble Forecast System (SREF) with 16-km grid spacing and the High-Resolution Ensemble Forecast version 2 (HREFv2) with 3-km grid spacing. Random forest forecast probabilities (RFFPs) from each ensemble are compared against raw ensemble probabilities over 496 days from April 2017 to November 2018 using 16-fold cross validation. RFFPs are also compared against spatially smoothed ensemble probabilities since the raw SREF and HREFv2 probabilities are overconfident and undersample the true forecast probability density function. Probabilistic precipitation forecasts are evaluated at four precipitation thresholds ranging from 0.1 to 3 in. In general, RFFPs are found to have better forecast reliability and resolution, fewer spatial biases, and significantly greater Brier skill scores and areas under the relative operating characteristic curve compared to corresponding raw and spatially smoothed ensemble probabilities. The RFFPs perform best at the lower thresholds, which have a greater observed climatological frequency. Additionally, the RF-based postprocessing technique benefits the SREF more than the HREFv2, likely because the raw SREF forecasts contain more systematic biases than those from the raw HREFv2. It is concluded that the RFFPs provide a convenient, skillful summary of calibrated ensemble output and are computationally feasible to implement in real time. Advantages and disadvantages of ML-based postprocessing techniques are discussed.

Development of a Probabilistic Subfreezing Road Temperature Nowcast and Forecast Using Machine Learning

“…Last, this algorithm has only been applied to deterministic model output so far. There are several approaches to applying machine learning to ensemble output (e.g., Gagne et al 2014Gagne et al , 2017Loken et al 2019). The best approach for this application is a topic currently under investigation.…”

MSDM v1.0: A machine learning model for precipitation nowcasting over eastern China using multisource data

“…Gagne et al (2009) use the decision tree to classify storm types based on radar observations. Loken et al (2019) calibrate the ensemble precipitation forecast via random forest. Hill et al (2020) use random forests to predict the probability of severe weather across the United States.…”

“…Hill et al (2020) use random forests to predict the probability of severe weather across the United States. Mao and Sorteberg (2020) use random forest to train a binary model to improve the accuracy of radar-based precipitation nowcasts. Bayesian techniques are an important branch of ML.…”

From Random Forests to Flood Forecasts: A Research to Operations Success Story

“…1. and Hamill 2015;Hamill and Scheuerer 2018;Whan and Schmeits 2018;Loken et al 2019), but these approaches have not focused specifically on rainfall that is excessive with respect to the local climatology. To address these challenges, the authors have developed, evaluated, and transitioned into operations a forecast system based on NWP model reforecasts, historical observations of excessive rainfall, and machine learning algorithms.…”