Identifying lightning processes in ERA5  soundings with deep learning

Ehrensperger, Gregor; Simon, Thorsten; Mayr, Georg J.; Hell, Tobias

doi:10.5194/gmd-18-1141-2025

Articles | Volume 18, issue 4

https://doi.org/10.5194/gmd-18-1141-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-18-1141-2025

© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 4

Development and technical paper

|

26 Feb 2025

Development and technical paper |

| 26 Feb 2025

Identifying lightning processes in ERA5 soundings with deep learning

Gregor Ehrensperger, Thorsten Simon, Georg J. Mayr, and Tobias Hell

Viewed

Since the preprint corresponding to this journal article was posted outside of Copernicus Publications, the preprint-related metrics are limited to HTML views.

Total article views: 4,609 (including HTML, PDF, and XML)

HTML	PDF	XML	Total	BibTeX	EndNote
3,938	488	183	4,609	142	192

HTML: 3,938
PDF: 488
XML: 183
Total: 4,609
BibTeX: 142
EndNote: 192

Views and downloads (calculated since 27 Jun 2024)

Month	HTML	PDF	XML	Total
Jun 2024	35	0	35
Jul 2024	210	0	210
Aug 2024	122	0	122
Sep 2024	58	0	58
Oct 2024	56	0	56
Nov 2024	46	0	46
Dec 2024	18	0	18
Jan 2025	82	0	82
Feb 2025	127	10	1	138
Mar 2025	153	12	2	167
Apr 2025	77	11	2	90
May 2025	85	9	2	96
Jun 2025	82	13	22	117
Jul 2025	79	3	1	83
Aug 2025	187	6	1	194
Sep 2025	444	12	0	456
Oct 2025	121	38	2	161
Nov 2025	191	29	7	227
Dec 2025	202	43	12	257
Jan 2026	340	38	10	388
Feb 2026	355	23	6	384
Mar 2026	129	29	4	162
Apr 2026	125	49	9	183
May 2026	105	14	4	123
Jun 2026	31	14	4	49
Jul 2026	43	10	3	56
Aug 2026	58	16	9	83
Sep 2026	166	44	46	256
Oct 2026	179	55	34	268
Nov 2026	32	10	2	44

Cumulative views and downloads (calculated since 27 Jun 2024)

Month	HTML	PDF	XML	Total
Jun 2024	35	0	35
Jul 2024	210	0	210
Aug 2024	122	0	122
Sep 2024	58	0	58
Oct 2024	56	0	56
Nov 2024	46	0	46
Dec 2024	18	0	18
Jan 2025	82	0	82
Feb 2025	127	10	1	138
Mar 2025	153	12	2	167
Apr 2025	77	11	2	90
May 2025	85	9	2	96
Jun 2025	82	13	22	117
Jul 2025	79	3	1	83
Aug 2025	187	6	1	194
Sep 2025	444	12	0	456
Oct 2025	121	38	2	161
Nov 2025	191	29	7	227
Dec 2025	202	43	12	257
Jan 2026	340	38	10	388
Feb 2026	355	23	6	384
Mar 2026	129	29	4	162
Apr 2026	125	49	9	183
May 2026	105	14	4	123
Jun 2026	31	14	4	49
Jul 2026	43	10	3	56
Aug 2026	58	16	9	83
Sep 2026	166	44	46	256
Oct 2026	179	55	34	268
Nov 2026	32	10	2	44

Viewed (geographical distribution)

Since the preprint corresponding to this journal article was posted outside of Copernicus Publications, the preprint-related metrics are limited to HTML views.

Total article views: 4,609 (including HTML, PDF, and XML) Thereof 4,525 with geography defined and 84 with unknown origin.

Country	#	Views	%

1

1

Cited

Saved (final revised paper)

Latest update: 07 Nov 2026

Short summary

As lightning is a brief and localized event, it is not explicitly resolved in atmospheric models. Instead, expert-based auxiliary descriptions are used to assess it. This study explores how AI can improve our understanding of lightning without relying on traditional expert knowledge. We reveal that AI independently identified the key factors known to experts as essential for lightning in the Alps region. This shows how knowledge discovery could be sped up in areas with limited expert knowledge.