# GeoPlant@PAISS — Data

来源：https://www.kaggle.com/competitions/geoplant-at-paiss/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The training data comprises **species observations** and **environmental data**. Below, we provide at least some explanation of the data.

❗Data availability❗
================
**1. For all Presence Absence (PA) observations, we provide the Bioclim, Landsat, and Sentinel-2 cubes.**
**2. For the Presence Only (PO) observations, we provide only the environmental values as tabular data.**

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

The species related **training data** comprises:
1.  **Presence-Absence (PA) surveys**: including around 100 thousand surveys with roughly 5,000 species of the European flora.  The presence-absence data (PA) is provided to compensate for the problem of false absences in PO data and calibrate models to avoid associated biases.
2.  **Presence-Only (PO) occurrences**: combines around five million observations of around 10,000 species primarily originating from PlantNet App. 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 a standardized sampling protocol), leading to various sampling biases. The local absence of a species from PO data does not necessarily 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 CSV files with species occurrence data available on Seafile for training.
- The PO metadata are available in `GLC25_PO_metadata_train.csv`.
- The PA metadata are available in `GLC25_PA_metadata_train.csv`.

Environmental data
==================
In addition to species data, we provide spatially referenced geographic and environmental data as supplementary input variables. More precisely, for each species observation location, we provide:
1.  **Satellite image patch**: 4-band (R, G, B, NIR) 64x64 tiff files at 10m resolution.
2.  **Landsat time series**: Up to 20 years of values for six satellite bands (R, G, B, NIR, SWIR1, and SWIR2).
3.  **Bioclim time series**:  Up to 20 years of values for 4 bands  (mean, min. and max temp., and total precipitation).
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 four separate folders with the data. A detailed description is provided below.
- The Satellite image patches in `./SatelitePatches/`.
- The Satellite time series in `./SateliteTimeSeries-Landsat/`.
- The Bioclim time series in `./BioclimTimeSeries/`.
- 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".

## **Landsat 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 (such as fires), or land-use changes.
*   _Format_: . TimeSeries-Cubes - Extracted values are 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_: `/SateliteTimeSeries-Landsat/cubes/`

## **Bioclim time series**

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.

*   _Format_: TimeSeries-Cubes - Extracted values are aggregated into 3d tensors with axes as RASTER-TYPE, YEAR, and MONTH.
*   _Resolution_: ~1 kilometer
*   _Source_: [Chelsa](https://chelsa-climate.org/)
*   _Access_: `/BioclimTimeSeries/cubes/`

## **Environmental values** 
For each observation, we provide additional environmental data as scalar values that have already been extracted from the rasters. We provide CSV files, one for each band raster type, including 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 determinants of plant species distributions. Check the `definition.txt` file for information 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/`