Modeling of irrigation water quality parameter (sodium adsorption ratio) using hybrid swarm intelligence-based neural networks in a semi-arid environment at SMBA dam, Algeria

Abstract

Sodium adsorption rate (SAR), which significantly affects soil and plant health, is determined according to the concentration of sodium ions, calcium, and magnesium in irrigation water. Accurate estimation of SAR values is vital for agricultural production and irrigation. In this study, hybrid swarm intelligence-based neural networks are used to model sodium adsorption ratio in irrigation water quality parameters in a semi-arid environment at Sidi M'Hamed Ben Aouda (SMBA) dam, Algeria. For this, the nature-inspired optimization techniques of particle swarm optimization (PSO), genetic algorithm (GA), Jaya algorithm (JA), artificial bee colony (ABC), and firefly algorithm (FFA) and the signal processing technique of variational mode decomposition (VMD) have been combined with artificial neural networks (ANN). Correlation matrices were used to select the data entry structure in the established models. Water quality parameters with a statistically significant and medium to high relationship with SAR values were presented as input to the model. The overall performance was measured using various statistical metrics, scatter diagrams, Taylor diagrams, correlograms, boxplots, and line plots. In addition, the effect of input parameters on model estimation was evaluated according to Sobol sensitivity analysis. As a result, the GA-ANN algorithm demonstrated superior performance (MSE = 0.073, MAE = 0.193, MAPE = 0.048, MBE=-0.16, R2 = 0.934, WI = 0.968, and KGE = 0.866) based on the statistical indicators, indicating better results compared to other models. The second-best model, ABC-ANN (MSE = 0.084, MAE = 0.233, MAPE = 0.066, MBE=-0.135, R2 = 0.897, WI = 0.965, and KGE = 0.920) was also selected. The weakest prediction outputs were obtained from the VMD-ANN model. The accurate and reliable estimation of SAR in irrigation water has the potential to facilitate improvements in agricultural irrigation management and agricultural production efficiency for farmers, agricultural practitioners, and policymakers.