The estimation of reference evapotranspiration (ET_o), a crucial step in the hydrologic cycle, is essential for system design and management, including the balancing, planning, and scheduling of agricultural water supply and water resources. When climates vary from arid to semi-arid, and there are problems with a lack of meteorological data and a lack of future information on ET_o, as is the case in Egypt, it is more important to estimate ET_o precisely. To address this, the current study aimed to model ET_o for Egypt’s most important agricultural governorates (Al Buhayrah, Alexandria, Ismailiyah, and Minufiyah) using four machine learning (ML) algorithms: linear regression (LR), random subspace (RSS), additive regression (AR), and reduced error pruning tree (REPTree). The Climate Forecast System Reanalysis (CFSR) of the National Centers for Environmental Prediction (NCEP) was used to gather daily climate data variables from 1979 to 2014. The datasets were split into two sections: the training phase, i.e., 1979–2006, and the testing phase, i.e., 2007–2014. Maximum temperature (T_max), minimum temperature (T_min), and solar radiation (SR) were found to be the three input variables that had the most influence on the outcome of subset regression and sensitivity analysis. A comparative analysis of ML models revealed that REPTree outperformed competitors by achieving the best values for various performance matrices during the training and testing phases. The study’s novelty lies in the use of REPTree to estimate and predict ET_o, as this algorithm has not been commonly used for this purpose. Given the sparse attempts to use this model for such research, the remarkable accuracy of the REPTree model in predicting ET_o highlighted the rarity of this study. In order to combat the effects of aridity through better water resource management, the study also cautions Egypt’s authorities to concentrate their policymaking on climate adaptation.

Al-Ahsa Oasis is one of the oldest and biggest agricultural regions in Saudi Arabia. Thirty-six soil samples representing most of the soil type in the region were collected and analysed in a laboratory for physical properties including particle size (sand%, silt%, clay%), saturation θ_s, and bulk density ρ. The soil–water characteristic curve (SWCC) was measured using the filter paper method. Intensive statistical analysis included correlation, stepwise multiple linear regression analysis (SWR), mean square error (MSE), and F-test were used to evaluate the potential PTFs. Silt (silt%) and bulk density (ρ) were achieved a high accuracy in prediction of (ρ) and saturation (θ_s) respectively. Both field capacity (FC) and wilting point (WP) were correlated significantly with θ_s with a very high prediction compatibility and MSE 0.004 and 0.001 respectively. Using tow levels of prediction demonstrated high correctness in predicting SWCC with correlation coefficient 0.986 and 0.952 with a low MSE equal to 0.0007 and 0.0028 respectively. The result of this study shown the high feasibility of developing a model for the prediction of SWCC using easily readable PTFs.

This study aims to produce digital maps showing the physical and hydraulic soil properties of the Al-Ahsa Oasis in Saudi Arabia by employing the capabilities of the GIS technique. These maps can display the pattern distribution of different physical and hydraulic properties of soil accurately and accessibly. Recently developed local pedotransfer function (PTF) models were applied to the basic soil data of earlier research covering 566 points. An analysis was conducted using a spatial interpolation technique of the GIS program. Maps of spatial patterns described essential soil physical and hydraulic properties such as sand%, silt%, clay%, bulk density (ρ), saturation (θ_s), field capacity (FC), wilting point (WP), and soil water characteristic curve (SWCC) fitting parameters b, c, d. Sand dominates most of the study area, particularly in the northeast near Hufof. This may be attributed to the deposition of drifting sand and dune movement. Silt and clay increased in other locations. Bulk density ρ was positively increased with sand and negatively with silt and CaCO₃ content. Soil hydraulic properties (θ, FC, WP, and SWCC fitting parameters b, c, d) were positively correlated with silt and ρ and negatively with sand content. This digital map can be employed for a general overview investigation, for the whole studied area, for agricultural expansion and for environmental studies.

Al-Hassa is one of the oldest and largest agricultural regions in Saudi Arabia. It was determined that thirty soil samples representing the majority of soil types within the region were collected and analyzed for their physical and hydraulic properties in a laboratory, including particle size (sand percent, silt percent, clay percent), saturation percent (θs), bulk density (ρ), calcium carbonate percent (CaCO3), Field capacity (FC), wilting point (WP), and saturated conductivity (Ks). A comprehensive statistical analysis was conducted to develop a pedotransfer function (PTF) to predict potential relationships between physical properties and Ks values based on correlation, stepwise multiple linear regression, mean square error (MSE), root mean square error (RMSE), t-test, and Nash-Sutcliffe efficiency (NSE). In a stepwise analysis, both sand and ρ highly influence the outcome. A significant correlation was found with Ks equal to (0.755), MSE equal to 0.045, RMSE equal to 0.194, and satisfactory NSE equal to 0.581. Using the spatial interpolation technique of the GIS map program, a new model was applied to more than 500 points of soil data in order to develop a new spatial pattern map based on the Ks value. The map is designed to provide an easy-to-read and quick-reach guide for environmental researchers and engineers in determining the Ks value in the studied area in Al-Ahsa Oasis.