Koh, Jonathan (2023). Gradient boosting with extreme-value theory for wildfire prediction. Extremes, 26(2), pp. 273-299. Springer 10.1007/s10687-022-00454-6
|
Text
s10687-022-00454-6.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (4MB) | Preview |
This paper details the approach of the team Kohrrelation in the 2021 Extreme Value Analysis data challenge, dealing with the prediction of wildfire counts and sizes over the contiguous US. Our approach uses ideas from extreme-value theory in a machine learning context with theoretically justified loss functions for gradient boosting. We devise a spatial cross-validation scheme and show that in our setting it provides a better proxy for test set performance than naive cross-validation. The predictions are benchmarked against boosting approaches with different loss functions, and perform competitively in terms of the score criterion, finally placing second in the competition ranking.
Item Type: |
Journal Article (Original Article) |
|---|---|
Division/Institute: |
08 Faculty of Science > Department of Mathematics and Statistics > Institute of Mathematical Statistics and Actuarial Science 10 Strategic Research Centers > Oeschger Centre for Climate Change Research (OCCR) 08 Faculty of Science > Institute of Geography |
UniBE Contributor: |
Koh Boon Han, Jonathan |
Subjects: |
300 Social sciences, sociology & anthropology > 360 Social problems & social services 500 Science > 510 Mathematics 300 Social sciences, sociology & anthropology > 310 Statistics |
ISSN: |
1386-1999 |
Publisher: |
Springer |
Language: |
English |
Submitter: |
Jonathan Koh Boon Han |
Date Deposited: |
21 Mar 2023 15:53 |
Last Modified: |
23 Apr 2023 02:18 |
Publisher DOI: |
10.1007/s10687-022-00454-6 |
BORIS DOI: |
10.48350/180444 |
URI: |
https://boris.unibe.ch/id/eprint/180444 |
Actions (login required)
 |
Edit item |