Predicting Cloud-To-Ground Lightning in the Western United States From the Large-Scale Environment Using Explainable Neural Networks.

ABSTRACT: Lightning is a major source of wildfire ignition in the western United States (WUS). We build and train convolutional neural networks (CNNs) to predict the occurrence of cloud-to-ground (CG) lightning across the WUS during June-September from the spatial patterns of seven large-scale meteorological variables from reanalysis (1995-2022). Individually trained CNN models at each 1° × 1° grid cell (n = 285 CNNs) show high skill at predicting CG lightning days across the WUS (median AUC = 0.8) and perform best in parts of the interior Southwest where summertime CG lightning is most common. Further, interannual correlation between observed and predicted CG lightning days is high (median r = 0.87), demonstrating that locally trained CNNs realistically capture year-to-year variation

SUBMITTER: Kalashnikov DA 

PROVIDER: S-EPMC11583119 | biostudies-literature | 2024 Nov

REPOSITORIES: biostudies-literature