loading page

Wildfire dynamics from ECOSTRESS data and machine learning: The case of South-Eastern Australia’s black summer
  • +2
  • Ivone K Masara,
  • Shakthi Bharathi Murugesan,
  • Soe Win Myint,
  • Yuanhui Zhu,
  • Joshua B Fisher
Ivone K Masara
School of Geographical Sciences and Urban Planning, Arizona State University

Corresponding Author:[email protected]

Author Profile
Shakthi Bharathi Murugesan
School of Geographical Sciences and Urban Planning, Arizona State University
Author Profile
Soe Win Myint
School of Geographical Sciences and Urban Planning, Arizona State University
Author Profile
Yuanhui Zhu
Arizona State University
Author Profile
Joshua B Fisher
Chapman University
Author Profile

Abstract

In 2019–20 Australia was devastated by the worst wildfires observed in decades. NASA’s ECOsystem Space-borne Thermal Radiometer Experiment on Space Station (ECOSTRESS) mission, launched in 2018, captured many dynamics of the fires at high resolution, including ecosystem stress prior to the fires. We aimed to determine the predictive capacity of ECOSTRESS observations for fire occurrence and intensity in Southeast Australia. We found that ECOSTRESS data (evaporative stress index and water use efficiency) were highly predictive of fire dynamics (25-65% occurrence prediction accuracy for ESI; and, 40-95% occurrence prediction for WUE > 1 gCkg-1H2O alone, depending on their levels) with the ESI coefficient averaging approximately three times stronger than general topographic variables or meteorological variables. Our results, based on a logistic regression model, had an overall predictive accuracy of 83%, suggesting high potential of using ECOSTRESS data to project and examine fires in Australia and other similar regions of the world.