We have discussed it with Karen Short. Potentially coming in the new version

Thanks to the Joint Fire Science Program for funding this research

*Our model attributed the greatest percentage of 150,247 wildfires from 1992 to 2020 for which the ignition source was unknown to equipment and vehicle use (21%), lightning (20%), and arson and incendiarism (18%).

*Our model more accurately separated wildfires ignited by natural versus human causes (93% accuracy), and discriminated among the 11 classes of human-ignited wildfires with 55% accuracy.

*ML models can identify the cause of wildfire ignitions and determine the contributions of diverse attributes to classification of cause
*Trained on wildfires from 1992 to 2020 with 12 known causes, the overall accuracy of our model exceeded 70% when applied to out-of-sample test data.

*The spatial and temporal distribution of wildfires is captured by associated biological, physical, social, and management attributes
*Wildfires are increasingly reported with an unknown cause (5-fold increase from 1992 to 2020), hindering targeted prevention strategies

Amirhossein Montazeri received three years of funding from the NASA FINESST program to model soil burn severity using satellite imagery and hashtag#MachineLearning:
lnkd.in/gJcUFegb

Yavar Pourmohammad received one year of funding from JFSP to develop a hashtag#MachineLearning model to infer the cause of wildfires that were recorded with an unknown cause using their attributes: lnkd.in/gJJraAqk