global-pasture-watch - GitLite

KO | EN

gitlite — search

#javascript #ai #llm #android #machine-learning #rust #docker #windows #vue #awesome-list #security #mcp #ios #openai

global-pasture-watch

(★ 66)

Mapping the extent, management and condition of the world’s grasslands

파일 탐색기

최종 버전 다운로드 (.zip)

- - output_10_0.png
  - output_12_0.png
  - output_14_1.png
  - output_39_1.png
  - output_39_3.png
  - output_57_0.png
  - output_57_1.png
  - output_59_0.png
  - output_59_1.png
- modeling.ipynb
- README.md
- - data_methods.png
  - gpp_deforestration.gif
  - grasslandGPP_bimonthly_2000.png
  - ugpp_bimonthly_2024.png
  - ugpp_change_2000_2024.png
  - ugpp_timeseries_poi.png
- - 01-global_lue_model.py
- README.md
- - data_methods.png
- - 01-AutoML_areal_regression_modeling.ipynb
  - misc.py
- - 01-build_census_database
  - 01-census-data-preparation.ipynb
  - 02-preparation_pot_land_livestock_layers.py
  - 03-prepare_vrts.ipynb
  - 03-spatiotemporal_zonal.py
  - 04-spatiotemporal_modeling.py
  - 04-spatiotemporal_modeling_preparation.ipynb
  - 05-technical_validation.ipynb
  - 06-global_predictions.py
  - 07-calculation_headcount.py
  - 08-reprojection_to_wgs84.py
  - 09-gee-publication.py
- README.md
- - data_methods.png
- - 01-icesat_sampling.py
  - 02-spacetime_overlay.py
  - 03-spatiotemporal_modeling.py
  - 04-global_predictions.py
  - 05-trend_analysis.py
- README.md
- - general.png
  - ggc-30m-workflow.jpg
.gitignore
.gitmodules
LICENSE
README.html
README.md

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Global Pasture Watch

[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.13890401.svg)](https://doi.org/10.5281/zenodo.13890401)
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.14933636.svg)](https://doi.org/10.5281/zenodo.14933636)
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.15198654.svg)](https://doi.org/10.5281/zenodo.15198654)
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.20396303.svg)](https://doi.org/10.5281/zenodo.20396303)

This repository provides the source code used to produce the follow Global Pasture Watch products (2000–2022+):
* [GGC-30m: Global grassland class and extent maps at 30-m](ggc-30m/README.md) (Publication: https://doi.org/10.1038/s41597-024-04139-6)
* [GLD-1km: Global livestock distributions maps at 1-km](gld-1km/README.md) (Publication: https://doi.org/10.7717/peerj.21494)
* [GSVH-30m: Global short vegetation height maps at 30-m](gsvh-30m/README.md) (Publication: https://doi.org/10.1038/s41597-025-05739-6)
* [GGPP-30m: Global gross primary productivity maps at 30-m](ggpp-30m/README.md) (publication: https://doi.org/10.7717/peerj.19774)

![Global Pasture Watch](https://raw.githubusercontent.com/wri/global-pasture-watch/main/resources/image/general.png)

## Zenodo:

The output maps, reference samples, ML models and additional datasets are publicly available in Zenodo:

* **Global grassland class and extent maps at 30m**
	* [Annual grassland class and extent maps at 30-m spatial resolution (2000—2022)](https://doi.org/10.5281/zenodo.13890400)
  * [Grassland reference samples based on visual interpretation of VHR imagery (2000–2022)](https://zenodo.org/records/11281157)
  * [Global machine learning model for prediction of cultivated and natural/semi-natural grassland](https://zenodo.org/records/11280849)
  * [Grassland sampling design derived by Feature Space Coverage Sampling (FSCV) at 1-km spatial resolution](https://zenodo.org/records/11275539)
  * [Integrated Approach to Global Land Use and Land Cover Reference Data Harmonization](https://zenodo.org/records/11285561)
* **Global livestock distributions maps at 1-km**
	* [Annual livestock headcount maps for cattle, goats, sheep and horses at 1-km 2000–2022 (FAOSTAT-adjusted)](https://doi.org/10.5281/zenodo.20396303)
	* [Annual cattle density maps at 1-km for 2000–2022 including 95% prediction interval](https://doi.org/10.5281/zenodo.17486471)
	* [Annual goat density maps at 1-km for 2000–2022 including 95% prediction interval](https://doi.org/10.5281/zenodo.17490112)
	* [Annual sheep density maps at 1-km for 2000–2022 including 95% prediction interval](https://doi.org/10.5281/zenodo.17490692)
	* [Annual horse density maps at 1-km for 2000–2022 including 95% prediction interval](https://doi.org/10.5281/zenodo.17490457)
	* [Annual buffalo density maps at 1-km for 2000–2022 including 95% prediction interval](https://doi.org/10.5281/zenodo.17485929)
	* [Livestock reference samples based on multi-source sub-national census data (2000—2022)](https://doi.org/10.5281/zenodo.17665040)
	* [Global machine learning models for livestock density predictions](https://doi.org/10.5281/zenodo.17665388)
	* [Annual maps of potential land for livestock production at 1-km for 2000–2022](https://doi.org/10.5281/zenodo.14933679)
* **Global short vegetation maps at 30-m**
	* [Annual short vegetation height maps at 30-m spatial resolution for 2000–2022 including prediction interval and trend analysis](https://doi.org/10.5281/zenodo.15198654)
* **Global global gross primary productivity maps maps at 30-m**
  * [Global Uncalibrated EO-based GPP and Grassland GPP Maps at 30m](https://doi.org/10.5281/zenodo.15675358)
  * [Global EC Flux Tower Bimonthly GPP Time Series from FluxNet2015, ICOS, AmeriFlux, OzFlux, and ChinaFlux for Product Validation](https://doi.org/10.5281/zenodo.15349578)

## STAC, Google Earth Engine & WebGIS apps

The output maps are also publicly available in Google Earth Engine and STAC:

* [Land & Carbon Lab Global Pasture Watch](https://developers.google.com/earth-engine/datasets/publisher/global-pasture-watch)
* [WRI Data Explorer](https://datasets.wri.org/datasets/grassland-dynamics?map=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%3D&ap3c=IGgHf5TfpNRjpT8CAGgHf5TOKzY6xEFLk_Jkbix1QAyjKdOjsg)
* [OpenLandMap STAC](https://stac.openlandmap.org)
* GEE Apps ([GPW gallery](https://global-pasture-watch.projects.earthengine.app/)):
  * [Height Comparison Toolkit (GPW-HCT)](https://gpw-lapig.projects.earthengine.app/view/hct)
  * [Global Grassland Map Customization](https://global-pasture-watch.projects.earthengine.app/view/ggc-30m)
  * [Global Grassland Comparison tool](https://ee-vieiramesquita.projects.earthengine.app/view/ggc-30m-comparison)
  * [Global Grassland Gross Primary Productivity](https://global-pasture-watch.projects.earthengine.app/view/ggpp-30m)
* [OpenLandMap](https://openlandmap.org)
* [EcoDataCube](https://ecodatacube.eu)
* [LandMetric](https://app.landmetric.org)

## Related softwares / libraries

The softwares and libraries produced / maintained in the context of the initiative are publicly available:

* [QGIS Fast Grid Inspection](https://plugins.qgis.org/plugins/qgis-fgi-plugin/#plugin-about)
* [Scikit-Map](https://github.com/openlandmap/scikit-map)
* [Geo-Wiki](https://www.geo-wiki.org/)
* [LUCKINet](https://github.com/luckinet)

## Webinars:

The webinars publicly available:

* [Global Pasture Watch: Mapping & Monitoring Global Grasslands and Livestock](https://www.wri.org/events/2023/4/global-pasture-watch-mapping-monitoring-global-grasslands-livestock)
* [Grassland Mapping & Monitoring: A Focus on Latin America](https://www.wri.org/events/2024/5/grassland-mapping-monitoring-focus-latin-america)
* [Global 30-m resolution ensemble digital terrain model and vegetation height datasets 2000–2022 based on ICESat-2, GEDI and spatiotemporal ML](https://youtu.be/dHAudnlLGbI)
* [Machine Learning methods for census data: lessons learned from mapping global livestock dynamics at 1 km resolution 2000–2022](https://youtu.be/zMCvicl51C4)

## Acknowledgements & Funding

This work is conducted by [WRI](https://wri.org), [OpenGeoHub Foundation](https://opengeohub.org/), [LAPIG/UFG](http://lapig.iesa.ufg.br), [IIASA](https://iiasa.ac.at/) and [iDiv](https://www.idiv.de/en/index.html) and has received funding from [Land and Carbon Lab](https://www.landcarbonlab.org/), via the [Global Pasture Watch](https://www.wri.org/events/2023/4/global-pasture-watch-mapping-monitoring-global-grasslands-livestock), and European Union’s Horizon Europe research and innovation program, via the [Open-Earth-Monitor Cyberinfrastructure project](https://earthmonitor.org), under grant agreement [No. 101059548](https://cordis.europa.eu/project/id/101059548)