A deep learning framework for lightning forecasting with multi-source spatiotemporal data

Weather forecasting requires comprehensive analysis of a variety of meteorological data. Recent decades have witnessed the advance of weather observation and simulation technologies, triggering an explosion of meteorological data which are collected from multiple sources (e.g., radar, automatic stations and numerical weather prediction) and usually characterized by a spatiotemporal (ST) structure. As a result, the adequate exploition of these multi-source ST data emerges as a promising but challenging topic for weather forecasting. To address this issue, we propose a data-driven forecasting framework (referred to as LightNet+) based on deep neural networks using a lightning scenario. Our framework design enables LightNet+ to make forecasts by mining complementary information distributed across multiple data sources, which may be heterogeneous in spatial (continuous versus discrete) and temporal (observations from the past versus simulation of the future) domains. We evaluate LightNet+ using a real-world weather dataset in North China. The experimental results demonstrate: (a) LightNet+ produces significantly better forecasts than three established lightning schemes, and (b) the more data sources are fed into LightNet+, the higher forecasting quality it achieves.