TY - JOUR
T1 - A Machine-Learning Approach to Predicting Daily Wildfire Expansion Rate
AU - Shmuel, Assaf
AU - Heifetz, Eyal
N1 - Publisher Copyright:
© 2023 by the authors.
PY - 2023/8
Y1 - 2023/8
N2 - Accurate predictions of daily wildfire growth rates are crucial, as extreme wildfires have become increasingly frequent in recent years. The factors which determine wildfire growth rates are complex and depend on numerous meteorological factors, topography, and fuel loads. In this paper, we have built upon previous studies that have mapped daily burned areas at the individual fire level around the globe. We applied several Machine Learning (ML) algorithms including XGBoost, Random Forest, and Multilayer Perceptron to predict daily fire growth rate based on meteorological factors, topography, and fuel loads. Our best model on the entire dataset obtained a 1.15 km2 MAE. The ML model obtained a 90% accuracy when predicting whether a fire’s growth rate will increase or decrease the following day, compared to 61% using a logistic regression. We discuss the central factors that determine wildfire growth rate. To the best of our knowledge, this study is the first to perform such analyses on a global dataset.
AB - Accurate predictions of daily wildfire growth rates are crucial, as extreme wildfires have become increasingly frequent in recent years. The factors which determine wildfire growth rates are complex and depend on numerous meteorological factors, topography, and fuel loads. In this paper, we have built upon previous studies that have mapped daily burned areas at the individual fire level around the globe. We applied several Machine Learning (ML) algorithms including XGBoost, Random Forest, and Multilayer Perceptron to predict daily fire growth rate based on meteorological factors, topography, and fuel loads. Our best model on the entire dataset obtained a 1.15 km2 MAE. The ML model obtained a 90% accuracy when predicting whether a fire’s growth rate will increase or decrease the following day, compared to 61% using a logistic regression. We discuss the central factors that determine wildfire growth rate. To the best of our knowledge, this study is the first to perform such analyses on a global dataset.
KW - fire growth rate
KW - fire weather
KW - machine learning
KW - wildfires
UR - http://www.scopus.com/inward/record.url?scp=85168936316&partnerID=8YFLogxK
U2 - 10.3390/fire6080319
DO - 10.3390/fire6080319
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:85168936316
SN - 2571-6255
VL - 6
JO - Fire
JF - Fire
IS - 8
M1 - 319
ER -