ben-ge/DEM: BigEarthNet Extended with Geographical and Environmental Data/Elevation Data

<strong>ben-ge/DEM: BigEarthNet Extended with Geographical and Environmental Data/Elevation Data</strong><br> M. Mommert, N. Kesseli, J. Hanna, L. Scheibenreif, D. Borth, B. Demir, "ben-ge: Extending BigEarthNet with Geographical and Environmental Data", IEEE International Geoscience and Remote Sensing Symposium, Pasadena, USA, 2023. ben-ge is a multimodal dataset for Earth observation (https://github.com/HSG-AIML/ben-ge) that serves as an extension to the BigEarthNet dataset. ben-ge complements the Sentinel-1/2 data contained in BigEarthNet by providing additional data modalities: * elevation data extracted from the Copernicus Digital Elevation Model GLO-30;<br> * land-use/land-cover data extracted from ESA Worldcover;<br> * climate zone information extracted from Beck et al. 2018;<br> * environmental data concurrent with the Sentinel-1/2 observations from the ERA-5 global reanalysis;<br> * a seasonal encoding. This archive contains the digital elevation model (DEM) data of ben-ge, which were extracted from the Copernicus Digital Elevation Model (GLO-30). <strong>Data</strong> Topographic maps are generated based on the global Copernicus Digital Elevation Model (GLO-30) (https://spacedata.copernicus.eu/collections/copernicus-digital-elevation-model). Relevant GLO-30 map tiles from the 2021 data release were downloaded through AWS (https://registry.opendata.aws/copernicus-dem/), reprojected into the coordinate frame of the corresponding Sentinel-1/2 patches and interpolated with bilinear resampling to 10 m resolution on the ground. Elevation data are provided in a separate geotiff file for each patch. The naming convention for these files uses the Sentinel-2 patch_id to which we append _dem.tif. Each file contains a single band with 16-bit integer values that refer to the elevation of that pixel over sea level. Relevant meta data for the ben-ge dataset are compiled in the file ben-ge_meta.csv. This file resides on the root level of this archive and contains the following data for each patch:<br> * patch_id: the Sentinel-2 patch id, which plays a central role for cross-referencing different data modalities for individual patches;<br> * patch_id_s1: the Sentinel-1 patch id for this specific patch;<br> * timestamp_s2: the timestamp for the Sentinel-2 observation;<br> * timestamp_s1: the timestamp for the Sentinel-1 observation;<br> * season_s2: the seasonal encoding (see below) for the time of the Sentinel-2 observation;<br> * season_s1: the seasonal encoding (see below) for the time of the Sentinel-1 observation;<br> * lon: longitude (WGS-84) of the center of the patch [degrees];<br> * lat: latitude (WGS-84) of the center of the patch [degrees];<br> * climatezone: integer value indicating the climate zone based on Beck et al. 2018 (see below for details). <br> <strong>File and directory structure</strong> This archive contains the following directory and file structure: |<br> |--- README (this file)<br> |--- ben-ge_meta.csv (ben-ge meta data)<br> |--- dem/ (digital elevation model data)<br> |--- S2A_MSIL2A_20171208T093351_3_82_dem.tif<br> ... To properly conserve the file and directory structure of the ben-ge dataset, please place this archive file on the root level of the ben-ge dataset and then unpack it. Once unpacked, ben-ge/DEM requires 17.2 GB of space. Other data modalities from ben-ge (as well as Sentinel-1/2 data as provided by BigEarthNet, https://bigearth.net/#downloads), may be added as required. For reference, the recommended structure for the full dataset looks as follows: |<br> |--- ben-ge_meta.csv (ben-ge meta data)<br> |--- ben-ge_era-5.csv (ben-ge environmental data)<br> |--- ben-ge_esaworldcover.csv (patch-wise ben-ge land-use/land-cover data)<br> |--- dem/ (digital elevation model data)<br> | |--- S2A_MSIL2A_20171208T093351_3_82_dem.tif<br> | ...<br> |--- esaworldcover/ (land-use/land-cover data)<br> | |--- S2B_MSIL2A_20170914T93030_26_83_esaworldcover.tif<br> | ...<br> |--- sentinel-1/ (Sentinel-1 SAR data)<br> | |--- S1A_IW_GRDH_1SDV_20180219T063851_29UPV_70_43/<br> | |--- S1A_IW_GRDH_1SDV_20180219T063851_29UPV_70_43_labels_metadata.json (BigEarthNet label file)<br> | |--- S1A_IW_GRDH_1SDV_20180219T063851_29UPV_70_43_VH.tif (BigEarthNet/Sentinel-1 VH polarization data)<br> | |--- S1A_IW_GRDH_1SDV_20180219T063851_29UPV_70_43_VV.tif (BigEarthNet/Sentinel-1 VV polarization data)<br> | ...<br> |--- sentinel-2/ (Sentinel-2 multispectral data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83/<br> | |--- S2B_MSIL2A_20170818T112109_31_83_B01.tif (BigEarthNet/Sentinel-2 Band 1 data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83_B02.tif (BigEarthNet/Sentinel-2 Band 2 data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83_B03.tif (BigEarthNet/Sentinel-2 Band 3 data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83_B04.tif (BigEarthNet/Sentinel-2 Band 4 data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83_B05.tif (BigEarthNet/Sentinel-2 Band 5 data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83_B06.tif (BigEarthNet/Sentinel-2 Band 6 data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83_B07.tif (BigEarthNet/Sentinel-2 Band 7 data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83_B08.tif (BigEarthNet/Sentinel-2 Band 8 data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83_B09.tif (BigEarthNet/Sentinel-2 Band 9 data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83_B11.tif (BigEarthNet/Sentinel-2 Band 11 data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83_B12.tif (BigEarthNet/Sentinel-2 Band 12 data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83_B8A.tif (BigEarthNet/Sentinel-2 Band 8A data)<br> | |--- S2B_MSIL2A_20170818T112109_31_83_labels_metadata.json (BigEarthNet label file)<br> ... <br> <strong>More Information</strong> For more information, please refer to https://github.com/HSG-AIML/ben-ge. <br> <strong>Citing ben-ge</strong><br> If you use data contained in this archive, please cite the following paper: M. Mommert, N. Kesseli, J. Hanna, L. Scheibenreif, D. Borth, B. Demir, "ben-ge: Extending BigEarthNet with Geographical and Environmental Data", IEEE International Geoscience and Remote Sensing Symposium, Pasadena, USA, 2023. <br>