Ben-ge: Extending BigEarthNet with Geographical and Environmental Data

TL;DR

This paper introduces the ben-ge dataset, which combines BigEarthNet-MM with geographical and environmental data to enhance land-use and land-cover classification and segmentation tasks in Earth observation.

Contribution

The work extends the BigEarthNet-MM dataset by integrating additional geographical and environmental modalities for improved Earth observation analysis.

Findings

Demonstrates improved classification accuracy with multi-modal data

Provides a publicly available dataset for Earth observation research

Showcases benefits of multi-modal data fusion in land-cover tasks

Abstract

Deep learning methods have proven to be a powerful tool in the analysis of large amounts of complex Earth observation data. However, while Earth observation data are multi-modal in most cases, only single or few modalities are typically considered. In this work, we present the ben-ge dataset, which supplements the BigEarthNet-MM dataset by compiling freely and globally available geographical and environmental data. Based on this dataset, we showcase the value of combining different data modalities for the downstream tasks of patch-based land-use/land-cover classification and land-use/land-cover segmentation. ben-ge is freely available and expected to serve as a test bed for fully supervised and self-supervised Earth observation applications.