A novel hybrid artificial neural network - Parametric scheme for postprocessing medium-range precipitation forecasts

Abstract

Many present-day statistical schemes for postprocessing weather forecasts, in particular precipitation forecasts, rely on calibration using prescribed statistical models to relate forecast statistics to distributional parameters. The efficacy of such schemes is often constrained not only by prescribed predictor-predictand relation, but also by arbitrary choices of temporal window and lead time range for training. To address this limitation, we propose an end-to-end, computationally efficient hybrid postprocessing scheme capable of producing full predictive distributions of precipitation accumulation without explicit stratification of forecast-observation pairs by forecast lead time and season. The proposed framework uses the censored, shifted gamma distribution (CSGD) as the predictive distribution but uses an artificial neural network (ANN) to estimate the distributional parameters of CSGD through a unified approach. This approach, referred to as ANN-CSGD, allows for simultaneous estimation of distributional parameters over multiple lead times and seasons in a single model by incorporating the latter variables as predictors to the ANN. We test our proposed ANN-CSGD model for postprocessing of ensemble mean forecasts of 24-h precipitation totals over selected river basins in California, at one- to seven-day lead times, from the Global Ensemble Forecast System (GEFS). The probabilistic quantitative precipitation forecasts (PQPFs) from the ANN-CSGD, are more skillful overall than those from the benchmark CSGD and the Mixed-type meta-Gaussian distribution (MMGD) models. The ANN-CSGD PQPFs highly improve the performance of those from CSGD in predicting the probability of precipitation (PoP) and are also much sharper and reliable at higher precipitation thresholds. We demonstrate how the hybrid approach, by using the entire available training data and its modified formulation, efficiently represents interactions between GEFS forecasts and season/lead times, thus leading to enhanced predictive performance.