A Novel Approach for Predicting Large Wildfires Using Machine Learning Towards Environmental Justice via Environmental Remote Sensing and Atmospheric Reanalysis Data across the United States
Preprint
- 1 December 2023
- preprint
- Published by California Digital Library (CDL) in EarthArXiv
Abstract
Large wildfires (>125 hectares) in the United States account for over 95% of the burned area each year. Predicting large wildfires is imperative, however, current wildfire predictive models are region-based and computationally intensive. Using a scalable model based on easily available environmental and atmospheric data, this research aims to accurately predict across the United States whether large wildfires will develop. The data used in this study includes 2,109 wildfires over 20 years, representing 14 million hectares burned. Remote sensing environmental data (Normalized Difference Vegetation Index - NDVI, Enhanced Vegetation Index - EVI, Leaf Area Index - LAI, Fraction of Photosynthetically Active Radiation - FPAR, Land Surface Temperature during the Day - LST Day, and Land Surface Temperature during the Night - LST Night) consisting of 1.3 billion satellite observations was used. Atmospheric reanalysis data (u component of wind, v component of wind, relative humidity, temperature, and geopotential) at four pressure levels (300, 500, 700, and 850 Ha) were also factored. Six machine learning classification models (Logistic Regression, Decision Tree, Random Forest, eXtreme Gradient Boosting, K-Nearest-Neighbors, and Support Vector Machine) were created and tested on the resulting dataset to determine their accuracy in predicting large wildfires. Model validation tests and variable importance analysis were performed. The eXtreme Gradient Boosting (XGBoost) Classification model performed the best in predicting large wildfires, with 90.44% accuracy, a True Positive Rate of 0.92, and a True Negative Rate of 0.88. Furthermore, towards environmental justice, an analysis was performed to identify disadvantaged communities that are also vulnerable to wildfires. This model can be used by wildfire safety organizations to predict large wildfires with high accuracy and prioritize resource allocation to employ protective safeguards for impacted socioeconomically disadvantaged communities.Keywords
All Related Versions
- Published version: Remote Sensing, 15 (23), 5501.
This publication has 16 references indexed in Scilit:
- Wildfire smoke impacts respiratory health more than fine particles from other sources: observational evidence from Southern CaliforniaNature Communications, 2021
- A review of machine learning applications in wildfire science and managementEnvironmental Reviews, 2020
- Increased likelihood of heat-induced large wildfires in the Mediterranean BasinScientific Reports, 2020
- Machine learning to predict final fire size at the time of ignitionInternational Journal of Wildland Fire, 2019
- Reanalyses and Observations: What’s the Difference?Bulletin of the American Meteorological Society, 2016
- Wildfire Spread Prediction and Assimilation for FARSITE Using Ensemble Kalman Filtering 1Procedia Computer Science, 2016
- The role of satellite remote sensing in climate change studiesNature Climate Change, 2013
- The ERA‐Interim reanalysis: configuration and performance of the data assimilation systemQuarterly Journal of the Royal Meteorological Society, 2011
- Fire in the Earth SystemScience, 2009
- Fire intensity, fire severity and burn severity: a brief review and suggested usageInternational Journal of Wildland Fire, 2009