Data-Driven Wildfire Risk Prediction in Northern California

Abstract

Over the years, rampant wildfires have plagued the state of California, creating economic and environmental loss. In 2018, wildfires cost nearly 800 million dollars in economic loss and claimed more than 100 lives in California. Over 1.6 million acres of land has burned and caused large sums of environmental damage. Although, recently, researchers have introduced machine learning models and algorithms in predicting the wildfire risks, these results focused on special perspectives and were restricted to a limited number of data parameters. In this paper, we have proposed two data-driven machine learning approaches based on random forest models to predict the wildfire risk at areas near Monticello and Winters, California. This study demonstrated how the models were developed and applied with comprehensive data parameters such as powerlines, terrain, and vegetation in different perspectives that improved the spatial and temporal accuracy in predicting the risk of wildfire including fire ignition. The combined model uses the spatial and the temporal parameters as a single combined dataset to train and predict the fire risk, whereas the ensemble model was fed separate parameters that were later stacked to work as a single model. Our experiment shows that the combined model produced better results compared to the ensemble of random forest models on separate spatial data in terms of accuracy. The models were validated with Receiver Operating Characteristic (ROC) curves, learning curves, and evaluation metrics such as: accuracy, confusion matrices, and classification report. The study results showed and achieved cutting-edge accuracy of 92% in predicting the wildfire risks, including ignition by utilizing the regional spatial and temporal data along with standard data parameters in Northern California.

Who are the actors and what are the factors that are used in models to map forest fire susceptibility? A systematic review

“…Model selection also needs to be considered when mapping forest fire susceptibility as model type affects accuracy (Malik et al 2021;Tuyen et al 2021). During the study period 2001-2021, 33 different models have been used globally to map forest fire susceptibility.…”

Data‐driven spatio‐temporal analysis of wildfire risk to power systems operation

“…Hence, their accuracy can be affected by the limited integration of the non-linear influence of variables, and similarly, do not fully utilise recent wildfire monitoring investments of grid utilities. Wildfire risk prediction has also been done where model performance using machine learning approaches have been evaluated [23]. Artificial intelligence techniques have also been effective for wildfire analysis and outperform conventional statistical methods [24][25][26].…”

RtFPS: An Interactive Map that Visualizes and Predicts Wildfires in the US

“…Most of the other studies listed the machine learning models and explained each of them by analyzing the result of performance metrics [14] [19]. They tend to dive deep to explain the prerequisite and algorithms of models, validating these models using cross-validation methods, focusing more on the comparing models [15]. None of them try to implement real-time predictions which is the core application for this research.…”