The GFSAD30 is a NASA funded project to provide high resolution global cropland data and their water use that contributes towards global food security in the twenty-first century. The GFSAD30 products are derived through multi-sensor remote sensing data (e.g., Landsat, MODIS, AVHRR), secondary data, and field-plot data and aims at documenting cropland dynamics from 2000 to 2025.
Monitoring global croplands is imperative for ensuring sustainable water and food security to the people of the world in the Twenty-first Century. The currently available cropland products suffer from major limitations such as:
- Absence of precise spatial location of the cropped areas;
- Coarse resolution nature of the map products with significant uncertainties in areas, locations, and detail;
- Uncertainties in differentiating irrigated areas from rainfed areas;
- Absence of crop types and cropping intensities; and
- Absence of a dedicated web\data portal for the dissemination of cropland products.
Thereby, the overarching goal of GFSAD30 project is to produce consistent and unbiased estimates of global agricultural cropland products such as:
1) Cropland extent\area;
2) Crop types with focus on 8 crops that occupy 70% of the global cropland areas;
3) Irrigated versus rainfed;
4) Cropping intensities: single, double, triple, and continuous cropping;
5) Cropland change over space and time: 2000-2025.
Once the above products are established, other products such as the following can be derived using the above products and certain other inputs:
6) Crop productivity (productivity per unit of land; kg\m2)
7) Water productivity (crop per drop or productivity per unit of water; kg\m3).
The GFSAD30 Cropland Extent Products are available to download for 7 regions of the world from LPDAAC at https://lpdaac.usgs.gov/news/release-of-gfsad-30-meter-cropland-extent-… view the GDSAD product in an interactive zoomable webpage, visit https://www.usgs.gov/apps/croplands/
A global synthesis work summarizing the methods and results of the entire GFSAD30 global cropland extent product was released as the USGS Professional Paper 1868 https://pubs.er.usgs.gov/publication/pp1868
Since the release of the GFSAD30 cropland extent product, the downloads from LPDAAC and citations have been tracked and published in the Open File Report 2022-1001 at https://pubs.er.usgs.gov/publication/ofr20221001











Relevant methodology including Models and Algorithms used by the group.
Automated Cropland Mapping Algorithm (ACMA) for Africa using Moderate Resolution Imaging Spectroradiometer (MODIS) NDVI Time-series
Automated Cropland Classification Algorithm (ACCA) for Australia using MODIS 250-m Time-series
GFSAD30 - Archives
Below are multimedia items associated with this project.
Below are publications associated with this project.
Mapping croplands of Europe, Middle East, Russia, and Central Asia using Landsat 30-m data, machine learning algorithms and Google Earth Engine
Global cropland-extent product at 30-m resolution (GCEP30) derived from Landsat satellite time-series data for the year 2015 using multiple machine-learning algorithms on Google Earth Engine cloud
Mapping croplands of Europe, Middle East, Russia, and Central Asia using Landsat 30-m data, machine learning algorithms and Google Earth Engine
Agricultural cropland extent and areas of South Asia derived using Landsat satellite 30-m time-series big-data using random forest machine learning algorithms on the Google Earth Engine cloud
Mapping cropland extent of Southeast and Northeast Asia using multi-year time-series Landsat 30-m data using Random Forest classifier on Google Earth Engine
A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform
Nominal 30-m cropland extent map of continental Africa by integrating pixel-based and object-based algorithms using Sentinel-2 and Landsat-8 Data on Google Earth Engine
MODIS phenology-derived, multi-year distribution of conterminous U.S. crop types
Spectral matching techniques (SMTs) and automated cropland classification algorithms (ACCAs) for mapping croplands of Australia using MODIS 250-m time-series (2000–2015) data
Automated cropland mapping of continental Africa using Google Earth Engine cloud computing
Mapping rice-fallow cropland areas for short-season grain legumes intensification in South Asia using MODIS 250 m time-series data
Global Cropland Area Database (GCAD) derived from Remote Sensing in Support of Food Security in the Twenty-first Century: Current Achievements and Future Possibilities
Global land cover mapping: a review and uncertainty analysis
Below are data or web applications associated with this project.
Below are news stories associated with this project.
The GFSAD30 project accomplished their goal!
The global croplands mapping project has succesfully mapped croplands across the entire planet in order to understand the security of food world wide. Below are many press anouncments and interviews with the project leader Prasad Thenkabail.
Below are partners associated with this project.
- Overview
The GFSAD30 is a NASA funded project to provide high resolution global cropland data and their water use that contributes towards global food security in the twenty-first century. The GFSAD30 products are derived through multi-sensor remote sensing data (e.g., Landsat, MODIS, AVHRR), secondary data, and field-plot data and aims at documenting cropland dynamics from 2000 to 2025.
Monitoring global croplands is imperative for ensuring sustainable water and food security to the people of the world in the Twenty-first Century. The currently available cropland products suffer from major limitations such as:
- Absence of precise spatial location of the cropped areas;
- Coarse resolution nature of the map products with significant uncertainties in areas, locations, and detail;
- Uncertainties in differentiating irrigated areas from rainfed areas;
- Absence of crop types and cropping intensities; and
- Absence of a dedicated web\data portal for the dissemination of cropland products.
Thereby, the overarching goal of GFSAD30 project is to produce consistent and unbiased estimates of global agricultural cropland products such as:
1) Cropland extent\area;
2) Crop types with focus on 8 crops that occupy 70% of the global cropland areas;
3) Irrigated versus rainfed;
4) Cropping intensities: single, double, triple, and continuous cropping;
5) Cropland change over space and time: 2000-2025.Once the above products are established, other products such as the following can be derived using the above products and certain other inputs:
6) Crop productivity (productivity per unit of land; kg\m2)
7) Water productivity (crop per drop or productivity per unit of water; kg\m3).The GFSAD30 Cropland Extent Products are available to download for 7 regions of the world from LPDAAC at https://lpdaac.usgs.gov/news/release-of-gfsad-30-meter-cropland-extent-… view the GDSAD product in an interactive zoomable webpage, visit https://www.usgs.gov/apps/croplands/
A global synthesis work summarizing the methods and results of the entire GFSAD30 global cropland extent product was released as the USGS Professional Paper 1868 https://pubs.er.usgs.gov/publication/pp1868
Since the release of the GFSAD30 cropland extent product, the downloads from LPDAAC and citations have been tracked and published in the Open File Report 2022-1001 at https://pubs.er.usgs.gov/publication/ofr20221001
This map shows cropland distribution across the world in a nominal 30-meter resolution derived primarily with Landsat imagery for the year 2015. The map uses machine learning algorithms on Google Earth Engine cloud computing platform. This is the baseline product of the GFSAD30 Project. There is a total of 1.874 billion hectares (roughly 12.6 percent of the global terrestrial area) of croplands in the world. View the global map or zoom-in further to see individual farms at https://www.croplands.org/app/map.(Public domain.) Sources/Usage: Some content may have restrictions. Visit Media to see details.The spatial distribution of global cropland areas (~1.5 billion hectares) and five dominant crop types (wheat, rice, maize, barley and soybeans). This composite map was produced by Thenkabail and Gumma through spatial modeling involving remote sensing derived global irrigated and rainfed croplands (Thenkabail et al., 2011, 2009a, 2009b) and five dominant global crop types from other sources (Ramankutty et al. (2008), Monfreda et al. (2008), and Portman et al. (2009)). The 5 crops constitute about 60% of all global cropland areas. Cover page credits: Dr. Prasad S. Thenkabail, U.S. Geological Survey (USGS) and Dr. Murali Krishna Gumma, International Rice Research Institute (IRRI) with inputs from the USGS Powell Center working group on global croplands (WGGC) team members (http://powellcenter.usgs.gov/current_projects.php#GlobalCroplandMembers). For more information contact: pthenkabail@usgs.gov or thenkabail@gmail.com. The image was produced for the PE&RS Special issue on global croplands, Vol. 78, No.8; August 2012 Sources/Usage: Some content may have restrictions. Visit Media to see details.Global cropland water use. Country-wise agricultural crop water use in km3/yr. In India, China, and Pakistan as a result of double and triple cropping that are irrigated, the water use is dominated by irrigated croplands (blue water use). In USA, the water use is dominated by rainfed croplands (green water use). Data source: Gleick (2011). Sources/Usage: Some content may have restrictions. Visit Media to see details.Hyperspectral signature bank of world’s major crops. The initial goal of a global cropland monitoring system should consist of developing hyperspectral signature bank of major world crops (e.g., this figure) along with crop phonologies (e.g., Figure 4) in order to: (a) establish improved models of crop biophysical and biochemical quantities, (b) increase crop classification accuracies, and (c) produce accurate crop and water productivity models. The six leading world crops (Table 1) cover 64% of the global cropland areas. Sample hyperspectral signatures of these six World crops are illustrated in the figure. The background image is irrigated and rainfed croplands of the world (Thenkabail et al., 2009a, 2009b, 2011). Sources/Usage: Some content may have restrictions. Visit Media to see details.Rice map of South Asia. Crop phenologies and intensities studied using time-series remotely sensed data illustrated for rice crop in South Asia. A clear and deep understanding of phenologies and intensities will require us to develop a temporal (e.g., this figure) and spectral knowledge base of each crop in different agro-ecosystems of the world leading to mapping distinct classes within a crop, which in turn will lead to accurate assessments of green water use (rainfed croplands) and blue water use (irrigated croplands). Sources/Usage: Some content may have restrictions. Visit Media to see details.Global croplands and other land use and land cover. This baseline product is derived based on AVHRR time-series, SPOT Vegetation, and a number of secondary data by using the Data published by Thenkabail et al. (2009, 2011; see publications). [Credits: Prasad Thenkabail and Zhuoting Wu]. Sources/Usage: Some content may have restrictions. Visit Media to see details.Key global cropland area products that will support food security analysis in the twenty-first century. [Credits: GFSAD30 project team] Sources/Usage: Some content may have restrictions. Visit Media to see details.An aggregated three class global cropland extent map at nominal 1-km based on four major studies: Thenkabail et al. (2009a, 2011), Pittman et al. (2010), Yu et al. (2013) and Friedl et al. (2010). Class 1 is total cropland extent based on pixels with 100% cropland cover (2.3 billion hectares). Class2 and Class3 have minor fractions of croplands. Sources/Usage: Some content may have restrictions. Visit Media to see details.A disaggregated twelve class global cropland extent map derived at nominal 1-km based on four major studies: Thenkabail et al. (2009a, 2011), Pittman et al. (2010), Yu et al. (2013) and Friedl et al. (2010). Classes 1-9 are cropland classes and show the dominance of irrigated and rainfed agriculture. Classes 10-12 have minor/very minor fractions of croplands. Sources/Usage: Some content may have restrictions. Visit Media to see details.Center image of global cropland (irrigated and rainfed) areas @ 1 km for year 2000 produced by overlying the remote sensing derived product of the International Water Management Institute (IWMI; Thenkabail et al., 2012, 2011, 2009a, 2009b; https://www.iwmi.cgiar.org/) over 5 dominant crops (wheat, rice, maize, barley and soybeans) of the world produced by Ramankutty et al. (2008). The 5 crops constitute about 60% of all global cropland areas. The IWMI remote sensing product is derived using remotely sensed data fusion (e.g., NOAA AVHRR, SPOT VGT, JERS SAR), secondary data (e.g., elevation, temperature, and precipitation), and in-situ data. Total area of croplands is 1.53 billion hectares of which 399 million hectares is total area available for irrigation (without considering cropping intensity) and 467 million hectares is annualized irrigated areas (considering cropping intensity). Surrounding NDVI images of irrigated areas: The January to December irrigated area NDVI dynamics is produced using NOAA AVHRR NDVI. The irrigated areas were determined by Thenkabail et al. (2011, 2009a, b). Sources/Usage: Some content may have restrictions. Visit Media to see details.Global agricultural dynamics over 2 decades (1982-2000) illustrated here for some of the most significant agricultural areas of the World. The baseline data is the global irrigated and rainfed croplands of the world for nominal year 2000 produced by Thenkabail et al. (2012). The time-series graphics is derived from AVHRR 8-km NDVI monthly data from 1982-2000. Sources/Usage: Some content may have restrictions. Visit Media to see details.Available field data points from various sources. The IWMI, Gumma, and Thenkabail collections are collected by this team or the former teams as in publications Thenkabail et al. (2009, 2011). These have detailed ground data at every point with coordinates, photos, and land cover types. The Geo_wiki_validation, Geo_wiki_competetion, and USAID_Project collections are sourced from various people from around the world as part of the Geo-Wiki Project (www.geo-wiki.org) which aims to improve the quality of global land cover maps. The project is currently adding more data through field visits during the period of the project as well as data sourced from various sources. (Credits for organizing the data: Mutlu Ozdogan and Matthew Bougie).Disclaimer: This data, compiled from various sources, is not for distribution at this stage. When we decide to disseminate this, that will be done through this website. - Science
Relevant methodology including Models and Algorithms used by the group.
Automated Cropland Mapping Algorithm (ACMA) for Africa using Moderate Resolution Imaging Spectroradiometer (MODIS) NDVI Time-series
This repo contains an automated cropland mapping algorithm (ACMA) for Africa using Moderate Resolution Imaging Spectroradiometer (MODIS) NDVI Time-series dataset, implemented by Google Earth Engine (GEE) JavaScript API. In general, this exact code was used by Jun Xiong to generate 250m global cropland product (GCP250m) for continental Africa. You can also read more on ACM2016 in a paper (Xiong and...Automated Cropland Classification Algorithm (ACCA) for Australia using MODIS 250-m Time-series
We have provided here automated cropland classification algorithm (ACCA) model (Figure 1) for Australia along with sample: (a) MODIS 250-m time-series data used to produce it, (b) cropland masks, and (c) output cropland product (Figure 2), and a readme file. User’s can download the ACCA algorithm (Figure 1, in .gmd format downloadable link below) that is in ERDAS Imagine modeler compatible format...GFSAD30 - Archives
Automated Cropland Classification Algorithm (ACCA) is rule-based methodology for classifying cropland areas as well irrigated versus rainfed croplands areas using satellite remote sensing data. The algorithm has been applied for Tajikistan and California. - Multimedia
Below are multimedia items associated with this project.
- Publications
Below are publications associated with this project.
Mapping croplands of Europe, Middle East, Russia, and Central Asia using Landsat 30-m data, machine learning algorithms and Google Earth Engine
Accurate and timely information on croplands is important for environmental, food security, and policy studies. Spatially explicit cropland datasets are also required to derive information on crop type, crop yield, cropping intensity, as well as irrigated areas. Large area defined as continental to global cropland mapping is challenging due to differential manifestation of croplands, wide rangeAuthorsAparna Phalke, Mutlu Ozdogan, Prasad Thenkabail, Tyler Erickson, Noel GorelickFilter Total Items: 23Global cropland-extent product at 30-m resolution (GCEP30) derived from Landsat satellite time-series data for the year 2015 using multiple machine-learning algorithms on Google Earth Engine cloud
Executive SummaryGlobal food and water security analysis and management require precise and accurate global cropland-extent maps. Existing maps have limitations, in that they are (1) mapped using coarse-resolution remote-sensing data, resulting in the lack of precise mapping location of croplands and their accuracies; (2) derived by collecting and collating national statistical data that are oftenAuthorsPrasad S. Thenkabail, Pardhasaradhi G. Teluguntla, Jun Xiong, Adam Oliphant, Russell G. Congalton, Mutlu Ozdogan, Murali Krishna Gumma, James C. Tilton, Chandra Giri, Cristina Milesi, Aparna Phalke, Richard Massey, Kamini Yadav, Temuulen Sankey, Ying Zhong, Itiya Aneece, Daniel FoleyMapping croplands of Europe, Middle East, Russia, and Central Asia using Landsat 30-m data, machine learning algorithms and Google Earth Engine
Accurate and timely information on croplands is important for environmental, food security, and policy studies. Spatially explicit cropland datasets are also required to derive information on crop type, crop yield, cropping intensity, as well as irrigated areas. Large area defined as continental to global cropland mapping is challenging due to differential manifestation of croplands, wide rangeAuthorsAparna Phalke, Mutlu Ozdogan, Prasad Thenkabail, Tyler Erickson, Noel GorelickAgricultural cropland extent and areas of South Asia derived using Landsat satellite 30-m time-series big-data using random forest machine learning algorithms on the Google Earth Engine cloud
The South Asia (India, Pakistan, Bangladesh, Nepal, Sri Lanka and Bhutan) has a staggering 900 million people (~43% of the population) who face food insecurity or severe food insecurity as per United Nations, Food and Agriculture Organization’s (FAO) the Food Insecurity Experience Scale (FIES). The existing coarse-resolution (>250-m) cropland maps lack precision in geo-location of individual farmsAuthorsMurali Krishna Gumma, Prasad Thenkabail, Pardhasaradhi Teluguntla, Adam OliphantMapping cropland extent of Southeast and Northeast Asia using multi-year time-series Landsat 30-m data using Random Forest classifier on Google Earth Engine
Cropland extent maps are useful components for assessing food security. Ideally, such products are a useful addition to countrywide agricultural statistics since they are not politically biased and can be used to calculate cropland area for any spatial unit from an individual farm to various administrative unites (e.g., state, county, district) within and across nations, which in turn can be usedAuthorsAdam Oliphant, Prasad S. Thenkabail, Pardhasaradhi Teluguntla, Jun Xiong, Murali Krishna Gumma, Russell G. Congalton, Kamini YadavA 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform
Mapping high resolution (30-m or better) cropland extent over very large areas such as continents or large countries or regions accurately, precisely, repeatedly, and rapidly is of great importance for addressing the global food and water security challenges. Such cropland extent products capture individual farm fields, small or large, and are crucial for developing accurate higher-level croplandAuthorsPardhasaradhi Teluguntla, Prasad S. Thenkabail, Adam Oliphant, Jun Xiong, Murali Krishna Gumma, Russell G. Congalton, Kamini Yadav, Alfredo HueteNominal 30-m cropland extent map of continental Africa by integrating pixel-based and object-based algorithms using Sentinel-2 and Landsat-8 Data on Google Earth Engine
A satellite-derived cropland extent map at high spatial resolution (30-m or better) is a must for food and water security analysis. Precise and accurate global cropland extent maps, indicating cropland and non-cropland areas, are starting points to develop higher-level products such as crop watering methods (irrigated or rainfed), cropping intensities (e.g., single, double, or continuous cropping)AuthorsJun Xiong, Prasad S. Thenkabail, James C. Tilton, Murali Krishna Gumma, Pardhasaradhi G. Teluguntla, Adam Oliphant, Russell G. Congalton, Kamini Yadav, Noel GorelickMODIS phenology-derived, multi-year distribution of conterminous U.S. crop types
Innovative, open, and rapid methods to map crop types over large areas are needed for long-term cropland monitoring. We developed two novel and automated decision tree classification approaches to map crop types across the conterminous United States (U.S.) using MODIS 250 m resolution data: 1) generalized, and 2) year-specific classification. The classification approaches use similarities and dissAuthorsRichard Massey, T.T Sankey, Russ Congalton, Kamini Yadav, Prasad Thenkabail, Mutlu Ozdogan, Sanchez MeadorSpectral matching techniques (SMTs) and automated cropland classification algorithms (ACCAs) for mapping croplands of Australia using MODIS 250-m time-series (2000–2015) data
Mapping croplands, including fallow areas, are an important measure to determine the quantity of food that is produced, where they are produced, and when they are produced (e.g. seasonality). Furthermore, croplands are known as water guzzlers by consuming anywhere between 70% and 90% of all human water use globally. Given these facts and the increase in global population to nearly 10 billion by thAuthorsPardhasaradhi G. Teluguntla, Prasad S. Thenkabail, Jun Xiong, Murali Krishna Gumma, Russell G. Congalton, Adam Oliphant, Justin Poehnelt, Kamini Yadav, Mahesh N. Rao, Richard MasseyAutomated cropland mapping of continental Africa using Google Earth Engine cloud computing
The automation of agricultural mapping using satellite-derived remotely sensed data remains a challenge in Africa because of the heterogeneous and fragmental landscape, complex crop cycles, and limited access to local knowledge. Currently, consistent, continent-wide routine cropland mapping of Africa does not exist, with most studies focused either on certain portions of the continent or at most aAuthorsJun Xiong, Prasad S. Thenkabail, Murali Krishna Gumma, Pardhasaradhi G. Teluguntla, Justin Poehnelt, Russell G. Congalton, Kamini Yadav, David ThauMapping rice-fallow cropland areas for short-season grain legumes intensification in South Asia using MODIS 250 m time-series data
The goal of this study was to map rainfed and irrigated rice-fallow cropland areas across South Asia, using MODIS 250 m time-series data and identify where the farming system may be intensified by the inclusion of a short-season crop during the fallow period. Rice-fallow cropland areas are those areas where rice is grown during the kharif growing season (June–October), followed by a fallow duringAuthorsMurali Krishna Gumma, Prasad S. Thenkabail, Pardhasaradhi G. Teluguntla, Mahesh N. Rao, Irshad A. Mohammed, Anthony M. WhitbreadGlobal Cropland Area Database (GCAD) derived from Remote Sensing in Support of Food Security in the Twenty-first Century: Current Achievements and Future Possibilities
The precise estimation of the global agricultural cropland- extents, areas, geographic locations, crop types, cropping intensities, and their watering methods (irrigated or rainfed; type of irrigation) provides a critical scientific basis for the development of water and food security policies (Thenkabail et al., 2012, 2011, 2010). By year 2100, the global human population is expected to grow to 1AuthorsPardhasaradhi G. Teluguntla, Prasad S. Thenkabail, Jun Xiong, Murali Krishna Gumma, Chandra Giri, Cristina Milesi, Mutlu Ozdogan, Russ Congalton, James Tilton, Temuulen Tsagaan Sankey, Richard Massey, Aparna Phalke, Kamini YadavGlobal land cover mapping: a review and uncertainty analysis
Given the advances in remotely sensed imagery and associated technologies, several global land cover maps have been produced in recent times including IGBP DISCover, UMD Land Cover, Global Land Cover 2000 and GlobCover 2009. However, the utility of these maps for specific applications has often been hampered due to considerable amounts of uncertainties and inconsistencies. A thorough review of theAuthorsRussell G. Congalton, Jianyu Gu, Kamini Yadav, Prasad S. Thenkabail, Mutlu Ozdogan - Web Tools
Below are data or web applications associated with this project.
- News
Below are news stories associated with this project.
The GFSAD30 project accomplished their goal!
The global croplands mapping project has succesfully mapped croplands across the entire planet in order to understand the security of food world wide. Below are many press anouncments and interviews with the project leader Prasad Thenkabail.
- Partners
Below are partners associated with this project.
Filter Total Items: 25