A Global Irrigated Area Map (GIAM) has been produced for the end of the last millennium using multiple satellite sensor, secondary, Google Earth and groundtruth data. The data included: (a) Advanced Very High Resolution Radiometer (AVHRR) 3‐band and Normalized Difference Vegetation Index (NDVI) 10 km monthly time‐series for 1997–1999, (b) Système pour l'Observation de la Terre Vegetation (SPOT VGT) NDVI 1 km monthly time series for 1999, (c) East Anglia University Climate Research Unit (CRU) rainfall 50 km monthly time series for 1961–2000, (d) Global 30 Arc‐Second Elevation Data Set (GTOPO30) 1 km digital elevation data of the World, (e) Japanese Earth Resources Satellite‐1 Synthetic Aperture Radar (JERS‐1 SAR) data for the rain forests during two seasons in 1996 and (f) University of Maryland Global Tree Cover 1 km data for 1992–1993. A single mega‐file data‐cube (MFDC) of the World with 159 layers, akin to hyperspectral data, was composed by re‐sampling different data types into a common 1 km resolution. The MFDC was segmented based on elevation, temperature and precipitation zones. Classification was performed on the segments. Quantitative spectral matching techniques (SMTs) used in hyperspectral data analysis were adopted to group class spectra derived from unsupervised classification and match them with ideal or target spectra. A rigorous class identification and labelling process involved the use of: (a) space–time spiral curve (ST‐SC) plots, (b) brightness–greenness–wetness (BGW) plots, (c) time series NDVI plots, (d) Google Earth very‐high‐resolution imagery (VHRI) ‘zoom‐in views’ in over 11 000 locations, (e) groundtruth data broadly sourced from the degree confluence project (3 864 sample locations) and from the GIAM project (1 790 sample locations), (f) high‐resolution Landsat‐ETM+ Geocover 150 m mosaic of the World and (g) secondary data (e.g. national and global land use and land cover data). Mixed classes were resolved based on decision tree algorithms and spatial modelling, and when that did not work, the problem class was used to mask and re‐classify the MDFC, and the class identification and labelling protocol repeated. The sub‐pixel area (SPA) calculations were performed by multiplying full‐pixel areas (FPAs) with irrigated area fractions (IAFs) for every class. A 28 class GIAM was produced and the area statistics reported as: (a) annualized irrigated areas (AIAs), which consider intensity of irrigation (i.e. sum of irrigated areas from different seasons in a year plus continuous year‐round irrigation or gross irrigated areas), and (b) total area available for irrigation (TAAI), which does not consider intensity of irrigation (i.e. irrigated areas at any given point of time plus the areas left fallow but ‘equipped for irrigation’ at the same point of time or net irrigated areas). The AIA of the World at the end of the last millennium was 467 million hectares (Mha), which is sum of the non‐overlapping areas of: (a) 252 Mha from season one, (b) 174 Mha from season two and (c) 41 Mha from continuous year‐round crops. The TAAI at the end of the last millennium was 399 Mha. The distribution of irrigated areas is highly skewed amongst continents and countries. Asia accounts for 79% (370 Mha) of all AIAs, followed by Europe (7%) and North America (7%). Three continents, South America (4%), Africa (2%) and Australia (1%), have a very low proportion of the global irrigation. The GIAM had an accuracy of 79–91%, with errors of omission not exceeding 21%, and the errors of commission not exceeding 23%. The GIAM statistics were also compared with: (a) the United Nations Food and Agricultural Organization (FAO) and University of Frankfurt (UF) derived irrigated areas and (b) national census data for India. The relationships and causes of differences are discussed in detail. The GIAM products are made available through a web portal (http://www.iwmigiam.org).

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), crop types, cropland fallows, as well as for assessment of cropland productivity (productivity per unit of land), and crop water productivity (productivity per unit of water). Uncertainties associated with the cropland extent map have cascading effects on all higher-level cropland products. However, precise and accurate cropland extent maps at high spatial resolution over large areas (e.g., continents or the globe) are challenging to produce due to the small-holder dominant agricultural systems like those found in most of Africa and Asia. Cloud-based geospatial computing platforms and multi-date, multi-sensor satellite image inventories on Google Earth Engine offer opportunities for mapping croplands with precision and accuracy over large areas that satisfy the requirements of broad range of applications. Such maps are expected to provide highly significant improvements compared to existing products, which tend to be coarser in resolution, and often fail to capture fragmented small-holder farms especially in regions with high dynamic change within and across years. To overcome these limitations, in this research we present an approach for cropland extent mapping at high spatial resolution (30-m or better) using the 10-day, 10 to 20-m, Sentinel-2 data in combination with 16-day, 30-m, Landsat-8 data on Google Earth Engine (GEE). First, nominal 30-m resolution satellite imagery composites were created from 36,924 scenes of Sentinel-2 and Landsat-8 images for the entire African continent in 2015–2016. These composites were generated using a median-mosaic of five bands (blue, green, red, near-infrared, NDVI) during each of the two periods (period 1: January–June 2016 and period 2: July–December 2015) plus a 30-m slope layer derived from the Shuttle Radar Topographic Mission (SRTM) elevation dataset. Second, we selected Cropland/Non-cropland training samples (sample size = 9791) from various sources in GEE to create pixel-based classifications. As supervised classification algorithm, Random Forest (RF) was used as the primary classifier because of its efficiency, and when over-fitting issues of RF happened due to the noise of input training data, Support Vector Machine (SVM) was applied to compensate for such defects in specific areas. Third, the Recursive Hierarchical Segmentation (RHSeg) algorithm was employed to generate an object-oriented segmentation layer based on spectral and spatial properties from the same input data. This layer was merged with the pixel-based classification to improve segmentation accuracy. Accuracies of the merged 30-m crop extent product were computed using an error matrix approach in which 1754 independent validation samples were used. In addition, a comparison was performed with other available cropland maps as well as with LULC maps to show spatial similarity. Finally, the cropland area results derived from the map were compared with UN FAO statistics. The independent accuracy assessment showed a weighted overall accuracy of 94%, with a producer’s accuracy of 85.9% (or omission error of 14.1%), and user’s accuracy of 68.5% (commission error of 31.5%) for the cropland class. The total net cropland area (TNCA) of Africa was estimated as 313 Mha for the nominal year 2015. The online product, referred to as the Global Food Security-support Analysis Data @ 30-m for the African Continent, Cropland Extent product (GFSAD30AFCE) is distributed through the NASA’s Land Processes Distributed Active Archive Center (LP DAAC) as (available for download by 10 November 2017 or earlier): https://doi.org/10.5067/MEaSUREs/GFSAD/GFSAD30AFCE.001 and can be viewed at https://croplands.org/app/map. Causes of uncertainty and limitations within the crop extent product are discussed in detail.

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 these global land cover projects including evaluating the sources of error and uncertainty is prudent and enlightening. Therefore, this paper describes our work in which we compared, summarized and conducted an uncertainty analysis of the four global land cover mapping projects using an error budget approach. The results showed that the classification scheme and the validation methodology had the highest error contribution and implementation priority. A comparison of the classification schemes showed that there are many inconsistencies between the definitions of the map classes. This is especially true for the mixed type classes for which thresholds vary for the attributes/discriminators used in the classification process. Examination of these four global mapping projects provided quite a few important lessons for the future global mapping projects including the need for clear and uniform definitions of the classification scheme and an efficient, practical, and valid design of the accuracy assessment.

Our goal is to map the rice areas of six South Asian countries using moderate-resolution imaging spectroradiometer (MODIS) time-series data for the time period 2000 to 2001. South Asia accounts for almost 40% of the world's harvested rice area and is also home to 74% of the population that lives on less than $2.00 a day. The population of the region is growing faster than its ability to produce rice. Thus, accurate and timely assessment of where and how rice is cultivated is important to craft food security and poverty alleviation strategies. We used a time series of eight-day, 500-m spatial resolution composite images from the MODIS sensor to produce rice maps and rice characteristics (e.g., intensity of cropping, cropping calendar) taking data for the years 2000 to 2001 and by adopting a suite of methods that include spectral matching techniques, decision trees, and ideal temporal profile data banks to rapidly identify and classify rice areas over large spatial extents. These methods are used in conjunction with ancillary spatial data sets (e.g., elevation, precipitation), national statistics, and maps, and a large volume of field-plot data. The resulting rice maps and statistics are compared against a subset of independent field-plot points and the best available subnational statistics on rice areas for the main crop growing season (kharif season). A fuzzy classification accuracy assessment for the 2000 to 2001 rice-map product, based on field-plot data, demonstrated accuracies from 67% to 100% for individual rice classes, with an overall accuracy of 80% for all classes. Most of the mixing was within rice classes. The derived physical rice area was highly correlated with the subnational statistics with R² values of 97% at the district level and 99% at the state level for 2000 to 2001. These results suggest that the methods, approaches, algorithms, and data sets we used are ideal for rapid, accurate, and large-scale mapping of paddy rice as well as for generating their statistics over large areas.

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 farms and have low map accuracies. This also results in uncertainties in cropland areas calculated from such products. Thereby, the overarching goal of this study was to develop a high spatial resolution (30-m or better) baseline cropland extent product of South Asia for the year 2015 using Landsat satellite time-series big-data and machine learning algorithms (MLAs) on the Google Earth Engine (GEE) cloud computing platform. To eliminate the impact of clouds, 10 time-composited Landsat bands (blue, green, red, NIR, SWIR1, SWIR2, Thermal, EVI, NDVI, NDWI) were derived for each of the three time-periods over 12 months (monsoon: Days of the Year (DOY) 151–300; winter: DOY 301–365 plus 1–60; and summer: DOY 61–150), taking the every 8-day data from Landsat-8 and 7 for the years 2013–2015, for a total of 30-bands plus global digital elevation model (GDEM) derived slope band. This 31-band mega-file big data-cube was composed for each of the five agro-ecological zones (AEZ’s) of South Asia and formed a baseline data for image classification and analysis. Knowledge-base for the Random Forest (RF) MLAs were developed using spatially well spread-out reference training data (N = 2179) in five AEZs. The classification was performed on GEE for each of the five AEZs using well-established knowledge-base and RF MLAs on the cloud. Map accuracies were measured using independent validation data (N = 1185). The survey showed that the South Asia cropland product had a producer’s accuracy of 89.9% (errors of omissions of 10.1%), user’s accuracy of 95.3% (errors of commission of 4.7%) and an overall accuracy of 88.7%. The National and sub-national (districts) areas computed from this cropland extent product explained 80-96% variability when compared with the National statistics of the South Asian Countries. The full-resolution imagery can be viewed at full-resolution, by zooming-in to any location in South Asia or the world, at www.croplands.org and the cropland products of South Asia downloaded from The Land Processes Distributed Active Archive Center (LP DAAC) of National Aeronautics and Space Administration (NASA) and the United States Geological Survey (USGS): https://lpdaac.usgs.gov/products/gfsad30saafgircev001/.