# GeoLifeCLEF 2024 @ LifeCLEF & CVPR-FGVC — Data 来源：https://www.kaggle.com/competitions/geolifeclef-2024/data 采集时间：2026-10-24T15:33:27Z The training data comprises **species observations** and **environmental data**. Below, we explain the data in detail. Links ===== ❗**[New Seafile repository](https://lab.plantnet.org/seafile/d/bdb829337aa44a9489f6/)**❗: repository containing all the data. To optimize download times, see the section **data downloading** at the bottom of this page. ❗**[GLC GitHub repository](https://github.com/plantnet/GLC)**❗: Useful codes to manipulate data with simple data loaders, examples, and sample data. More dataloaders can be added after the challenge starts. Observations data ================= The species related **training data** comprises: 1. **Presence-Absence (PA) surveys**: including around 90 thousand surveys with roughly 10,000 species of the European flora. The presence-absence data (PA) is provided to compensate for the problem of false-absences of PO data and calibrate models to avoid associated biases. 2. **Presence-Only (PO) occurrences**: combines around five million observations from numerous datasets gathered from the Global Biodiversity Information Facility (GBIF, www.gbif.org). This data constitutes the larger piece of the training data and covers all countries of our study area, but it has been sampled opportunistically (without standardized sampling protocol), leading to various sampling biases. The local absence of a species among PO data doesn't mean it is truly absent. An observer might not have reported it because it was difficult to "see" it at this time of the year, to identify it as not a monitoring target, or just unattractive. There are two CSVs with species occurrence data on the Seafile available for training. The detailed description is provided again on **SeaFile** in separate ReadME files in relevant folders. - The PO metadata are available in `PresenceOnlyOccurences/GLC24_PO_metadata_train.csv`. - The PA metadata are available in `PresenceAbsenceSurveys/GLC24_PA_metadata_train.csv`. Environmental data ================== Besides species data, we provide spatialized geographic and environmental data as additional input variables (see Figure 1). More precisely, For each species observation location, we provide: 1. **Satellite image patches**: 3-band (RGB) and 1-band (NIR) 128x128 images at 10m resolution. 2. **Satellite time series**: Up to 20 years of values for six satellite bands (R, G, B, NIR, SWIR1, and SWIR2). 3. **Environmental rasters** Various climatic, pedologic, land use, and human footprint variables at the European scale. We provide scalar values, time-series, and original rasters from which you may extract local 2D images. There are three separate folders with the relevant data on the Seafile available for training. The detailed description is provided below and again on **SeaFile** in separate "Readme" files in relevant folders. - The Satellite image patches in `./SatellitePatches/`. - The Satellite time series in `./SatelliteTimeSeries/`. - The Environmental rasters in `./EnvironmentalRasters/`.
**Figure.** Illustration of of the environmental data for an occurrence (glcID=4859165) collected in northern Switzerland (lon=8.5744;lat=47.7704) in 2021. A. The 1280x1280m satellite image patches were sampled in 2021 around the observation. B. Quarterly time series of six satellite bands at the point location since winter 1999-2000. C. Three example bioclimatic images (~65x65km) around the observation were extracted from the provided environmental rasters. ## **Satellite image patches:** 1280mx1280m RGB and NIR patches (four bands) centered at the observation geolocation and taken the same year. The patches are compressed in two zip files (patchs\_rgb.zip, patchs\_nir.zip) accessible in folder /SatelliteImages/. * _Format_: 128x128 JPEG images, a color JPEG file for RGB data and a grayscale one for Near-Infrared. * _Resolution_: 10 meters per pixel * Source: Sentinel2 remote sensing data pre-processed by the [Ecodatacube platform](https://stac.ecodatacube.eu/) * _Access_: First, one must download and decompress the provided zip files. Each JPEG file corresponds to a unique observation location (via "surveyId"). To load the RGB or NIR patch for a selected observation, take the "surveyId" from any occurrence CSV and load it following this rule --> '.../CD/AB/XXXXABCD.jpeg'. For example, the image location for the surveyId 3018575 is "./75/85/3018575.jpeg". For all "surveyId" with less than four digits, you can use a similar rule. For a "surveyId" 1 is "./1/1.jpeg". ## **Satellite time series** Each observation is associated with the time series of the satellite median point values over each season since the winter of 1999 for six satellite bands (R, G, B, NIR, SWIR1, and SWIR2). This data carries a high-resolution local signature of the past 20 years' succession of seasonal vegetation changes, potential extreme natural events (fires), or land use changes. * _Format1_: Six CSV files, one per band. The corresponds to the "surveyId," and the columns are the 84 seasons from winter 2000 until autumn 2020. * _Format2_: . TimeSeries-Cubes - The above-mentioned CSV aggregated into 3d tensors with axes as BAND, QUARTER, and YEAR. * _Resolution_: The original satellite data has a resolution of 30m per pixel * _Source_: Landsat remote sensing data pre-processed by the [Ecodatacube platform](https://stac.ecodatacube.eu/) * _Access_: `/SatelliteTimeSeries/` ## **Monthly climatic rasters** Four climatic variables computed monthly (mean, minimum and maximum temperature, and total precipitation) from January 2000 to December 2019, yielding 960 low-resolution rasters covering Europe. * _Format1_: CSV files, one per raster referenced through the "surveyId". * _Format2_: TimeSeries-Cubes - Above mentioned CSV aggregated into 3d tensors with axis as RASTER-TYPE, YEAR, and MONTH. * _Resolution_: ~1 kilometer * _Source_: [Chelsa](https://chelsa-climate.org/) * _Access_: `/EnvironmentalRasters/Climate/Climatic_Monthly_2000-2019` ## **Environmental rasters** For each observation, we provide additional environmental data such as GeoTIFF rasters and scalar values already extracted from the rasters. We provide CSV files, one per band raster type, i.e., Climate, Elevation, Human Footprint, LandCover, and SoilGrids. 1. **Bioclimatic rasters**: 19 low-resolution rasters covering Europe; commonly used in species distribution modeling. Provided in longitude/latitude coordinates (WGS84). - _Format_: GeoTIFF files with compression and CSV file with extracted values. - _Resolution_: 30 arcsec (~ 1 kilometer) - _Source_: [CHELSA](https://chelsa-climate.org/bioclim/) - _Access_: `/EnvironmentalRasters/Climate/BioClimatic_Average_1981-2010` 2. **Soil rasters**: Nine pedologic low-resolution rasters covering Europe. Provided variables describe the soil properties from 5 to 15cm depth and are determinant of plant species distributions. Check the `definition.txt` file about the provided variables (e.g., pH, clay, organic carbon and nitrogen contents, etc.). - _Format_: GeoTIFF files with compression and CSV file with extracted values. - _Resolution_: ~1 kilometer - _Source_: [Soilgrids](https://soilgrids.org/) - _Access_: `/EnvironmentalRasters/Soilgrids` 3. **Elevation**: High-resolution raster covering Europe. - _Format_: GeoTIFF file with compression, Int16 numeric storage (13.2GB) and CSV file with extracted values. - _Resolution_: 1 arc second (~30 meter) - _Source_: [ASTER Global Digital Elevation Model V3](https://lpdaac.usgs.gov/products/astgtmv003/) - _Access_: `/EnvironmentalRasters/Elevation` 4. **Land Cover**: A medium-resolution multi-band land cover raster covering Europe. Each band describes either the land cover class prediction or its confidence under various classifications. We recommend the use of IGBP (17 classes) or LCCS (43 classes) layers, often used in species distribution modeling. - _Format_: GeoTIFF file with compression and CSV file with extracted values. - _Resolution_: ~500m - _Source_: [MODIS Terra+Aqua 500m](https://ladsweb.modaps.eosdis.nasa.gov/missions-and-measurements/products/MCD12Q1/#overview) - _Access_: `/EnvironmentalRasters/LandCover/` 5. **Humand footprint**: Several low-resolution rasters describing human footprint, encapsulating seven pressures on the environment (e.g., nighlight level, population density) induced by human presence and activity, are provided for two time periods, the early 90's (~1993) and late 2000' (~2009). We provide two summary rasters combining all human pressures and two detailed rasters per pressure, which avoid an arbitrary degradation of the original data. - _Format_: GeoTIFF files with compression and CSV file with extracted values. - _Resolution_: ~1km - _Source_: [Venter et al., 2016](https://datadryad.org/stash/dataset/doi:10.5061/dryad.052q5) - _Access_: The folder `/EnvironmentalRasters/HumanFootprint/` contains a readme file with detailed information about this data and two subfolders: summarized/ contains the two summary rasters (for 1993 and 2009) and detailed/ contains the 2\*7 single pressure raster. Data downloading ================ All PA-related data are already provided through Kagle; however, all the original rasters are provided on the Seafile. To download the full dataset, we recommend downloading each group separately using zipped archives.