Articles | Volume 23, issue 22
Research article
24 Nov 2023
Research article |  | 24 Nov 2023

Machine-learning-based investigation of the variables affecting summertime lightning occurrence over the Southern Great Plains

Siyu Shan, Dale Allen, Zhanqing Li, Kenneth Pickering, and Jeff Lapierre

Data sets

Cloud Condensation Nuclei Particle Counter (AOSCCN1COL) J. Uin, E. Andrews, C. Salwen, O. Enekwizu, and C. Hayes

Cloud Condensation Nuclei Particle Counter (AOSCCN2COLAAVG) A. Koontz, J. Uin, E. Andrews, O. Enekwizu, C. Hayes, and C. Salwen

Active Remote Sensing of CLouds (ARSCL) product using Ka-band ARM Zenith Radars (ARSCLKAZR1KOLLIAS) K. Johnson, M. Jensen, and S. Giangrande

Active Remote Sensing of CLouds (ARSCL) product using Ka-band ARM Zenith Radars (ARSCLKAZR1KOLLIAS) K. Johnson, S. Giangrande, and T. Toto

Cloud Type Classification (CLDTYPE) D. Zhang, Y. Shi, and L. Riihimaki

Interpolated Sonde (INTERPOLATEDSONDE) M. Jensen, S. Giangrande, T. Fairless, and A. Zhou

Planetary Boundary Layer Height (PBLHTMPL1SAWYERLI) C. Sivaraman and D. Zhang

Video Disdrometer (VDIS) D. Wang and M. J. Bartholomew

ERA5 hourly data on pressure levels from 1940 to present H. Hersbach, B. Bell, P. Berrisford, G. Biavati, A. Horányi, J. Muñoz Sabater, J. Nicolas, C. Peubey, R. Radu, I. Rozum, D. Schepers, A. Simmons, C. Soci, D. Dee, and J-N. Thépaut

Download Daily Data US EPA - U.S. Environmental Protection Agency

MERRA-2 tavg1_2d_aer_Nx: 2d, 1-Hourly, Time-averaged, Single-Level, Assimilation, Aerosol Diagnostics V5.12.4 Global Modeling and Assimilation Office (GMAO)

Short summary

Several machine learning models are applied to identify important variables affecting lightning occurrence in the vicinity of the Southern Great Plains ARM site during the summer months of 2012–2020. We find that the random forest model is the best predictor among common classifiers. We rank variables in terms of their effectiveness in nowcasting ENTLN lightning and identify geometric cloud thickness, rain rate and convective available potential energy (CAPE) as the most effective predictors.

Final-revised paper