# GeoLifeCLEF25 @ CVPR & LifeCLEF — Data

来源：https://www.kaggle.com/competitions/geolifeclef-2025/data

采集时间：2026-10-19T06:28:31Z

The training data comprises **species observations** and **environmental data**. Below, we explain the data in detail.

❗Data availability❗
================
**1. All Presence Absence (PA) data are provided through Kaggle.**
**2. All Presence Only (PO) data are available on [Seafile repository](https://lab.plantnet.org/seafile/d/979791609d0e4016a68a/). The PO related "tabular data" are available on Kagle.**
**3. All the original rasters are provided on the Seafile. Or on [GeoPlant Kaggle dataset](https://www.kaggle.com/datasets/picekl/geoplant?select=EnviromentalRasters).**


Observations data
=================

The species related **training data** comprises:
1.  **Presence-Absence (PA) surveys**: including around 100 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/GLC25_PO_metadata_train.csv`.
- The PA metadata are available in `PresenceAbsenceSurveys/GLC25_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) 64x64 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/`.

## **Satellite image patches:** 
640mx640m R,G,B, NIR patches (four bands) centered at the observation geolocation and taken the same year. The patches are **provided in the four band TIFF file** accessible in the folder /SatelliteImages/.
*   _Format_: 64x64 TIFF files.
*   _Resolution_: 10 meters per pixel
*   Source: Sentinel2 remote sensing data pre-processed by the [Ecodatacube platform](https://stac.ecodatacube.eu/)
*   _Access_: Each TIFF file corresponds to a unique observation location (via "surveyId"). To load the patches 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.tiff". For all "surveyId" with less than four digits, you can use a similar rule. For a "surveyId" 1 is "./1/1.tiff".

## **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. **Human footprint**: 22 high-resolution OpenStreetMap rasters describing variables that reflect human footprint-
    - _Format_: GeoTIFF files with compression and CSV file with extracted values.
    -  _Resolution_: 10-30m
    - _Source_: [Ecodatacube platform](https://stac.ecodatacube.eu/)
    - _Access_: The folder `/EnvironmentalRasters/HumanFootprint/`