Publication Date

6-1-2021

Document Type

Article

Publication Title

Remote Sensing

Volume

13

Issue

11

DOI

10.3390/rs13112203

Abstract

Producing high-resolution near-real-time forecasts of fire behavior and smoke impact that are useful for fire and air quality management requires accurate initialization of the fire location. One common representation of the fire progression is through the fire arrival time, which defines the time that the fire arrives at a given location. Estimating the fire arrival time is critical for initializing the fire location within coupled fire-atmosphere models. We present a new method that utilizes machine learning to estimate the fire arrival time from satellite data in the form of burning/not burning/no data rasters. The proposed method, based on a support vector machine (SVM), is tested on the 10 largest California wildfires of the 2020 fire season, and evaluated using independent observed data from airborne infrared (IR) fire perimeters. The SVM method results indicate a good agreement with airborne fire observations in terms of the fire growth and a spatial representation of the fire extent. A 12% burned area absolute percentage error, a 5% total burned area mean percentage error, a 0.21 False Alarm Ratio average, a 0.86 Probability of Detection average, and a 0.82 Sørensen’s coefficient average suggest that this method can be used to monitor wildfires in near-real-time and provide accurate fire arrival times for improving fire modeling even in the absence of IR fire perimeters.

Funding Number

ICER-1664175

Funding Sponsor

National Science Foundation

Keywords

Active fires satellite data, Fire monitoring, Machine learning, Support vector machine

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Department

Research Foundation; Meteorology and Climate Science

Download

Share

COinS