Data

Tools

Indexes

Applications

Experiments

Open Sustainable Technology

A curated list of open technology projects to sustain a stable climate, energy supply, biodiversity and natural resources.

EuroCropsML

A pre-processed and ready-to-use machine learning dataset for crop type classification of agricultural parcels in Europe.
https://github.com/dida-do/eurocropsml

Category: Consumption
Sub Category: Agriculture and Nutrition

Keywords

agriculture crop-classification dataset deep-learning earth-observation machine-learning sentinel-2 torch

Last synced: about 16 hours ago
JSON representation

Repository metadata

EuroCropsML is a ready-to-use benchmark dataset for few-shot crop type classification using Sentinel-2 imagery.

README.md

EuroCropsML

Ready-to-use benchmark dataset for few-shot crop type classification using Sentinel-2 imagery.

Part of the PreTrainAppEO ("Pre-Training Applicability in Earth Observation") research project.

Read the Docs
PyPI Version

Python Version
GitHub License
Zenodo DOI

EuroCropsML is a pre-processed and ready-to-use machine learning dataset for crop type classification of agricultural parcels in Europe.
It consists of a total of 706,683 Sentinel-2 multi-class labeled data points with a total of 176 distinct classes.
Each data point contains an annual time series of per parcel median pixel values of Sentinel-2 L1C (top-of-atmosphere) reflectance data for the year 2021.
The dataset is based on Version 9 of EuroCrops, an open-source collection of remote sensing reference data.

For EuroCropsML, we acquired and aggregated data for the following countries:

Country Number of distinct classes Total number of datapoints for Sentinel-2
Estonia 127 175,906
Latvia 103 431,143
Portugal 79 99,634

Spatial distribution of labels within Estland and Latvia.
Spatial distribution of labels within Portugal.

The distribution of class labels differs substantially between the regions of Estonia, Latvia, and Portugal.
This makes transferring knowledge gained in one region to another region quite challenging, especially if only few labeled data points are available.
Therefore, this dataset is particularly suited to explore transfer-learning methods for few-shot crop type classification.

The data acquisition, aggregation, and pre-processing steps are schematically illustrated below. A more detailed description is given in the dataset section of our documentation.

Data Acquisition Pipeline.

Getting Started

eurocropsml is a Python package hosted on PyPI.

Installation

The recommended installation method is pip-installing into a virtual environment:

$ python -Im pip install eurocropsml

Usage Guide

The quickest way to interact with the eurocropsml package and get started is to use the EuroCropsML dataset is via the provided command-line interface (CLI).

For example, to get help on available commands and options, use

$ eurocropsml-cli --help

To show the currently used (default) configuration for the eurocropsml dataset CLI, use

$ eurocropsml-cli datasets eurocrops config

To download the EuroCropsML dataset as currently configured, use

$ eurocropsml-cli datasets eurocrops download

Alternatively, the dataset can also be manually downloaded from our Zenodo repository.

A comprehensive documentation of the CLI can be found in the CLI Reference section of our documentation.

For a complete example use-case demonstrating the ready-to-use EuroCropsML dataset in action, please refer to the project's associated official repository for benchmarking meta-learning algorithms.

Project Information

The eurocropsml code repository is released under the MIT License.
Its documentation lives at Read the Docs, the code on GitHub and the latest release can by found on PyPI.
It is tested on Python 3.10+.

If you would like to contribute to eurocropsml you are most welcome. We have written a short guide to help you get started.

Background

The EuroCropsML dataset and associated eurocropsml code repository are provided and developed as part of the joint PretrainAppEO research project by the chair of Remote Sensing Technology at Technical University Munich and dida.

The goal of the project is to investigate methods that rely on the approach of pre-training and fine-tuning machine learning models in order to improve generalizability for various standard applications in Earth observation and remote sensing.

The ready-to-use EuroCopsML dataset is developed for the purpose of improving and benchmarking few-shot crop type classification methods.

EuroCropsML is based on Version 9 of EuroCrops, an open-source collection of remote sensing reference data for agriculture from countries of the European Union.

Citation

If you use the EuroCropsML dataset or eurocropsml code repository in your research, please cite our project as follows:

Plain text

Reuss, J., & Macdonald, J. (2024). EuroCropsML [dataset]. Zenodo. https://doi.org/10.5281/zenodo.10629610

Bibtex

@misc{reuss_macdonald_eurocropsml_2024,
  author       = {Reuss, Joana and Macdonald, Jan},
  title        = {EuroCropsML},
  year         = 2024,
  publisher    = {Zenodo},
  doi          = {10.5281/zenodo.10629610},
  url          = {https://doi.org/10.5281/zenodo.10629610}
}

Acknowledgments & Funding

The PreTrainAppEO research project is funded by the German Space Agency at DLR on behalf of the Federal Ministry for Economic Affairs and Climate Action (BMWK).

Owner metadata

GitHub Events

Total
Last Year

Committers metadata

Last synced: 6 days ago

Total Commits: 61
Total Committers: 3
Avg Commits per committer: 20.333
Development Distribution Score (DDS): 0.459

Commits in past year: 61
Committers in past year: 3
Avg Commits per committer in past year: 20.333
Development Distribution Score (DDS) in past year: 0.459

Name Email Commits
jmaces j****s@h****e 33
jsreuss 7****s 27
katya 6****o 1

Committer domains:

Issue and Pull Request metadata

Last synced: 1 day ago

Total issues: 114
Total pull requests: 82
Average time to close issues: 22 days
Average time to close pull requests: 14 days
Total issue authors: 3
Total pull request authors: 3
Average comments per issue: 0.1
Average comments per pull request: 0.26
Merged pull request: 72
Bot issues: 0
Bot pull requests: 0

Past year issues: 114
Past year pull requests: 82
Past year average time to close issues: 22 days
Past year average time to close pull requests: 14 days
Past year issue authors: 3
Past year pull request authors: 3
Past year average comments per issue: 0.1
Past year average comments per pull request: 0.26
Past year merged pull request: 72
Past year bot issues: 0
Past year bot pull requests: 0

More stats: https://issues.ecosyste.ms/repositories/lookup?url=https://github.com/dida-do/eurocropsml

Top Issue Authors

  • jsreuss (99)
  • jmaces (12)
  • katyagikalo (3)

Top Pull Request Authors

  • jsreuss (66)
  • jmaces (13)
  • katyagikalo (3)

Top Issue Labels

  • enhancement (51)
  • bug (35)
  • documentation (15)
  • wontfix (3)

Top Pull Request Labels

  • bug (6)
  • documentation (6)
  • enhancement (3)

Package metadata

pypi.org: eurocropsml

EuroCropsML is a ready-to-use benchmark dataset for few-shot crop type classification using Sentinel-2 imagery.

  • Homepage:
  • Documentation: https://eurocropsml.readthedocs.io/en/latest/
  • Licenses: MIT License
  • Latest release: 0.4.1 (published 3 days ago)
  • Last Synced: 2025-04-25T14:32:29.283Z (1 day ago)
  • Versions: 6
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 382 Last month
  • Rankings:
    • Dependent packages count: 9.484%
    • Forks count: 32.982%
    • Average: 36.931%
    • Stargazers count: 42.688%
    • Dependent repos count: 62.57%
  • Maintainers (1)

Score: 9.991086257015196