Water scarcity is a major challenge for irrigated agriculture, particularly in developing countries where access to meteorological data for calculating reference evapotranspiration (ET_o) is limited. Thus, this study explores the potential of two machine learning models (random forest (RF) and long short-term memory (LSTM)) and autoregressive integrated moving average (ARIMA) to forecast ET_o. The investigation was conducted for four weather stations in Egypt, from 1982 to 2020. The machine learning models were evaluated using four combinations of inputs: maximum and minimum temperature, relative humidity, and wind speed. The best results for both RF and LSTM models were achieved with the first set of inputs that included all four variables at both regional and local scales. For the regional scale, RF and LSTM models achieved R² values of 0.85 and 0.86, respectively, with RMSE values of 0.69 and 0.68 mm/day. At the local scale, RF and LSTM models exhibited R² values ranging from 0.92 to 0.95 and 0.93 to 0.95, respectively, while RMSE ranged between 0.38 and 0.46 mm/day and 0.37–0.43 mm/day, respectively. Additionally, ARIMA models were employed for tim series analysis of the same ET_o data. ARIMA (2,1,4) and ARIMA (2,1,3) were found to be the most suitable models for the local-scale analysis while ARIMA (2,1,4) was identified as the optimal model for the regional-scale analysis. For the local-scale analysis, R² values ranged from 0.86 to 0.91 and RMSE values ranged from 0.26 to 0.38. The regional scale analysis yielded an R² value of 0.89 and an RMSE value of 0.58 mm/day. The developed models can be used in places where meteorological data for forecasting ET_o are limited.

Assessing the energy cycle and greenhouse gas (GHG) emissions of wheat production in small Egyptian farms is essential to improve wheat productivity to meet population growth and achieve sustainable development. This study aims to compare wheat production in terms of energy use and GHG emissions for different scenarios in the Delta of Egypt and to use Data Envelopment Analysis (DEA) to optimize the wheat production system. Three common scenarios of the wheat production system (S-I, S-II, and S-III) from old lands with one scenario (S-IV) from newly reclaimed land were included in the study. Data were collected from small farmers through a face-to-face questionnaire and interviews in 2022–2023. The results showed that the third scenario (S-III) in the old lands had the lowest input energy consumption (42,555 MJ ha⁻¹) and the highest output energy (160,418 MJ ha⁻¹), with an energy use efficiency of 3.770. In comparison, the input and output energy for the newly reclaimed scenario (S-IV) were 37,575 and 130,581 MJ ha⁻¹, respectively, with an energy use efficiency of 3.475. S-III was an optimum scenario due to its high energy indicators, such as energy productivity of 0.173 kg MJ⁻¹. The total GHG emissions of S-III were the lowest in old lands with a value of 1432.9 kg CO_2-eq ha⁻¹, while S-IV had 1290.2 kg CO_2-eq ha⁻¹. The highest GHG emissions input was diesel fuel for machinery and irrigation, followed by manure, chemical fertilizers, and agricultural machinery use. Using mechanization in most farming operations for S-III and S-IV led to decreased losses of agricultural inputs with increasing outputs (yield and straw). Therefore, using them in wheat farming practices is recommended to increase the wheat farming system’s energy efficiency and GHG emissions.

The inequality between available water supplies and growing water demand from diverse sectors, as well as the predicted climate changes are putting significant pressures on Egypt’s food security. There is a nation-wide demand for new scientifically proven on-farm practices to boost water productivity of major food crops. The objective of this study was to explore the use of various deficit irrigation schemes to improve water productivity ( WP) of tomato cultivated in Egypt under distinct climate change scenarios, RCP4.5 and RCP8.5, in three time-steps of the reference period (2006– 2016), 2030s, and 2050s. The AquaCrop model was used to simulate the influence of climate change on the tomato crop, as well as two deficit irrigation application schemes for the full growing season and the regulated application for the initial and maturity crop stages. With the same irrigation method, the predicted WP increased in a general pattern across all climate change scenarios. The combination of irrigation schedule with the 80% deficit irrigation can enhance WP near the optimum level (approximately 2.2 kg∙m–3), especially during early and mature stages of the crop, saving up to 16% of water. The results showed that the expected temperature rise by 2050s would reduce the crop growth cycle by 3– 11 days for all irrigation treatments, resulting in a 1–6% decrease in crop evapotranspiration ( ETc) and affecting the dry tomato yield with different patterns of increase and decrease due to climate change.

Designing an irrigation landscape turf network using pop-up sprays and expert system programs involves integrating hydraulic principles, nozzle selection, spacing strategies, and software tools to optimize water efficiency and coverage. This study evaluates the performance of a sprinkler irrigation system at Al Azbakeya historical garden using two layout patterns, square and triangular, under varying operating pressures (150, 170, and 200 kPa). Performance indicators such as Distribution Uniformity (DU) and Christiansen’s Uniformity (CU) were analyzed. Results showed significant improvements in DU and CU with increasing pressure, particularly for the square layout, which achieved 90% DU and 93.74% CU at 200 kPa classified as excellent. In contrast, the triangular pattern reached only 86.35% DU and 75.10% CU, maintaining an acceptable range. To support irrigation design and management, the DOSEX program was used and validated against CROPWAT estimates. DOSEX produced irrigation run-times and component configurations closely matching those of CROPWAT, confirming its reliability. Furthermore, monthly water requirement analysis revealed that site-specific data produced by DOSEX better aligns with local climatic variations than generic calculations. Water saving analysis demonstrated that both DOSEX and CROPWAT showed increasing savings with higher pressures; however, DOSEX consistently reported slightly higher savings due to its use of localized, real-time weather data and optimization capabilities. At 210 kPa, water savings reached 11.2% with DOSEX versus 10.11% with CROPWAT.