Inference of Wildfire Causes From Their Physical, Biological, Social and Management Attributes
Abstract Effective wildfire prevention includes actions to deliberately target different wildfire causes. However, the cause of an increasing number of wildfires is unknown, hindering targeted prevention efforts. We developed a machine learning model of wildfire ignition cause across the western Uni...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Earth's Future |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2024EF005187 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583396332666880 |
|---|---|
| author | Yavar Pourmohamad John T. Abatzoglou Erica Fleishman Karen C. Short Jacquelyn Shuman Amir AghaKouchak Matthew Williamson Seyd Teymoor Seydi Mojtaba Sadegh |
| author_facet | Yavar Pourmohamad John T. Abatzoglou Erica Fleishman Karen C. Short Jacquelyn Shuman Amir AghaKouchak Matthew Williamson Seyd Teymoor Seydi Mojtaba Sadegh |
| author_sort | Yavar Pourmohamad |
| collection | DOAJ |
| description | Abstract Effective wildfire prevention includes actions to deliberately target different wildfire causes. However, the cause of an increasing number of wildfires is unknown, hindering targeted prevention efforts. We developed a machine learning model of wildfire ignition cause across the western United States on the basis of physical, biological, social, and management attributes associated with wildfires. Trained on wildfires from 1992 to 2020 with 12 known causes, the overall accuracy of our model exceeded 70% when applied to out‐of‐sample test data. Our model more accurately separated wildfires ignited by natural versus human causes (93% accuracy), and discriminated among the 11 classes of human‐ignited wildfires with 55% accuracy. Our model attributed the greatest percentage of 150,247 wildfires from 1992 to 2020 for which the ignition source was unknown to equipment and vehicle use (21%), lightning (20%), and arson and incendiarism (18%). |
| format | Article |
| id | doaj-art-31cc6c0340ca4e119108891a69f6d170 |
| institution | Kabale University |
| issn | 2328-4277 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Earth's Future |
| spelling | doaj-art-31cc6c0340ca4e119108891a69f6d1702025-01-28T15:40:38ZengWileyEarth's Future2328-42772025-01-01131n/an/a10.1029/2024EF005187Inference of Wildfire Causes From Their Physical, Biological, Social and Management AttributesYavar Pourmohamad0John T. Abatzoglou1Erica Fleishman2Karen C. Short3Jacquelyn Shuman4Amir AghaKouchak5Matthew Williamson6Seyd Teymoor Seydi7Mojtaba Sadegh8Department of Civil Engineering Boise State University Boise ID USAManagement of Complex Systems Department University of California Merced CA USACollege of Earth, Ocean, and Atmospheric Sciences Oregon State University Corvallis OR USAUSDA Forest Service Rocky Mountain Research Station Missoula MT USAEarth Science Division NASA Ames Research Center Moffett Field CA USADepartment of Civil and Environmental Engineering University of California Irvine CA USAHuman‐Environment Systems Boise State University Boise ID USADepartment of Civil Engineering Boise State University Boise ID USADepartment of Civil Engineering Boise State University Boise ID USAAbstract Effective wildfire prevention includes actions to deliberately target different wildfire causes. However, the cause of an increasing number of wildfires is unknown, hindering targeted prevention efforts. We developed a machine learning model of wildfire ignition cause across the western United States on the basis of physical, biological, social, and management attributes associated with wildfires. Trained on wildfires from 1992 to 2020 with 12 known causes, the overall accuracy of our model exceeded 70% when applied to out‐of‐sample test data. Our model more accurately separated wildfires ignited by natural versus human causes (93% accuracy), and discriminated among the 11 classes of human‐ignited wildfires with 55% accuracy. Our model attributed the greatest percentage of 150,247 wildfires from 1992 to 2020 for which the ignition source was unknown to equipment and vehicle use (21%), lightning (20%), and arson and incendiarism (18%).https://doi.org/10.1029/2024EF005187wildfiremachine learningwildfire preventionrisk mitigationwildfire attributes |
| spellingShingle | Yavar Pourmohamad John T. Abatzoglou Erica Fleishman Karen C. Short Jacquelyn Shuman Amir AghaKouchak Matthew Williamson Seyd Teymoor Seydi Mojtaba Sadegh Inference of Wildfire Causes From Their Physical, Biological, Social and Management Attributes Earth's Future wildfire machine learning wildfire prevention risk mitigation wildfire attributes |
| title | Inference of Wildfire Causes From Their Physical, Biological, Social and Management Attributes |
| title_full | Inference of Wildfire Causes From Their Physical, Biological, Social and Management Attributes |
| title_fullStr | Inference of Wildfire Causes From Their Physical, Biological, Social and Management Attributes |
| title_full_unstemmed | Inference of Wildfire Causes From Their Physical, Biological, Social and Management Attributes |
| title_short | Inference of Wildfire Causes From Their Physical, Biological, Social and Management Attributes |
| title_sort | inference of wildfire causes from their physical biological social and management attributes |
| topic | wildfire machine learning wildfire prevention risk mitigation wildfire attributes |
| url | https://doi.org/10.1029/2024EF005187 |
| work_keys_str_mv | AT yavarpourmohamad inferenceofwildfirecausesfromtheirphysicalbiologicalsocialandmanagementattributes AT johntabatzoglou inferenceofwildfirecausesfromtheirphysicalbiologicalsocialandmanagementattributes AT ericafleishman inferenceofwildfirecausesfromtheirphysicalbiologicalsocialandmanagementattributes AT karencshort inferenceofwildfirecausesfromtheirphysicalbiologicalsocialandmanagementattributes AT jacquelynshuman inferenceofwildfirecausesfromtheirphysicalbiologicalsocialandmanagementattributes AT amiraghakouchak inferenceofwildfirecausesfromtheirphysicalbiologicalsocialandmanagementattributes AT matthewwilliamson inferenceofwildfirecausesfromtheirphysicalbiologicalsocialandmanagementattributes AT seydteymoorseydi inferenceofwildfirecausesfromtheirphysicalbiologicalsocialandmanagementattributes AT mojtabasadegh inferenceofwildfirecausesfromtheirphysicalbiologicalsocialandmanagementattributes |