Sensitivity Analysis of Parameters Affecting the Early Cost of Drip Irrigation Systems Using Meta-Heuristic Algorithms

this study aims to determine the most effective features on the cost of drip irrigation systems in four parts, including the Cost of pumping station and central control system (TCP), Cost of on-farm equipment (TCF), Cost of installation and operation on-farm and pumping station (TCI) and Total cost (TCT). First, data of 100 drip irrigation projects implemented in different parts of the country were collected and it was prepared a database containing 39 important and influential variables in the cost of the mentioned parts. Based on the sensitivity analysis, the best evaluation criteria were obtained in TCP and the numerical amount of gamma statistic, Expected Absolute Error, Gradient statistic, Standard Error of Γ, coefficient of determination (R2), and V-Ratio index were recorded as 0.048, 0.219, 0.008, 0.024, 0.87 and 0.192, respectively, which indicate the high correlation between the experimental variables and the cost of the corresponded sector. To find the optimal combination of data for cost modeling, we used Genetic Algorithm (GA), Hill Climbing (HC), and Full Embedding (FE). The results showed that the number of required variables and the optimal input combination, which covered 40 and 90% of the variables (16 and 35 variables, respectively) in GA and HC method reached 20% in the FE method and only eight variables were selected for cost modeling and also the results of this method were selected as the superior model. Moreover, the result of the hybrid model revealed the simplest and most optimal model was obtained when QT (l/s) (total amount of available water flow), SR (m) (plant row spacing), QE (l/s) (emitter flow), T (h) (number of working hours per day) and NIT (n) (number of irrigation shifts) were used as the optimal input combination to modeling the cost of drip irrigation systems.