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

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

doi:https://doi.org/10.5194/nhess-22-577-2022

Articles | Volume 22, issue 2

https://doi.org/10.5194/nhess-22-577-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/nhess-22-577-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

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

Data sets

Machine learning dataset for "Nowcasting thunderstorm hazards using machine learning: the impact of data sources on performance" J. Leinonen, U. Hamann, U. Germann, and J. R. Mecikalski https://doi.org/10.5281/zenodo.5566730

Next Generation Radar (NEXRAD) Level 2 Base Data NOAA National Weather Service (NWS) Radar Operations Center https://doi.org/10.7289/V5W9574V

NOAA GOES-R Series Advanced Baseline Imager (ABI) Level 1b Radiances GOES-R Calibration Working Group and GOES-R Series Program https://doi.org/10.7289/V5BV7DSR

NOAA GOES-R Series Advanced Baseline Imager (ABI) Level 2 Cloud Top Height (ACHA) GOES-R Algorithm Working Group and GOES-R Series Program Office https://doi.org/10.7289/V5HX19ZQ

NOAA GOES-R Series Advanced Baseline Imager (ABI) Level 2 Cloud Optical Depth (COD) GOES-R Algorithm Working Group and GOES-R Series Program Office https://doi.org/10.7289/V58G8J02

NOAA GOES-R Series Advanced Baseline Imager (ABI) Level 2 Cloud Top Pressure (CTP) GOES-R Algorithm Working Group and GOES-R Series Program Office https://doi.org/10.7289/V5D50K85

NOAA GOES-R Series Advanced Baseline Imager (ABI) Level 2 Derived Stability Indices GOES-R Algorithm Working Group and GOES-R Series Program Office https://doi.org/10.7289/V50Z71KF

ASTER Global Digital Elevation Model V003 NASA/METI/AIST/Japan Spacesystems and US/Japan ASTER Science Team https://doi.org/10.5067/ASTER/ASTGTM.003

Model code and software

Machine learning code and dataset for "Nowcasting thunderstorm hazards using machine learning: the impact of data sources on performance" J. Leinonen, U. Hamann, U. Germann, and J. R. Mecikalski https://doi.org/10.5281/zenodo.6206919

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.