Estimation of potato water footprint using machine leaning algorithms models in arid regions

Abstract

Precise assessment of water footprint to enhance water consumption and crop yields for irrigated agricultural efficiency is required in order to achieve water management sustainability. Although Penman-Monteith is more successful than others and is the most frequently used technique to calculate water footprint it requires a significant number of meteorological parameters at different spatio-temporal scales, sometimes inaccessible in many of the poor nations. Due to the greatest performance in the non-linear relations of inputs and output of the model, the complex hydrological phenomena are frequently described in machine learning models. Therefore, the objective of this research is to 1) develop and compare between the four-machine learning: Support Vector Regression (SVR), Random Forest (RF), Extreme Gradient Boost (XGB) and Artificial Neural Network (ANN) over three potato’s governorates (Al-Gharbia, Al-Dakahlia, and Al-Beheira) in Delta, Egypt and 2) select the best model in the best combination of climate input variables, which achieves high precision and low error in forecasting potato blue WF. The available variables for this study are maximum temperature (Tmax), minimum temperature (Tmin), average temperature (Tave), wind speed (WS), relative humidity (RH), precipitation (P), vapor pressure deficit (VPD), solar radiation (SR), Sown area (SA), and crop coefficient (Kc) to predict potato BWFP during (1990–2016). Six scenarios of input variables were used to test the weight of each variable in for four applied models. Different statistical indicators have been used to assess applied model performance (NSE, RMSE, MAE, MBE, A, R2, SI and MAPE). The results demonstrated that Sc5 with the XGB and ANN model is competent enough to evaluate BWF only if there are just vapor pressure deficit, precipitation, solar radiation, crop coefficient data followed by Sc1. The created models produced comparatively superior outcomes and can contribute to the decision-making process for water management and development planners.

Study on Residual Stresses of 2219 Aluminum Alloy with TIG Welding and Its Reduction by Shot Peening

“…Maleki et al [13] used various microscopy techniques to characterize the microstructure, performed microhardness, residual stress measurements and fatigue tests to understand the mechanisms of shot peening strengthening. Mohamed et al [14] investigated the influence of process pressure, nozzle distance, shot velocity, and shot angle on coverage, saturation, and surface quality through experimental investigations. Wu et al [15] examined the effects of shot peening coverage on residual stresses, surface roughness, microhardness, and microstructure of rolled surfaces.…”