CoChat

A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning

Open access
Sykas, Dimitrios, Sdraka, Maria, Zografakis, Dimitrios, Papoutsis, Ioannis · 2022 · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

The DOI matches its Crossref record; 56 of the 58 references it cites were found in a registry or an index, and 2 are not checked yet.

Abstract

In this work, we introduce Sen4AgriNet, a Sentinel-2-based time series multicountry benchmark dataset, tailored for agricultural monitoring applications with machine and deep learning. Sen4AgriNet dataset is annotated from farmer declarations collected via the land parcel identification system (LPIS) for harmonizing country-wide labels. These declarations have only recently been made available as open data, allowing for the first time the labeling of satellite imagery from ground truth data. We proceed to propose and standardize a new crop type taxonomy across Europe that addresses common agriculture policy (CAP) needs, based on the Food and Agriculture Organization (FAO) indicative crop classification scheme. Sen4AgriNet is the only multicountry, multiyear dataset that includes all spectral information. It is constructed to cover the period 2016–2020 for Catalonia and France, while it can be extended to include additional countries. Currently, it contains 42.5 million parcels, which makes it significantly larger than other available archives. We extract two subdatasets to highlight its value for diverse deep learning applications—the object aggregated dataset (OAD) and the patches assembled dataset (PAD). OAD capitalizes zonal statistics of each parcel, thus creating a powerful label-to-features instance for classification algorithms. On the other hand, PAD structure generalizes the classification problem to parcel extraction and semantic segmentation and labeling. The PAD and OAD are examined under three different scenarios to showcase and model the effects of spatial and temporal variability across different years and different countries.1

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/jstars.2022.3164771

Cites

56 of 58 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Taxonomy of Sen4AgriNet potential applications.
Fig. 1 Taxonomy of Sen4AgriNet potential applications.CC-BY · From the PDF
Fig. 2 Proposed Sen4AgriNet crop categorization taxonomy structure, inspired by FAO and based on the customization of the ICC [55] model.
Fig. 2 Proposed Sen4AgriNet crop categorization taxonomy structure, inspired by FAO and based on the customization of the ICC [55] model.CC-BY · From the PDF
Fig. 3 Representative patches from the proposed dataset. (a) Catalonia 2019 (31TCG), (b) Catalonia 2020 (31TCG), (c) France 2019 (31TDK), (d) France 2019 (31TDK). Note that (a) and (b) refer to the same patch on different years, whereas (c) and (d) refer to different patches from the same year and region.
Fig. 3 Representative patches from the proposed dataset. (a) Catalonia 2019 (31TCG), (b) Catalonia 2020 (31TCG), (c) France 2019 (31TDK), (d) France 2019 (31TDK). Note that (a) and (b) refer to the same patch on different years, whereas (c) and (d) refer to different patches from the same year and region.CC-BY · From the PDF
Fig. 4 France and Catalonia (Spain) LPIS dataset overlaid with Sentinel-2 tiles.
Fig. 4 France and Catalonia (Spain) LPIS dataset overlaid with Sentinel-2 tiles.CC-BY · From the PDF
Fig. 5 Mean NDVI of different crops across space and time.
Fig. 5 Mean NDVI of different crops across space and time.CC-BY · From the PDF
Fig. 6 Scenario 1. Visual evaluation of the U-Net, ConvLSTM, and ConvSTAR PAD predictions for two different image patches.
Fig. 6 Scenario 1. Visual evaluation of the U-Net, ConvLSTM, and ConvSTAR PAD predictions for two different image patches.CC-BY · From the PDF
Image 7
CC-BY · From the PDF
Fig. 7 Scenario 2. Visual evaluation of the U-Net, ConvLSTM, and ConvSTAR predictions for two different image patches.
Fig. 7 Scenario 2. Visual evaluation of the U-Net, ConvLSTM, and ConvSTAR predictions for two different image patches.CC-BY · From the PDF
Fig. 9 UMAP visualizations for the examined datasets. (a) Distribution of the selected crops in all regions and years, (b) distribution of data across the three different datasets, (c) and (d) distribution of the train and test data in the three scenarios. Better viewed in colour.
Fig. 9 UMAP visualizations for the examined datasets. (a) Distribution of the selected crops in all regions and years, (b) distribution of data across the three different datasets, (c) and (d) distribution of the train and test data in the three scenarios. Better viewed in colour.CC-BY · From the PDF
Fig. 10 Pixel distribution of the selected crop classes across the different scenarios. Vertical axis is in logarithmic scale.
Fig. 10 Pixel distribution of the selected crop classes across the different scenarios. Vertical axis is in logarithmic scale.CC-BY · From the PDF
Fig. 11 PAD results. The first row shows the U-Net results, the second one the ConvLSTM results whereas the third the ConvSTAR results. Each column corresponds to a different scenario.
Fig. 11 PAD results. The first row shows the U-Net results, the second one the ConvLSTM results whereas the third the ConvSTAR results. Each column corresponds to a different scenario.CC-BY · From the PDF
Fig. 12 OAD results. The first row shows the LSTM results whereas the second row the transformer-encoder classifier results. The third row illustrates results obtained for the TempCNN architecture. Each column corresponds to a different scenario.
Fig. 12 OAD results. The first row shows the LSTM results whereas the second row the transformer-encoder classifier results. The third row illustrates results obtained for the TempCNN architecture. Each column corresponds to a different scenario.CC-BY · From the PDF
Image 13
CC-BY · From the PDF
Image 14
CC-BY · From the PDF
Image 15
CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 58 references

Research works printed but not linked: 5

  1. Ji, 2018, 3D convolutional neural networks for crop classification with multi-temporal remote sensing images, 10
  2. 10.3390/iigi7040129 · doi:10.3390/iigi7040129
  3. Tong, 2020, Land-cover classification with high-resolution remote sensing images using transferable deep models, 237, 111322
  4. 2005, A System of Integrated Agricultural Censuses and Surveys. Volume 1, World Programme for the Census of Agriculture 2010
  5. Sykas, 2021, Sen4agrinet: A harmonized multi-country, multi-temporal benchmark dataset for agricultural earth observation machine learning applications, 10.1109/igarss47720.2021.9553603 · DOI

Cited by

See all 74

Metadata

Authors
Sykas, D., Sdraka, M., Zografakis, D., & Papoutsis, I.
Affiliations
  • Institute of Astronomy, Astrophysics, Space Applications & Remote Sensing, National Observatory of Athens, Athens, Greece
  • National Observatory of Athens (GR)
Venue
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Published
2022
Volume
15
Pages
3323-3339
ISSN
  • 1939-1404 (ISSN-L)
  • 2151-1535
OpenAlex
W4225728415
Cited by
59
References
56
Citations by year
2026: 17 · 2025: 8 · 2024: 15 · 2023: 13 · 2022: 6
FWCI
5.60
Type
journal article
Language
en
Open access
Locations
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • arXiv (Cornell University)
Funders
H2020 LEIT Space (101004188)
Topics
  • Physical Sciences › Environmental Science › Ecology › Remote Sensing in Agriculture
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
  • Life Sciences › Agricultural and Biological Sciences › Plant Science › Smart Agriculture and AI
Keywords
Sentinel-2, crop classification, crop segmentation, agricultural monitoring, Land Parcel Identification System, Common Agricultural Policy, satellite time series, semantic segmentation, zonal statistics, Catalonia, France

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning. https://app.cochat.ai/papers/10.1109/jstars.2022.3164771
The paper
Sykas, D., Sdraka, M., Zografakis, D., & Papoutsis, I. (2022). A Sentinel-2 Multiyear, Multicountry Benchmark Dataset for Crop Classification and Segmentation With Deep Learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. https://doi.org/10.1109/jstars.2022.3164771

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.