Forecasting Bushfire Risk: Integrating a new ground-based sensor network, remote sensing, and weather data to forecast forest fuel dryness

Bushfires in southern Australia have resulted in more than 825 deaths and destroyed more than 7400 houses since 1901. The economic cost of the 2020 bushfire season alone was estimated to be $100 billion. The “dryness” of leaves and litter (called fuel) within the forest is a strong determinant of the risk of bushfire, however this dryness is very difficult to adequately predict. This project aims to develop new tools for Australian bushfire managers to forescast and map fuel dryness and in doing so, better anticipate where, when, and how bushfires and prescribed burns will burn. This will save lives, protect property, and improve the allocation of limited firefighting resources.

This team's novel approach will develop machine learning algorithms to integrate a world-first network of 34 real-time “fuel dryness” sensors in forests, with spatial and temporal remote sensing and meteorological predictor variables, to forecast fuel dryness at high resolution across vast forested landscapes. The research group is an international leader in this research area, developing both biophysical and remote sensing-based models of fuel dryness. The team seeks to collaborate with MDAP (who will provide the technical knowledge of ML model development, and the computational resources to develop, train, and interact with new models) in the exploration and development of data-based models for landscape fuel dryness.