Modeling Fire Risk in Hawai'i Using Satellite, Atmospheric and Geographic Data
Uloženo v:
| Název: | Modeling Fire Risk in Hawai'i Using Satellite, Atmospheric and Geographic Data |
|---|---|
| Autoři: | Spears, Tyler |
| Informace o vydavateli: | Zenodo, 2024. |
| Rok vydání: | 2024 |
| Témata: | Forest fire, Wildfires/statistics & numerical data |
| Popis: | Wildfires threaten ecosystems, communities, and property, underscoring the need for accurate predictive models for disaster management. This project develops a Deep Neural Network (DNN) to estimate wildfire occurrence probability by integrating meteorological data, satellite fire detection records, and static environmental features like topography and vegetation classifications. Using data since 2011, the model builds a sample from each satellite pixel, using meteorological, topographical, and fuel conditions as features and fire presence as the label. Temporal aggregation captures historical trends through averaged meteorological features. The DNN optimizes predictions using cross-entropy loss, producing spatial risk maps to support emergency planning and land management. This research highlights machine learning's potential in wildfire prediction, offering a framework for integrating environmental data to mitigate fire risks and address global challenges. |
| Druh dokumentu: | Report |
| Jazyk: | English |
| DOI: | 10.5281/zenodo.14502960 |
| DOI: | 10.5281/zenodo.14502961 |
| Rights: | CC BY |
| Přístupové číslo: | edsair.doi.dedup.....9d58a11b33d2bd93d576d1135912e2e6 |
| Databáze: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | Wildfires threaten ecosystems, communities, and property, underscoring the need for accurate predictive models for disaster management. This project develops a Deep Neural Network (DNN) to estimate wildfire occurrence probability by integrating meteorological data, satellite fire detection records, and static environmental features like topography and vegetation classifications. Using data since 2011, the model builds a sample from each satellite pixel, using meteorological, topographical, and fuel conditions as features and fire presence as the label. Temporal aggregation captures historical trends through averaged meteorological features. The DNN optimizes predictions using cross-entropy loss, producing spatial risk maps to support emergency planning and land management. This research highlights machine learning's potential in wildfire prediction, offering a framework for integrating environmental data to mitigate fire risks and address global challenges. |
|---|---|
| DOI: | 10.5281/zenodo.14502960 |