Evaluating extreme precipitation forecasts: a threshold-weighted, spatial verification approach for comparing an AI weather prediction model against a high-resolution NWP model
Research, Science and Innovation Group, Bureau of Meteorology, Melbourne, Australia
Tracy Hertneky
NSF National Center for Atmospheric Research (NCAR) and Developmental Testbed Center (DTC), Boulder, CO, USA
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: 1,346 (including HTML, PDF, and XML)
HTML
PDF
XML
Total
BibTeX
EndNote
1,318
7
21
1,346
1
1
HTML: 1,318
PDF: 7
XML: 21
Total: 1,346
BibTeX: 1
EndNote: 1
Views and downloads (calculated since 04 Feb 2026)
Cumulative views and downloads
(calculated since 04 Feb 2026)
Total article views: 50 (including HTML, PDF, and XML)
HTML
PDF
XML
Total
BibTeX
EndNote
41
7
2
50
1
1
HTML: 41
PDF: 7
XML: 2
Total: 50
BibTeX: 1
EndNote: 1
Views and downloads (calculated since 10 Nov 2026)
Cumulative views and downloads
(calculated since 10 Nov 2026)
Total article views: 1,296 (including HTML, PDF, and XML)
HTML
PDF
XML
Total
BibTeX
EndNote
1,277
0
19
1,296
0
0
HTML: 1,277
PDF: 0
XML: 19
Total: 1,296
BibTeX: 0
EndNote: 0
Views and downloads (calculated since 04 Feb 2026)
Cumulative views and downloads
(calculated since 04 Feb 2026)
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: 1,346 (including HTML, PDF, and XML)
Thereof 1,337 with geography defined
and 9 with unknown origin.
Total article views: 50 (including HTML, PDF, and XML)
Thereof 50 with geography defined
and 0 with unknown origin.
Total article views: 1,296 (including HTML, PDF, and XML)
Thereof 1,287 with geography defined
and 9 with unknown origin.
This study introduces a verification method that accounts for differences in grid resolution when evaluating extreme event forecasts. We apply it to an artificial intelligence-based weather prediction model and a high-resolution numerical weather prediction model. Results show that, when assessed on equivalent neighborhood scales, the high resolution numerical weather prediction model only outperforms the AI system for short lead times in predicting extreme precipitation.
This study introduces a verification method that accounts for differences in grid resolution...