Lightning Prediction under Uncertainty: DeepLight with Hazy Loss

TL;DR

DeepLight is a novel deep learning model that predicts lightning by integrating multi-source meteorological data and a special loss function to handle uncertainty, significantly outperforming existing methods.

Contribution

The paper introduces DeepLight, a new deep learning architecture with a Hazy Loss function that better captures lightning's spatial-temporal uncertainty and utilizes diverse meteorological data.

Findings

DeepLight improves the Equitable Threat Score by 18-30%.

It effectively captures spatial correlations using multi-branch convolution.

The Hazy Loss enhances learning amidst lightning unpredictability.

Abstract

Lightning, a common feature of severe meteorological conditions, poses significant risks, from direct human injuries to substantial economic losses. These risks are further exacerbated by climate change. Early and accurate prediction of lightning would enable preventive measures to safeguard people, protect property, and minimize economic losses. In this paper, we present DeepLight, a novel deep learning architecture for predicting lightning occurrences. Existing prediction models face several critical limitations: i) they often struggle to capture the dynamic spatial context and the inherent randomness of lightning events, including whether lightning occurs and its variability in location and timing even under similar meteorological conditions; ii) they underutilize key observational data, such as radar reflectivity and cloud properties; and iii) they rely heavily on Numerical Weather Prediction (NWP) systems, which are both computationally expensive and highly sensitive to parameter settings. To overcome these challenges, DeepLight leverages multi-source meteorological data, including radar reflectivity, cloud properties, and historical lightning occurrences through a dual-encoder architecture. By employing multi-branch convolution techniques, it dynamically captures spatial correlations across varying extents. Furthermore, its novel Hazy Loss function explicitly addresses the spatio-temporal uncertainty of lightning by penalizing deviations based on proximity to true events, enabling the model to better learn patterns amidst randomness. Extensive experiments show that DeepLight improves the Equitable Threat Score (ETS) by 18\%--30\% over state-of-the-art methods, establishing it as a robust solution for lightning prediction.