The potential of generalized deep learning models developed for crop water estimation was examined in the current study. This study was conducted in a semiarid region of India, i.e., Karnataka, with daily climatic data (maximum and minimum air temperatures, maximum and minimum relative humidity, wind speed, sunshine hours, and rainfall) of 44 years (1976–2020) for twelve locations. The Extreme Gradient Boosting (XGBoost), Gradient Boosting (GB), and Random Forest (RF) are three ensemble deep learning models that were developed using all of the climatic data from a single location (Bengaluru) from January 1976 to December 2017 and then immediately applied at eleven different locations (Ballari, Chikmaglur, Chitradurga, Devnagiri, Dharwad, Gadag, Haveri, Koppal, Mandya, Shivmoga, and Tumkuru) without the need for any local calibration. For the test period of January 2018–June 2020, the model’s capacity to estimate the numerical values of crop water requirement (Penman-Monteith (P-M) ETo values) was assessed. The developed ensemble deep learning models were evaluated using the performance criteria of mean absolute error (MAE), average absolute relative error (AARE), coefficient of correlation (r), noise to signal ratio (NS), Nash–Sutcliffe efficiency (ɳ), and weighted standard error of estimate (WSEE). The results indicated that the WSEE values of RF, GB, and XGBoost models for each location were smaller than 1 mm per day, and the model’s effectiveness varied from 96% to 99% across various locations. While all of the deep learning models performed better with respect to the P-M ETo approach, the XGBoost model was able to estimate ETo with greater accuracy than the GB and RF models. The XGBoost model’s strong performance was also indicated by the decreased noise-to-signal ratio. Thus, in this study, a generalized mathematical model for short-term ETo estimates is developed using ensemble deep learning techniques. Because of this type of model’s accuracy in calculating crop water requirements and its ability for generalization, it can be effortlessly integrated with a real-time water management system or an autonomous weather station at the regional level.

Semi-Arid Tropical (SAT) regions are influenced by climate change impacts affecting the rainfed crops in their productivity and production. Water Footprint (WF) assessment for rainfed crops on watershed scale is critical for water resource planning, development, efficient crop planning, and, better water use efficiency. A semi-arid tropical watershed was selected in lower Krishna river basin having a 4700 ha area in Telangana, India. Soil and Water Assessment Tool (SWAT) was used to estimate the water balance components of watershed like runoff, potential evapotranspiration, percolation, and effective rainfall for base period (1994 to 2013) and different climate change scenarios of Representative Concentration Pathways (RCP) 2.6, 4.5 and 8.5 for the time periods of 2020, 2050 and 2080. Green and blue WF of rainfed crops viz., maize, sorghum, groundnut, redgram and cotton were performed by considering rainfed, and two critical irrigations (CI) of 30mm and 50mm. It indicated that the effective rainfall (ER) is less than crop evapo-transpiration (ET) during crop growing period under different RCPs, time periods, and base period. The green WF under rainfed condition over different RCPs and time periods had decreasing trend for all crops. The study suggested that in the rainfed agro-ecosystems, the blue WF can significantly reduce the total WF by enhancing the productivity through critical irrigation management using on farm water resources developed through rainwater harvesting structures. The maximum significant reduction in WF over the base period was observed 13–16% under rainfed, 30–32% with 30 mm CI and 40–42% with 50 mm CI by 2080. Development of crop varieties particularly in oilseeds and pulses which have less WF and higher yields for unit of water consumed could be a solution for improving overall WF in the watersheds of SAT regions.

The potential of generalized machine learning models developed for crop water estimation was examined in the current study. Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), and Random Forest (RF) are three ensembled machine learning models that were developed using all of the data from a single location from 1976 to 2017 and then immediately applied at eleven different locations without the need for any local calibration. For the test period of January 2018 to June 2020, the model's capacity to estimate the numerical values of crop water requirement (Pen-man-Monteith (PM) ETo values) was assessed. In comparison to the GBM and RF models, the XGBoost model outperformed them both marginally and significantly. The estimate's weighted standard error was smaller than 0.85 mm/day, and the model's effectiveness varied from 96% to 99% across various locations. The model's strong performance was indicated by the decreased noise-to-signal ratio. A real-time water management system at the regional level can be seamlessly linked with this type of model due to its accuracy in estimating crop water requirements and its capacity to generalize.