Multi-time Predictions of Wildfire Grid Map using Remote Sensing Local Data

TL;DR

This paper introduces a distributed learning framework utilizing remote sensing data for multi-week wildfire prediction across multiple locations, improving accuracy by accounting for incomplete data and dynamic online estimation.

Contribution

It presents a novel distributed, online, spatiotemporal modeling approach for wildfire prediction that handles incomplete observations and multiple time horizons.

Findings

Higher prediction accuracy than existing methods

Effective handling of incomplete state observations

Successful multi-week wildfire grid map predictions

Abstract

Due to recent climate changes, we have seen more frequent and severe wildfires in the United States. Predicting wildfires is critical for natural disaster prevention and mitigation. Advances in technologies in data processing and communication enabled us to access remote sensing data. With the remote sensing data, valuable spatiotemporal statistical models can be created and used for resource management practices. This paper proposes a distributed learning framework that shares local data collected in ten locations in the western USA throughout the local agents. The local agents aim to predict wildfire grid maps one, two, three, and four weeks in advance while online processing the remote sensing data stream. The proposed model has distinct features that address the characteristic need in prediction evaluations, including dynamic online estimation and time-series modeling. Local fire event triggers are not isolated between locations, and there are confounding factors when local data is analyzed due to incomplete state observations. Compared to existing approaches that do not account for incomplete state observation within wildfire time-series data, on average, we can achieve higher prediction performance.