Using AutoML and generative AI to predict the type of wildfire propagation in Canadian conifer forests

• Published in: Ecological informatics Vol. 82; p. 102711
• Main Authors: Khanmohammadi, Sadegh, Cruz, Miguel G., Perrakis, Daniel D.B., Alexander, Martin E., Arashpour, Mehrdad
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.09.2024
• Subjects: AutoGluon; Crown fire; Generative adversarial networks; Random Forest; TabPFN; Wildfire behaviour; XGBoost; AutoGluon; XGBoost; TabPFN; Generative adversarial networks; Wildfire behaviour; Crown fire; Random Forest
• ISSN: 1574-9541
• DOI: 10.1016/j.ecoinf.2024.102711

Accurate prediction of wildfire behaviour is critical for safe and effective fire management and suppression. This study focused on developing and evaluating machine learning (ML) models based on a dataset collected of outdoor experimental fires in Canadian conifer forests. Binary classification models (surface fire vs. crown fire) and multi-class fire type models (surface, passive crown, active crown) were created using ensemble tree methods (Random Forest, XGBoost) and automated ML (AutoGluon, TabPFN). Generative adversarial networks (GAN) were used to generate synthetic data to overcome imbalances in the type of fire distribution. The results show automated ML methods applied to the binary problem to perform best of all tested methods, with an overall accuracy of 91%. TabPFN had the highest accuracy for the multi-class problem, with the use of GAN improving model fit. Results show overfitting issues with some of the ML models, highlighting the need of independent evaluation when ML models are developed. The TabPFN models have potential for application in supporting fire management, namely in fuel management and identifying situations with high fire spread and intensity potential that can impact firefighter safety. •ML approach used to predict wildfire propagation type in Canadian conifer forests.•TabPFN methods outperformed other ML methods in independent evaluations.•Multi-class modelling used to predict surface, passive, and active crown fires.•Generative AI improved model performance with synthetic data for imbalanced classes.