This study proposes a novel monitoring tool based on Satellite Remote Sensing (SRS) data to examine the status of water distribution and Water Use Efficiency (WUE) under changing water policies in large-scale and complex irrigation schemes. The aim is to improve our understanding of the water-food nexus in such schemes. With a special reference to the Gezira Irrigation Scheme (GeIS) in Sudan during the period 2000–2014, the tool devised herein is well suited for cases where validation data are absent. First, it introduces an index, referred to as the Crop Water Consumption Index (CWCI), to assess the efficiency of water policies. The index is defined as the ratio of actual evapotranspiration (ETa) over agricultural areas to total ETa for the whole scheme where ETa is estimated using the Simplified Surface Energy Balance model (SSEB). Second, the tool uses integrated Normalized Difference Vegetation Index (iNDVI), as a proxy for crop productivity, and ETa to assess the WUE. Third, the tool uses SSEB ETa and NDVI in an attempt to detect wastage of water. Four key results emerged from this research as follows: 1) the WUE has not improved despite the changing agricultural and water policies, 2) the seasonal ETa can be used to detect the drier areas of GeIS, i.e. areas with poor irrigation water supply, 3) the decreasing trends of CWCI, slope of iNDVI-ETa linear regression and iNDVI are indicative of inefficient utilization of irrigation water in the scheme, and 4) it is possible to use SSEB ETa and NDVI to identify channels with spillover problems and detect wastage of rainwater that is not used as a source for irrigation. In conclusion, the innovative tool developed herein has provided important information on the efficiency of a large-scale irrigation scheme to help rationalize laborious water management processes and increase productivity.

Accurate information on irrigated areas’ spatial distribution and extent are crucial in enhancing agricultural water productivity, water resources management, and formulating strategic policies that enhance water and food security and ecologically sustainable development. However, data are typically limited for smallholder irrigated areas, which is key to achieving social equity and equal distribution of financial resources. This study addressed this gap by delineating disaggregated smallholder and commercial irrigated areas through the random forest algorithm, a non-parametric machine learning classifier. Location within or outside former apartheid “homelands” was taken as a proxy for smallholder, and commercial irrigation. Being in a medium rainfall area, the huge irrigation potential of the Inkomati-Usuthu Water Management Area (UWMA) is already well developed for commercial crop production outside former homelands. However, information about the spatial distribution and extent of irrigated areas within former homelands, which is largely informal, was missing. Therefore, we first classified cultivated lands in 2019 and 2020 as a baseline, from where the Normalised Difference Vegetation Index (NDVI) was used to distinguish irrigated from rainfed, focusing on the dry winter period when crops are predominately irrigated. The mapping accuracy of 84.9% improved the efficacy in defining the actual spatial extent of current irrigated areas at both smallholder and commercial spatial scales. The proportion of irrigated areas was high for both commercial (92.5%) and smallholder (96.2%) irrigation. Moreover, smallholder irrigation increased by over 19% between 2019 and 2020, compared to slightly over 7% in the commercial sector. Such information is critical for policy formulation regarding equitable and inclusive water allocation, irrigation expansion, land reform, and food and water security in smallholder farming systems.

Accurate information on irrigated areas’ spatial distribution and extent are crucial in enhancing agricultural water productivity, water resources management, and formulating strategic policies that enhance water and food security and ecologically sustainable development. However, data are typically limited for smallholder irrigated areas, which is key to achieving social equity and equal distribution of financial resources. This study addressed this gap by delineating disaggregated smallholder and commercial irrigated areas through the random forest algorithm, a non-parametric machine learning classifier. Location within or outside former apartheid “homelands” was taken as a proxy for smallholder, and commercial irrigation. Being in a medium rainfall area, the huge irrigation potential of the Inkomati-Usuthu Water Management Area (UWMA) is already well developed for commercial crop production outside former homelands. However, information about the spatial distribution and extent of irrigated areas within former homelands, which is largely informal, was missing. Therefore, we first classified cultivated lands in 2019 and 2020 as a baseline, from where the Normalised Difference Vegetation Index (NDVI) was used to distinguish irrigated from rainfed, focusing on the dry winter period when crops are predominately irrigated. The mapping accuracy of 84.9% improved the efficacy in defining the actual spatial extent of current irrigated areas at both smallholder and commercial spatial scales. The proportion of irrigated areas was high for both commercial (92.5%) and smallholder (96.2%) irrigation. Moreover, smallholder irrigation increased by over 19% between 2019 and 2020, compared to slightly over 7% in the commercial sector. Such information is critical for policy formulation regarding equitable and inclusive water allocation, irrigation expansion, land reform, and food and water security in smallholder farming systems.

Accurate information on irrigated areas’ spatial distribution and extent are crucial in enhancing agricultural water productivity, water resources management, and formulating strategic policies that enhance water and food security and ecologically sustainable development. However, data are typically limited for smallholder irrigated areas, which is key to achieving social equity and equal distribution of financial resources. This study addressed this gap by delineating disaggregated smallholder and commercial irrigated areas through the random forest algorithm, a non-parametric machine learning classifier. Location within or outside former apartheid “homelands” was taken as a proxy for smallholder, and commercial irrigation. Being in a medium rainfall area, the huge irrigation potential of the Inkomati-Usuthu Water Management Area (UWMA) is already well developed for commercial crop production outside former homelands. However, information about the spatial distribution and extent of irrigated areas within former homelands, which is largely informal, was missing. Therefore, we first classified cultivated lands in 2019 and 2020 as a baseline, from where the Normalised Difference Vegetation Index (NDVI) was used to distinguish irrigated from rainfed, focusing on the dry winter period when crops are predominately irrigated. The mapping accuracy of 84.9% improved the efficacy in defining the actual spatial extent of current irrigated areas at both smallholder and commercial spatial scales. The proportion of irrigated areas was high for both commercial (92.5%) and smallholder (96.2%) irrigation. Moreover, smallholder irrigation increased by over 19% between 2019 and 2020, compared to slightly over 7% in the commercial sector. Such information is critical for policy formulation regarding equitable and inclusive water allocation, irrigation expansion, land reform, and food and water security in smallholder farming systems.