A Satellite Time Series Dataset for Crop Type Mapping

Evaluation Results
Explore the evaluation results qualitatively
and quantitatively
average accuracy overall accuracy
lstm 0.57 0.80
transformer 0.58 0.80
tempcnn 0.55 0.79
starrnn 0.58 0.79
msresnet 0.51 0.78
omniscalecnn 0.53 0.77
last update 8.5.2020
Python Package
The dataset, model source codes and pretrained weights can be obtained via a python package. Install with
pip install breizhcrops
and run the minimal working example

import breizhcrops as bzh
dataset = bzh.BreizhCrops("frh04")
x, y, field_id = dataset[0]
model = models.pretrained("Transformer")
y_pred = model(x.unsqueeze(0))
to get started.
Github Repository

Please feel free to contribute models, open issues, Fork and our GitHub repository


Please consider citing our paper BreizhCrops: A Time Series Dataset for Crop Type Mapping

  title={BreizhCrops: A Time Series Dataset for Crop Type Mapping},
  author={Ru{\ss}wurm, Marc and Pelletier, Charlotte and Zollner, Maximilian and Lef{\`e}vre, S{\'e}bastien and K{\"o}rner, Marco},
  journal={International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ISPRS (2020)},