Thunderstorm Nowcasting With Deep Learning: A Multi‐Hazard Data Fusion Model

Jussi Leinonen, Ulrich Hamann, Ioannis Vasileios Sideris, Urs Germann

Geophysical Research Letters 2023 article cited by 52

Source Open-access PDF More in Climate & Environment

importance 6/10 ai assisted Meteorological Phenomena and Simulations hazard nowcasting stage: research

Problem

Short-term prediction of thunderstorm hazards (lightning, hail, heavy precipitation) is needed by first responders, infrastructure managers and aviation.

Why it matters

Thunderstorm hazards threaten lives, aviation safety and infrastructure with little warning time.

What the AI did

A deep learning model fuses weather radar, lightning detection, satellite imagery, numerical weather prediction and elevation data to predict three hazard types probabilistically; Shapley values quantify each data source's importance.

Results

Probabilistic predictions on 1 km grid, 5 min temporal resolution, lead times up to 60 min; radar products most important predictors. No skill scores stated in abstract.

Impact

Demonstrated multi-hazard nowcasting capability, but abstract gives no performance benchmarks or operational adoption.

Record

Venue	Geophysical Research Letters
Published	2023
Work type	article
Authors	Jussi Leinonen, Ulrich Hamann, Ioannis Vasileios Sideris, Urs Germann
Citations	52 (OpenAlex, at import time)
References	45
Model or method	deep learning model (specific architecture not stated in source)
Organization	not stated in source
Primary source	https://doi.org/10.1029/2022gl101626
Open access	gold
Keywords	deep learning, nowcasting, thunderstorm, hail, lightning, data fusion

Importance rating

6 / 10

significant — thousands to millions affected

Thunderstorm hazards threaten lives, aviation and infrastructure per abstract, but no scale, benchmarks or adoption are stated; significant multi-sector benefit inferred.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Climate & Environment

#	Paper	Year	Citations	Importance
1	Learning skillful medium-range global weather forecasting Rémi Lam, Álvaro Sánchez‐González, Matthew Willson, Peter Wirnsberger,...	2023	1,416	8
2	Accurate medium-range global weather forecasting with 3D neural networks Kaifeng Bi, Lingxi Xie, Hengheng Zhang, Xin Chen, Xiaotao Gu, Qi Chuan...	2023	1,631	8
3	FuXi: a cascade machine learning forecasting system for 15-day global weather forecast Lei Chen, Xiaohui Zhong, Feng Zhang, Yuan Cheng, Yinghui Xu, Qi Yuan,...	2023	355	8
4	Skilful nowcasting of extreme precipitation with NowcastNet Yuchen Zhang, Mingsheng Long, Kaiyuan Chen, Lanxiang Xing, Ronghua Jin...	2023	451	8
5	Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects Natei Ermias Benti, Mesfin Diro Chaka, Addisu Gezahegn Semie	2023	378	8