Developing novel machine-learning-based fire weather indices
Accurate wildfire risk estimation is an essential yet challenging task. As the frequency of extreme fire weather and wildfires is on the rise, forest managers and firefighters require accurate wildfire risk estimations to successfully implement forest management and firefighting strategies. Wildfire...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/acc008 |
| _version_ | 1797844630791782400 |
|---|---|
| author | Assaf Shmuel Eyal Heifetz |
| author_facet | Assaf Shmuel Eyal Heifetz |
| author_sort | Assaf Shmuel |
| collection | DOAJ |
| description | Accurate wildfire risk estimation is an essential yet challenging task. As the frequency of extreme fire weather and wildfires is on the rise, forest managers and firefighters require accurate wildfire risk estimations to successfully implement forest management and firefighting strategies. Wildfire risk depends on non-linear interactions between multiple factors; therefore, the performance of linear models in its estimation is limited. To date, several traditional fire weather indices (FWIs) have been commonly used by weather services, such as the Canadian FWI.@Traditional FWIs are primarily based on empirical and statistical analyses. In this paper, we propose a novel FWI that was developed using machine learning—the machine learning based fire weather index (MLFWI). We present the performance of the MLFWI and compare it with various traditional FWIs. We find that the MLFWI significantly outperforms traditional indices in predicting wildfire occurrence, achieving an area under the curve score of 0.99 compared to 0.62–0.80. We recommend applying the MLFWI in wildfire warning systems. |
| first_indexed | 2024-04-09T17:25:25Z |
| format | Article |
| id | doaj.art-e540b6dc681c458b81b63d50594ea92e |
| institution | Directory Open Access Journal |
| issn | 2632-2153 |
| language | English |
| last_indexed | 2024-04-09T17:25:25Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj.art-e540b6dc681c458b81b63d50594ea92e2023-04-18T13:53:04ZengIOP PublishingMachine Learning: Science and Technology2632-21532023-01-014101502910.1088/2632-2153/acc008Developing novel machine-learning-based fire weather indicesAssaf Shmuel0https://orcid.org/0000-0002-1794-9381Eyal Heifetz1https://orcid.org/0000-0002-3584-3978Department of Geophysics, Porter School of the Environment and Earth Sciences, Tel Aviv University , Tel Aviv 69978, IsraelDepartment of Geophysics, Porter School of the Environment and Earth Sciences, Tel Aviv University , Tel Aviv 69978, IsraelAccurate wildfire risk estimation is an essential yet challenging task. As the frequency of extreme fire weather and wildfires is on the rise, forest managers and firefighters require accurate wildfire risk estimations to successfully implement forest management and firefighting strategies. Wildfire risk depends on non-linear interactions between multiple factors; therefore, the performance of linear models in its estimation is limited. To date, several traditional fire weather indices (FWIs) have been commonly used by weather services, such as the Canadian FWI.@Traditional FWIs are primarily based on empirical and statistical analyses. In this paper, we propose a novel FWI that was developed using machine learning—the machine learning based fire weather index (MLFWI). We present the performance of the MLFWI and compare it with various traditional FWIs. We find that the MLFWI significantly outperforms traditional indices in predicting wildfire occurrence, achieving an area under the curve score of 0.99 compared to 0.62–0.80. We recommend applying the MLFWI in wildfire warning systems.https://doi.org/10.1088/2632-2153/acc008machine learningfire weather indicesforest managementwildfire risk |
| spellingShingle | Assaf Shmuel Eyal Heifetz Developing novel machine-learning-based fire weather indices Machine Learning: Science and Technology machine learning fire weather indices forest management wildfire risk |
| title | Developing novel machine-learning-based fire weather indices |
| title_full | Developing novel machine-learning-based fire weather indices |
| title_fullStr | Developing novel machine-learning-based fire weather indices |
| title_full_unstemmed | Developing novel machine-learning-based fire weather indices |
| title_short | Developing novel machine-learning-based fire weather indices |
| title_sort | developing novel machine learning based fire weather indices |
| topic | machine learning fire weather indices forest management wildfire risk |
| url | https://doi.org/10.1088/2632-2153/acc008 |
| work_keys_str_mv | AT assafshmuel developingnovelmachinelearningbasedfireweatherindices AT eyalheifetz developingnovelmachinelearningbasedfireweatherindices |