[Statlist] Research Seminar in Statistics *FRIDAY, 25 FEBRUARY 2022* GSEM, University of Geneva

gsem-support-instituts g@em-@upport-|n@t|tut@ @end|ng |rom un|ge@ch
Mon Feb 21 08:33:36 CET 2022


Dear All,

We are pleased to invite you to our next Research Seminar.

Looking forward to seeing you


Organized by Prof. Sebastian Engelke on behalf of the Research Center for Statistics (https://www.unige.ch/gsem/en/research/institutes/rcs/)


FRIDAY, 22 FEBRUARY 2022 at 11:15am, Uni-Mail M 5220 & ONLINE

Zoom research webinar: https://unige.zoom.us/j/92924332087?pwd=U1U1NFk4dTFCRHBMeWYrSDBQcXBiQT09
Meeting ID: 929 2433 2087
Passcode: 399192


Modelling and Predicting Extreme Wildfires
Jonathan Boon Han Koh, University of Bern
https://www.imsv.unibe.ch/about_us/staff/koh_jonathan_boon_han/index_eng.html


ABSTRACT:
Accurate spatiotemporal modelling of conditions leading to moderate and large wildfires allows us to provide better understanding of mechanisms driving fire-prone ecosystems and improves risk management. This talk is based on the two papers: Koh et al. (2021, arXiv:2105.08004) and Koh (2021, arXiv:2110.09497). In the first paper, we develop a joint model for the occurrence intensity and the wildfire size distribution by combining extreme-value theory and point processes within a novel Bayesian hierarchical model, and use it to study daily summer wildfire data for the French Mediterranean basin during 1995--2018. The occurrence component models wildfire ignitions as a spatiotemporal log-Gaussian Cox process. Burnt areas are numerical marks attached to points and are considered as extreme if they exceed a high threshold. The size component is a two-component mixture varying in space and time that jointly models moderate and extreme fires. We capture non-linear influence of covariates (Fire Weather Index, forest cover) through component-specific smooth functions, which may vary with season. We propose estimating shared random effects between model components to reveal and interpret common drivers of different aspects of wildfire activity. This increases parsimony and reduces estimation uncertainty, giving better predictions. The second 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.


Visit the website: https://www.unige.ch/gsem/en/research/seminars/rcs/




More information about the Statlist mailing list