The increasing frequency of droughts and floods due to climate change has severely affected water resources across the globe in recent years. An optimal design for the scheduling and management of irrigation is thus urgently needed to adapt agricultural activities to the changing climate. The accurate estimation of reference crop evapotranspiration (ET0), a vital hydrological component of the water balance and crop water need, is a tiresome task if all the relevant climatic variables are unavailable. This study investigates the potential of four ensemble techniques for estimating precise values of the daily ET0 at representative stations in 10 agro-climatic zones in the state of Karnataka, India, from 1979 to 2014. The performance of these models was evaluated by using several combinations of climatic variables as inputs by using tenfold cross-validation. The outcomes indicated that predictions of ET0 by all four ensemble models based on all climatic variables were the most accurate in comparison with other input combinations. The random forest regressor was found to deliver the best performance among the four models on all measures considered (Nash–Sutcliffe efficiency, 1.0, root-mean-squared error, 0.016 mm/day, and mean absolute error, 0.011 mm/day). However, it incurred the highest computational cost, whereas the computational cost of the bagging model for linear regression was the lowest. The extreme gradient-boosting model delivered the most stable performance with a modified training dataset. The work here shows that these models can be recommended for daily ET₀ estimation based on the users’ interests.

Accurate estimation of reference evapotranspiration (ET₀) is an essential requirement for water resource management and scheduling agricultural activities. Several empirical methods have been employed in estimating ET₀ across diverse climate regimes over the past decades. The Python implementation for estimation of daily and monthly ET₀ values of representative stations of ten agro-climatic zones of Karnataka from 1979 through 2014 using the standard FAO Penman-Monteith method was carried out. The assessment of temporal and spatial variability of monthly ET₀ values across the various agro-climatic zones done by the various statistical measures revealed that the variation in spatial ET₀ values was higher than temporal indicating major differentiation of ET₀ values was with respect to the stations rather than years under study. The non-parametric Mann-Kendall test conducted at 1% significance level on the annual ET₀ values revealed that statistically significant increasing trend was observed for all the ten stations during the study period. The trend test conducted on the climate variables like mean air temperature, wind speed, relative humidity and solar radiation signify their influence the annual ET₀ values. The magnitude changes in the trends detected by the Theil Sen’s slope indicated that increasing values of mean temperature, solar radiation and decreasing values of relative humidity predominantly contributed to the annual upward trend in ET₀ values for the 10 stations. A trivial impact of wind speed on annual ET₀ values was observed for the stations. Kalburgi and Udupi stations exhibited positive ET₀ trend with the highest and lowest annual values among ten stations.