Articles | Volume 22, issue 2
Research article
25 Feb 2022
Research article |  | 25 Feb 2022

Nowcasting thunderstorm hazards using machine learning: the impact of data sources on performance

Jussi Leinonen, Ulrich Hamann, Urs Germann, and John R. Mecikalski

Related authors

Reconstruction of the mass and geometry of snowfall particles from multi-angle snowflake camera (MASC) images
Jussi Leinonen, Jacopo Grazioli, and Alexis Berne
Atmos. Meas. Tech., 14, 6851–6866,,, 2021
Short summary
Unsupervised classification of snowflake images using a generative adversarial network and K-medoids classification
Jussi Leinonen and Alexis Berne
Atmos. Meas. Tech., 13, 2949–2964,,, 2020
Short summary
Marine liquid cloud geometric thickness retrieved from OCO-2's oxygen A-band spectrometer
Mark Richardson, Jussi Leinonen, Heather Q. Cronk, James McDuffie, Matthew D. Lebsock, and Graeme L. Stephens
Atmos. Meas. Tech., 12, 1717–1737,,, 2019
Short summary
Retrieval of snowflake microphysical properties from multifrequency radar observations
Jussi Leinonen, Matthew D. Lebsock, Simone Tanelli, Ousmane O. Sy, Brenda Dolan, Randy J. Chase, Joseph A. Finlon, Annakaisa von Lerber, and Dmitri Moisseev
Atmos. Meas. Tech., 11, 5471–5488,,, 2018
Short summary
Performance assessment of a triple-frequency spaceborne cloud–precipitation radar concept using a global cloud-resolving model
J. Leinonen, M. D. Lebsock, S. Tanelli, K. Suzuki, H. Yashiro, and Y. Miyamoto
Atmos. Meas. Tech., 8, 3493–3517,,, 2015
Short summary

Related subject area

Atmospheric, Meteorological and Climatological Hazards
Investigation of an extreme rainfall event during 8–12 December 2018 over central Vietnam – Part 1: Analysis and cloud-resolving simulation
Chung-Chieh Wang and Duc Van Nguyen
Nat. Hazards Earth Syst. Sci., 23, 771–788,,, 2023
Short summary
Increased spatial extent and likelihood of compound long-duration dry and hot events in China, 1961–2014
Yi Yang, Douglas Maraun, Albert Ossó, and Jianping Tang
Nat. Hazards Earth Syst. Sci., 23, 693–709,,, 2023
Short summary
Validating a tailored drought risk assessment methodology: drought risk assessment in local Papua New Guinea regions
Isabella Aitkenhead, Yuriy Kuleshov, Jessica Bhardwaj, Zhi-Weng Chua, Chayn Sun, and Suelynn Choy
Nat. Hazards Earth Syst. Sci., 23, 553–586,,, 2023
Short summary
Seasonal fire danger forecasts for supporting fire prevention management in an eastern Mediterranean environment: the case of Attica, Greece
Anna Karali, Konstantinos V. Varotsos, Christos Giannakopoulos, Panagiotis P. Nastos, and Maria Hatzaki
Nat. Hazards Earth Syst. Sci., 23, 429–445,,, 2023
Short summary
Uncovering the veil of night light changes in times of catastrophe
Vincent Schippers and Wouter Botzen
Nat. Hazards Earth Syst. Sci., 23, 179–204,,, 2023
Short summary

Cited articles

Abrams, M., Crippen, R., and Fujisada, H.: ASTER Global Digital Elevation Model (GDEM) and ASTER Global Water Body Dataset (ASTWBD), Remote Sens., 12, 1156,, 2020. a
Autonès, F. and Claudon, M.: Algorithm Theoretical Basis Document for the Convection Product Processors of the NWC/GEO, Tech. Rep. SAF/NWC/CDOP/MFT/SCI/ATBD/11, Meteo-France, Toulouse, (last access: 21 February 2022), 2012. a
Ayzel, G., Scheffer, T., and Heistermann, M.: RainNet v1.0: a convolutional neural network for radar-based precipitation nowcasting, Geosci. Model Dev., 13, 2631–2644,, 2020. a
Barras, H., Hering, A., Martynov, A., Noti, P.-A., Germann, U., and Martius, O.: Experiences with >50,000 Crowdsourced Hail Reports in Switzerland, B. Am. Meteorol. Soc., 100, 1429–1440,, 2019. a
Bedka, K., Murillo, E. M., Homeyer, C. R., Scarino, B., and Mersiovsky, H.: The Above-Anvil Cirrus Plume: An Important Severe Weather Indicator in Visible and Infrared Satellite Imagery, Weather Forecast., 33, 1159–1181,, 2018. a
Short summary
We evaluate the usefulness of different data sources and variables to the short-term prediction (nowcasting) of severe thunderstorms using machine learning. Machine-learning models are trained with data from weather radars, satellite images, lightning detection and weather forecasts and with terrain elevation data. We analyze the benefits provided by each of the data sources to predicting hazards (heavy precipitation, lightning and hail) caused by the thunderstorms.
Final-revised paper