Modelling wildland fire burn severity in California using a spatial Super Learner approach
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914728180187136 |
|---|---|
| author | Simafranca, Nicholas Willoughby, Bryant O'Neil, Erin Farr, Sophie Reich, Brian J Giertych, Naomi Johnson, Margaret Pascolini-Campbell, Madeleine |
| author_facet | Simafranca, Nicholas Willoughby, Bryant O'Neil, Erin Farr, Sophie Reich, Brian J Giertych, Naomi Johnson, Margaret Pascolini-Campbell, Madeleine |
| contents | Given the increasing prevalence of wildland fires in the Western US, there is a critical need to develop tools to understand and accurately predict burn severity. We develop a machine learning model to predict post-fire burn severity using pre-fire remotely sensed data. Hydrological, ecological, and topographical variables collected from four regions of California - the sites of the Kincade fire (2019), the CZU Lightning Complex fire (2020), the Windy fire (2021), and the KNP Fire (2021) - are used as predictors of the difference normalized burn ratio. We hypothesize that a Super Learner (SL) algorithm that accounts for spatial autocorrelation using Vecchia's Gaussian approximation will accurately model burn severity. In all combinations of test and training sets explored, the results of our model showed the SL algorithm outperformed standard Linear Regression methods. After fitting and verifying the performance of the SL model, we use interpretable machine learning tools to determine the main drivers of severe burn damage, including greenness, elevation and fire weather variables. These findings provide actionable insights that enable communities to strategize interventions, such as early fire detection systems, pre-fire season vegetation clearing activities, and resource allocation during emergency responses. When implemented, this model has the potential to minimize the loss of human life, property, resources, and ecosystems in California. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_16187 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Modelling wildland fire burn severity in California using a spatial Super Learner approach Simafranca, Nicholas Willoughby, Bryant O'Neil, Erin Farr, Sophie Reich, Brian J Giertych, Naomi Johnson, Margaret Pascolini-Campbell, Madeleine Machine Learning Applications 62-08, 62P12 Given the increasing prevalence of wildland fires in the Western US, there is a critical need to develop tools to understand and accurately predict burn severity. We develop a machine learning model to predict post-fire burn severity using pre-fire remotely sensed data. Hydrological, ecological, and topographical variables collected from four regions of California - the sites of the Kincade fire (2019), the CZU Lightning Complex fire (2020), the Windy fire (2021), and the KNP Fire (2021) - are used as predictors of the difference normalized burn ratio. We hypothesize that a Super Learner (SL) algorithm that accounts for spatial autocorrelation using Vecchia's Gaussian approximation will accurately model burn severity. In all combinations of test and training sets explored, the results of our model showed the SL algorithm outperformed standard Linear Regression methods. After fitting and verifying the performance of the SL model, we use interpretable machine learning tools to determine the main drivers of severe burn damage, including greenness, elevation and fire weather variables. These findings provide actionable insights that enable communities to strategize interventions, such as early fire detection systems, pre-fire season vegetation clearing activities, and resource allocation during emergency responses. When implemented, this model has the potential to minimize the loss of human life, property, resources, and ecosystems in California. |
| title | Modelling wildland fire burn severity in California using a spatial Super Learner approach |
| topic | Machine Learning Applications 62-08, 62P12 |
| url | https://arxiv.org/abs/2311.16187 |