A multiclass short-term lightning predictor for the Amazon region using ground-based meteorological data and artificial neural network

Abstract

Lightning prediction is a complex task due to the intricate nature of this phenomenon. Various sectors of society, including aviation and civil defense, can benefit from accurate lightning occurrence information. Methodologies that can predict lightning occurrence are crucial to minimize the issues related to this phenomenon. In this work, we propose a novel approach using the machine learning model called Artificial Neural Network (ANN) to predict lightning occurrence one hour ahead. We use ground-based meteorological data from the National Institute of Meteorology (INMET) and the number of lightning per hour to feed the ANN model. We used a lightning dataset of six years of observation (2015–2020) from GLD360 to train, validate, and test machine learning algorithm models. A model was developed for each weather station. We use data from 24 stations distributed throughout the Brazilian Legal Amazon region. The multiclass predictor was based on three categories: no lightning, low-intensity, and high-intensity of lightning. We also developed a solution comprising two cascade ANN models, each performing binary prediction. The first predicts the occurrence or no occurrence of lightning, and the second predicts the intensity: low or high. The cascade approach showed superior performance compared to the regular approach.