Mjölnir: A Deep Learning Parametrization Framework for Global Lightning Flash Density

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Cheon, Minjong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915440873177088
author Cheon, Minjong
author_facet Cheon, Minjong
contents Recent advances in AI-based weather forecasting models, such as FourCastNet, Pangu-Weather, and GraphCast, have demonstrated the remarkable ability of deep learning to emulate complex atmospheric dynamics. Building on this momentum, we propose Mjölnir, a novel deep learning-based framework for global lightning flash density parameterization. Trained on ERA5 atmospheric predictors and World Wide Lightning Location Network (WWLLN) observations at a daily temporal resolution and 1 degree spatial resolution, Mjölnir captures the nonlinear mapping between large-scale environmental conditions and lightning activity. The model architecture is based on the InceptionNeXt backbone with SENet, and a multi-task learning strategy to simultaneously predict lightning occurrence and magnitude. Extensive evaluations yield that Mollnir accurately reproduces the global distribution, seasonal variability, and regional characteristics of lightning activity, achieving a global Pearson correlation coefficient of 0.96 for annual mean fields. These results suggest that Mjölnir serves not only as an effective data-driven global lightning parameterization but also as a promising AI-based scheme for next-generation Earth system models (AI-ESMs).
format Preprint
id arxiv_https___arxiv_org_abs_2504_19822
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mjölnir: A Deep Learning Parametrization Framework for Global Lightning Flash Density
Cheon, Minjong
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Atmospheric and Oceanic Physics
Recent advances in AI-based weather forecasting models, such as FourCastNet, Pangu-Weather, and GraphCast, have demonstrated the remarkable ability of deep learning to emulate complex atmospheric dynamics. Building on this momentum, we propose Mjölnir, a novel deep learning-based framework for global lightning flash density parameterization. Trained on ERA5 atmospheric predictors and World Wide Lightning Location Network (WWLLN) observations at a daily temporal resolution and 1 degree spatial resolution, Mjölnir captures the nonlinear mapping between large-scale environmental conditions and lightning activity. The model architecture is based on the InceptionNeXt backbone with SENet, and a multi-task learning strategy to simultaneously predict lightning occurrence and magnitude. Extensive evaluations yield that Mollnir accurately reproduces the global distribution, seasonal variability, and regional characteristics of lightning activity, achieving a global Pearson correlation coefficient of 0.96 for annual mean fields. These results suggest that Mjölnir serves not only as an effective data-driven global lightning parameterization but also as a promising AI-based scheme for next-generation Earth system models (AI-ESMs).
title Mjölnir: A Deep Learning Parametrization Framework for Global Lightning Flash Density
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2504.19822