标题： 一种闪电击中密度的深度学习模型 显示英文标题

标题： A Deep Learning Model of Lightning Stroke Density

摘要： 闪电在地球的气候系统中起着关键作用，但现有的用于预测和地球系统模型的参数化方法在捕捉其频率的空间和时间变化方面仍有改进空间。 本研究利用 ERA 和 IMERG 数据集中的气象变量，开发了基于深度学习的闪电击中密度参数化方法。 使用 2010 至 2021 年的世界范围闪电定位网络 (WWLLN) 数据训练具有 U-Net 结构的卷积神经网络 (CNN)，并在 2022 和 2023 年的 WWLLN 闪电观测数据上进行评估。 与对流有效位能和降水的乘积相比，CNN 将平均域均值偏差降低了数量级，并在所有闪电条件下产生了显著更高的分数技能得分 (FSS) 值。 与之前发表的参数化方法相比，CNN 在海洋上表现出更高的技能，最佳性能的模拟和观测闪电击中密度气候学之间的 r2 值高达 0.93。 CNN 还能够准确捕捉事件尺度上闪电空间模式的 12 小时演变，且技能较高。 这些结果表明，深度学习在改进天气和地球系统模型中的闪电参数化方面具有潜力。 显示英文摘要

摘要： Lightning plays a crucial role in the Earth's climate system, yet existing parameterizations for use in forecasting and earth system models show room for improvement in capturing spatial and temporal variations in its frequency. This study develops deep learning-based parameterizations of lightning stroke density using meteorological variables from the ERA and IMERG datasets. Convolutional neural networks (CNNs) with U-Net architectures are trained using World Wide Lightning Location Network (WWLLN) data from 2010 to 2021 and evaluated on WWLLN lightning observations from 2022 and 2023. The CNNs reduce the average domain mean bias by an order of magnitude and produce significantly higher Fractions Skill Score (FSS) values across all lightning regimes compared to the multiplicative product of CAPE and precipitation. The CNNs show skill relative to previously published parameterizations over the oceans especially, with r2 values as high as 0.93 achieved between the best performing modeled and observed lightning stroke density climatologies. The CNNs are also able to accurately capture the 12-hourly evolution of lightning spatial patterns on an event-scale with high skill. These results show the potential for deep learning to improve on lightning parameterizations in weather and earth system models.