Evapotranspiration (ET) is a major component of the water cycle and agricultural water balance. Estimation of water consumption over agricultural areas is important for agricultural water resources planning, management, and regulation. It leads to the establishment of a sustainable water balance, mitigates the impacts of water scarcity, as well as prevents the overusing and wasting of precious water resources. As evapotranspiration is a major consumptive use of irrigation water and rainwater on agricultural lands, improvements of water use efficiency and sustainable water management in agriculture must be based on the accurate estimation of ET. Applications of precision and digital agricultural technologies, the integration of advanced techniques including remote sensing and satellite technology, and usage of machine learning algorithms will be an advantage to enhance the accuracy of the ET estimation in agricultural water management. This paper reviews and summarizes the technical development of the available methodologies and explores the advanced techniques in the estimation of ET in agricultural water management and highlights the potential improvements to enhance the accuracy of the ET estimation to achieve precise agricultural water management.

Groundwater resources are severely threatened not only in terms of their quality but also their quantity. The availability of groundwater in arid regions is highly important as it caters to domestic needs, irrigation, and industrial purposes in those areas. With the increasing population and human needs, artificial recharging of groundwater has become an important topic because of rainfall scarcity, high evaporation, and shortage of surface water resources in arid regions. However, this has been given the minimum attention in the context of Sri Lanka. Therefore, the current research was carried out to demarcate suitable sites for the artificial recharging of aquifers with the help of geographic information system (GIS) techniques, in one of the water-scarce regions in Sri Lanka. Tissamaharama District Secretariat Division (DSD) is located in Hambanthota district. This region faces periodic water stress with a low-intensity seasonal rainfall pattern and a lack of surface water sources. Hydrological, geological, and geomorphological parameters such as rainfall, soil type, slope, drainage density, and land use patterns were considered to be the most influential parameters in determining the artificial recharging potential in the study area. The GIS tools were used to carry out a weighted overlay analysis to integrate the effects of each parameter into the potential for artificial groundwater recharge. The result of the study shows that 14.60% of the area in the Tissamaharama DSD has a very good potential for artificial groundwater recharge, while 41.32% has a good potential and 39.03% and 5.05% have poor and very poor potential for artificial groundwater recharge, respectively. The southern part of the DSD and the Yala nature reserve areas are observed to have a higher potential for artificial groundwater recharge than the other areas of Tissamaharama DSD. It is recommended to test the efficiency and effects of groundwater recharge using groundwater models by simulating the effects of groundwater recharge in future studies. Therefore, the results of the current research will be helpful in effectively managing the groundwater resources in the study area.

Near-real-time (NRT) satellite precipitation data inherits complex and random errors due to various reasons. The primary objective of this research is to utilize satellite-based precipitation data for hydrological modelling in ungauged areas. The novelty of this study lies in the development of a hybrid stacking-based machine learning framework that integrates hydrologically meaningful predictors: root-zone soil moisture, potential evapotranspiration (PET), and their time-lagged representations to reduce uncertainty in near-real-time satellite precipitation (GSMaP-NRT). Unlike conventional bias-correction approaches that rely primarily on statistical adjustment between satellite and gauge rainfall, this study incorporates physically relevant catchment-state variables to improve predictive skill, with a focus on the Ovens River basin in Australia. A calibrated GR4H hydrological model was used to simulate the runoff of the catchment. Six objective functions were used to evaluate the performance of the approach. The results demonstrate that stacking machine learning algorithms reduces the Mean Absolute Error of GSMaP-NRT satellite precipitation data by 36% and the corresponding modelled streamflow error by 44% for lower precipitation events (< 2 mm/hour). All six objective functions achieved optimal performances within the low precipitation events. However, RMSE remained high for intermediate and heavy precipitation events. The model-estimated major streamflow peaks for the years 2010 and 2016, based on gauged precipitation and ML-corrected satellite precipitation, are 41% and 48% lower than the observed streamflow peaks, respectively. The reasons were the inability of the GR4H model to capture the perfect initial conditions and the x ₄ time parameter during the calibration process.