BreizhCrops: A Time Series Dataset for Crop Type Mapping

TL;DR

BreizhCrops is a new satellite time series dataset from Brittany, France, designed for benchmarking crop type classification methods, including deep neural networks and traditional models, with resources available for practitioners.

Contribution

Introduction of a comprehensive, publicly available benchmark dataset for crop classification using satellite time series, facilitating method comparison and development.

Findings

Comparison of seven deep neural networks and a Random Forest baseline.

Dataset and models are accessible for reproducibility and further research.

Plan to expand the dataset and incorporate new methods for improved accuracy.

Abstract

We present Breizhcrops, a novel benchmark dataset for the supervised classification of field crops from satellite time series. We aggregated label data and Sentinel-2 top-of-atmosphere as well as bottom-of-atmosphere time series in the region of Brittany (Breizh in local language), north-east France. We compare seven recently proposed deep neural networks along with a Random Forest baseline. The dataset, model (re-)implementations and pre-trained model weights are available at the associated GitHub repository (https://github.com/dl4sits/BreizhCrops) that has been designed with applicability for practitioners in mind. We plan to maintain the repository with additional data and welcome contributions of novel methods to build a state-of-the-art benchmark on methods for crop type mapping.