A Multimodal Supervised Machine Learning Approach for Satellite-based Wildfire Identification in Europe

TL;DR

This paper presents a multimodal supervised machine learning method that combines satellite thermal data, land cover, and other sources to improve the accuracy of wildfire detection in Europe.

Contribution

It introduces a novel multimodal approach that integrates multiple data sources and cross-referenced datasets for more accurate wildfire hotspot identification.

Findings

Effective disambiguation of wildfire hotspots from other events

Improved accuracy over traditional single-source methods

Demonstrated success on European satellite data

Abstract

The increasing frequency of catastrophic natural events, such as wildfires, calls for the development of rapid and automated wildfire detection systems. In this paper, we propose a wildfire identification solution to improve the accuracy of automated satellite-based hotspot detection systems by leveraging multiple information sources. We cross-reference the thermal anomalies detected by the Moderate-resolution Imaging Spectroradiometer (MODIS) and the Visible Infrared Imaging Radiometer Suite (VIIRS) hotspot services with the European Forest Fire Information System (EFFIS) database to construct a large-scale hotspot dataset for wildfire-related studies in Europe. Then, we propose a novel multimodal supervised machine learning approach to disambiguate hotspot detections, distinguishing between wildfires and other events. Our methodology includes the use of multimodal data sources, such as the ERSI annual Land Use Land Cover (LULC) and the Copernicus Sentinel-3 data. Experimental results demonstrate the effectiveness of our approach in the task of wildfire identification.