Flash Type Classification of GLM Flashes

While the Geostationary Lightning Mapper (GLM) detects total lightning, it is currently not used to distinguish intra-cloud (IC) lightning from cloud-to-ground (CG) lightning. This research explores the classification of GLM flashes into CG/IC using the optical attributes of lightning. GLM flashes are matched to ENTLN flashes to create a training dataset of CG and IC flashes for a Random Forest model. GLM flash and group characteristics, including the flash energy, child count, grandchild count, maximum number of events in a group (MNEG), maximum group area (MGA), flash duration, propagation, elongation, flash footprint, maximum group energy, and mean group energy are collected. These flash characteristics are then implemented into the model and used to predict CG vs. IC flash classification. Results of model implementation are revealed and skill scores including the probability of detection (POD), false alarm rate (FAR), critical score index (CSI), and percent correct (PC) are presented. The importance of each parameter as a predictor in the Random Forest algorithm is also discussed. Initial results show that the maximum group area, the mean energy, the time illuminated, the time of day and the location of the flash are the strongest predictors in flash type. Preliminary results also reveal good skill in the model prediction of flash type. Using the classification algorithm, the Cloud Flash Fraction (CFF) is calculated for the GLM domain and the CFF over different regions is discussed.