Assessing the performance and explainability of an avalanche danger forecast model

Cristina Pérez-Guillén, Frank Techel, Michele Volpi, and Alec van Herwijnen

Viewed

Total article views: 574 (including HTML, PDF, and XML)

HTML	PDF	XML	Total	BibTeX	EndNote
394	134	46	574	15	20

HTML: 394
PDF: 134
XML: 46
Total: 574
BibTeX: 15
EndNote: 20

Views and downloads (calculated since 06 Aug 2024)

Month	HTML	PDF	XML	Total
Aug 2024	110	36	16	162
Sep 2024	24	9	5	38
Oct 2024	42	16	1	59
Nov 2024	38	23	2	63
Dec 2024	48	24	3	75
Jan 2025	33	10	8	51
Feb 2025	13	1	7	21
Mar 2025	9	6	2	17
Apr 2025	77	9	2	88

Cumulative views and downloads (calculated since 06 Aug 2024)

Month	HTML	PDF	XML	Total
Aug 2024	110	36	16	162
Sep 2024	24	9	5	38
Oct 2024	42	16	1	59
Nov 2024	38	23	2	63
Dec 2024	48	24	3	75
Jan 2025	33	10	8	51
Feb 2025	13	1	7	21
Mar 2025	9	6	2	17
Apr 2025	77	9	2	88

HTML	PDF	XML	Total	BibTeX	EndNote
69	8	2	79	1	1

HTML	PDF	XML	Total	BibTeX	EndNote
325	126	44	495	14	19

Viewed (geographical distribution)

Total article views: 574 (including HTML, PDF, and XML) Thereof 574 with geography defined and 0 with unknown origin.

Country	#	Views	%


Total:	0
HTML:	0
PDF:	0
XML:	0


Total:	0
HTML:	0
PDF:	0
XML:	0


Total:	0
HTML:	0
PDF:	0
XML:	0

Latest update: 13 Apr 2025

Short summary

This study assesses the performance and explainability of a random-forest classifier for predicting dry-snow avalanche danger levels during initial live testing. The model achieved ∼ 70 % agreement with human forecasts, performing equally well in nowcast and forecast modes, while capturing the temporal dynamics of avalanche forecasting. The explainability approach enhances the transparency of the model's decision-making process, providing a valuable tool for operational avalanche forecasting.