用深度学习预测全球闪电密度，准确率高达0.96。
Mjölnir: A Deep Learning Parametrization Framework for Global Lightning Flash Density
- 基于InceptionNeXt和SENet的多任务模型，学习大气条件与闪电关系。
- 全球年均闪电分布相关性达0.96，精准捕捉季节和区域特征。
- 适合气候模拟与灾害预警，助力下一代地球系统模型研发。
近年来，基于人工智能的天气预报模型（如FourCastNet、Pangu-Weather、GraphCast）展现了深度学习在模拟复杂大气动力学方面的强大能力。在此基础上，我们提出Mjölnir，一种新型的全球闪电闪击密度深度学习参数化框架。该模型基于ERA5大气预测因子和全球闪电定位网络（WWLLN）观测数据，在日尺度和1度空间分辨率下进行训练，捕捉大尺度环境条件与闪电活动之间的非线性映射关系。模型采用InceptionNeXt主干网络结合SENet，并采用多任务学习策略，同时预测闪电发生与强度。大量评估表明，Mjölnir能准确复现闪电活动的全球分布、季节变化和区域特征，年平均场的全局皮尔逊相关系数达0.96。结果表明，Mjölnir不仅是一种高效的数据驱动型全球闪电参数化方案，也为下一代地球系统模型（AI-ESMs）提供了有前景的AI建模路径。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。