Improvements in irrigated areas’ classification accuracy are critical to enhance agricultural water management and inform policy and decision-making on irrigation expansion and land use planning. This is particularly relevant in water-scarce regions where there are plans to increase the land under irrigation to enhance food security, yet the actual spatial extent of current irrigation areas is unknown. This study applied a non-parametric machine learning algorithm, the random forest, to process and classify irrigated areas using images acquired by the Landsat and Sentinel satellites, for Mpumalanga Province in Africa. The classification process was automated on a big-data management platform, the Google Earth Engine (GEE), and the R-programming was used for post-processing. The normalised difference vegetation index (NDVI) was subsequently used to distinguish between irrigated and rainfed areas during 2018/19 and 2019/20 winter growing seasons. High NDVI values on cultivated land during the dry season are an indication of irrigation. The classification of cultivated areas was for 2020, but 2019 irrigated areas were also classified to assess the impact of the Covid-19 pandemic on agriculture. The comparison in irrigated areas between 2019 and 2020 facilitated an assessment of changes in irrigated areas in smallholder farming areas. The approach enhanced the classification accuracy of irrigated areas using ground-based training samples and very high-resolution images (VHRI) and fusion with existing datasets and the use of expert and local knowledge of the study area. The overall classification accuracy was 88%.

Unmanned Aerial Vehicles (UAVs) are an alternative to costly and time-consuming traditional methods to improve agricultural water management and crop productivity through the acquisition, processing, and analyses of high-resolution spatial and temporal crop data at field scale. UAVs mounted with multispectral and thermal cameras facilitate the monitoring of crops throughout the crop growing cycle, allowing for timely detection and intervention in case of any anomalies. The use of UAVs in smallholder agriculture is poised to ensure food security at household level and improve agricultural water management in developing countries. This review synthesises the use of UAVs in smallholder agriculture in the smallholder agriculture sector in developing countries. The review highlights the role of UAV derived normalised difference vegetation index (NDVI) in assessing crop health, evapotranspiration, water stress and disaster risk reduction. The focus is to provide more accurate statistics on irrigated areas, crop water requirements and to improve water productivity and crop yield. UAVs facilitate access to agro-meteorological information at field scale and in near real-time, important information for irrigation scheduling and other on-field decision-making. The technology improves smallholder agriculture by facilitating access to information on crop biophysical parameters in near real-time for improved preparedness and operational decision-making. Coupled with accurate meteorological data, the technology allows for precise estimations of crop water requirements and crop evapotranspiration at high spatial resolution. Timely access to crop health information helps inform operational decisions at the farm level, and thus, enhancing rural livelihoods and wellbeing.

Rainfall and air temperature variability pose the greatest risk to environmental change. Past trends in rainfall and air temperature facilitate projecting future climate changes for informed policy responses. We used a combination of the normalised difference vegetation index (NDVI) and observed data from 1968 to 2017 to assess changes in rainfall, moisture stress, and air temperature variability over time on bioclimatic regions of KwaZulu-Natal (KZN) Province, South Africa. Indicators used included consecutive dry days (CDDs), consecutive wet days (CWDs), very heavy rainfall days (R20), monthly maximum daily maximum air temperature (TXx), monthly minimum daily minimum air temperature (TNn), the total number of rainfall days, and monthly air temperature averages. Trends in rainfall and moisture stress are notable in different bioclimatic regions across the province. However, these trends are diverse, in general, and spatially different across and within the bioclimatic regions. Further, related rainfall indicators do not respond in the same way as would be expected. Air temperature trends were consistent with global trends and land–air temperature anomalies. Although daytime air temperatures showed a positive trend, extreme air temperature events and increases are predominant in inland regions. Night-time air temperatures showed an upward trend in most stations across KZN. Local weather-and-climate related characteristics are evolving due to climatic variability and change. The study shows that changes in climatic activities are detectable at a local level from existing historical weather data; therefore, adaptation strategies should be contextualised to respond to local and area-specific challenges.