BigEarthNet

A Large-Scale Sentinel Benchmark Archive

About BigEarthNet

The BigEarthNet archive was constructed by the Remote Sensing Image Analysis (RSiM) Group and the Database Systems and Information Management (DIMA) Group at the Technische Universität Berlin (TU Berlin). This work is supported by the European Research Council under the ERC Starting Grant BigEarth and by the Berlin Institute for the Foundations of Learning and Data (BIFOLD). Before BIFOLD, the Berlin Big Data Center (BBDC) supported the work.

BigEarthNet is a benchmark archive, consisting of 590,326 pairs of Sentinel-1 and Sentinel-2 image patches. The first version (v1.0-beta) of BigEarthNet includes only Sentinel 2 images. Recently, it has been enriched by Sentinel-1 images to create a multi-modal BigEarthNet benchmark archive (called also as BigEarthNet-MM).

BigEarthNet with Sentinel-2 Image Patches

To construct BigEarthNet with Sentinel-2 image patches (called as BigEarthNet-S2 now, previously BigEarthNet), 125 Sentinel-2 tiles acquired between June 2017 and May 2018 over the 10 countries (Austria, Belgium, Finland, Ireland, Kosovo, Lithuania, Luxembourg, Portugal, Serbia, Switzerland) of Europe were initially selected. All the tiles were atmospherically corrected by the Sentinel-2 Level 2A product generation and formatting tool (sen2cor). Then, they were divided into 590,326 non-overlapping image patches. Each image patch was annotated by the multiple land-cover classes (i.e., multi-labels) that were provided from the CORINE Land Cover database of the year 2018 (CLC 2018).

BigEarthNet with Sentinel-1 Image Patches

To construct BigEarthNet with Sentinel-1 image patches (called as BigEarthNet-S1), 321 Sentinel-1 scenes acquired between June 2017 and May 2018 that jointly cover the area of all original 125 Sentinel-2 tiles with close temporal proximity were selected and processed. BigEarthNet-S1 consists of 590,326 preprocessed Sentinel-1 image patches - one for each Sentinel-2 patch. A more detailed explanation on the processing is given in its dataset description document.

For the details about BigEarthNet, please see our papers:

G. Sumbul, M. Charfuelan, B. Demir, V. Markl, "BigEarthNet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding", IEEE International Geoscience and Remote Sensing Symposium, pp. 5901-5904, Yokohama, Japan, 2019.

G. Sumbul, A. d. Wall, T. Kreuziger, F. Marcelino, H. Costa, P. Benevides, M. Caetano, B. Demir, V. Markl, "BigEarthNet-MM: A Large Scale Multi-Modal Multi-Label Benchmark Archive for Remote Sensing Image Classification and Retrieval", IEEE Geoscience and Remote Sensing Magazine, 2021, doi: 10.1109/MGRS.2021.3089174.

Downloads

If you use the BigEarthNet archive, please cite our papers given below:

G. Sumbul, M. Charfuelan, B. Demir, V. Markl, "BigEarthNet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding", IEEE International Geoscience and Remote Sensing Symposium, pp. 5901-5904, Yokohama, Japan, 2019.

G. Sumbul, A. d. Wall, T. Kreuziger, F. Marcelino, H. Costa, P. Benevides, M. Caetano, B. Demir, V. Markl, "BigEarthNet-MM: A Large Scale Multi-Modal Multi-Label Benchmark Archive for Remote Sensing Image Classification and Retrieval", IEEE Geoscience and Remote Sensing Magazine, 2021, doi: 10.1109/MGRS.2021.3089174.

BigEarthNet-S1

(~55GB)v1.0-beta

BigEarthNet-MM

Download BigEarthNet-S2

Download BigEarthNet-S1

Deep Learning Models

19 Labels

News

For the details of the positions, please follow this link.
BigEarthNet has been enriched by including Sentinel-1 images. The new version contains 590,326 pairs of Sentinel-1 and Sentinel-2 image patches to support research studies on multi-modal/cross-modal image classification, retrieval and search.
There are several researchers and colleagues all around the world, contributing to advance BigEarthNet through their BigEarthNet related software tools and datasets. We appreciate their excellent work and effort!
For details, please see BigEarthNet Externals.
We are looking for a highly motivated Postdoctoral Researcher with a strong record of accomplishment in machine learning and computer vision. Successful candidate will conduct research and develop advanced deep learning based algorithms for satellite image search/retrieval from large-scale data archives and semantic scene understanding. This will entail the development of novel deep learning models that can address the problems on incomplete, noisy and imbalanced training sets for scalable image search, retrieval and classification.
For details, please contact Prof. Demir (demir@tu-berlin.de).
We made public an alternative class-nomenclature to allow DL models for better learning&describing the complex spatial/spectral information content of Sentinel-2 images in BigEarthNet. The new class nomenclature is the product of a collaboration between the Direção-Geral do Território in Lisbon, Portugal and the Remote Sensing Image Analysis (RSiM) group at TU Berlin, Germany. For details, please visit this link.
We are looking for highly motivated PhD candidates to join the Remote Sensing Image Analysis (RSiM) group at the Faculty of Electrical Engineering and Computer Science, Technische Universität Berlin, Germany. The research of the PhD candidates will aim at the participation in the research activities of the Remote Sensing Image Analysis (RSiM) group in the field of machine learning and big data management for earth observation and the development of image search and retrieval methods and systems for querying large-scale satelilite image archives in the compressed domain. Developed methods will aim at enabling accurate and scalable image indexing and retrieval by efficiently characterizing the high-spectral and spatial information. Very good command of German and English is required. For details, please visit this link.
We prepared a script that returns the original Level-1C tile information of each Sentinel-2 image patch given in the BigEarthNet. To download the script, see: https://git.tu-berlin.de/rsim/bigearthnet-tools. Note that all the considered Level-1C tiles were atmospherically corrected by the Sentinel-2 Level 2A product generation and formatting tool (sen2cor) before creating the patches. Thus, the script is useful to have access to the original Level-1C tile of each patch.
In the BigEarthNet, we have kept the image patches with seasonal snow cover. This is to allow tag based search and retrieval studies independently from seasons. However, soon we will provide the list of patches with seasonal snow that can be important for the scene classification and content based image search/retrieval studies.
BigEarthNet has been released at the Big Data from Space (BIDS'19) Conference in Munich, Germany.

FAQ

Yes, some Sentinel-2 patches include seasonal-snow. We kept them in the archive to allow tag-based search and retrieval studies independently from seasons. However, if you work on scene classification, content-based image retrieval and search only by using Sentinel-2 image patches, we suggest not to include patches fully covered by seasonal-snow for training and test stages of the machine/deep learning algorithms. The list of these patches is provided in the ‘Download’ page.
Sentinel-2 tiles in the BigEarthNet are associated to cloud cover less than 1%, whereas in some cases the cloud cover are populated within some patches. We kept these patches in the BigEarthNet to allow multi-modal learning studies (soon Sentinel-1 images will be also included in BigEarthNet). However, if you work on scene classification, content-based image retrieval and search only by using Sentinel-2 image patches, we suggest not to include these patches for training and test stages of the machine/deep learning algorithms. The list of patches fully covered by cloud and cloud shadow is provided in the ‘Download’ page.
The BigEarthNet Archive is licensed under the Community Data License Agreement – Permissive, Version 1.0.