Abstract
In irrigation systems, salinity is a critical problem as it has undesirable impacts on crop health, agricultural throughput and farming management. Considering these, it is imperative to regularly monitor and develop measures to predict salinity of the soil to negate the salinization effects on agriculture. This paper constructs and evaluates the performance of the hybrid machine learning model of multilayer perceptron (MLP)-Grey Wolf Optimizer (MLP-GWO) for electrical conductivity (EC). MLP-GWO model is trained with soil sample data (i.e., parameters for organic matter, OM and soil constituents Ca+2, Mg+2, K+, Na+, Cl−, SO4−2, HCO3−) from Khuzestan province in Iran. Seven modelling scenarios representing different combinations of salinity parameters are investigated to establish a hybrid MLP-GWO model that aims to reduce the error rate of the resulting forecasts of EC. To ascertain conclusive results, the MLP-GWO model is cross-validated with its classical counterpart without the add-in (i.e., GWO) optimizer, and the model error metrics are evaluated by coefficients of determination (R2), root mean squared error (RMSE) and relative root mean square error (RRMSE) in independent test data. For all tested predictive models, the performance of the MLP-GWO hybrid model is superior to a classical model, evidenced by larger R2 (~0.552–0.711 relative to ~0.430–0.711) and a lower RMSE and RRSE (~1.293–3.537 vs. 1.616–4.421 and ~3.736–9.899 vs. 4.613–12.133). The proposed GWO as an optimizer leads to a plausible improvement in an MLP model due to the most optimal weights attained in the neuronal layer that facilitates a robust feature extraction process to predict EC. As conclusion, the obtained results proved the effectiveness of the hybrid MLP-GWI model for predicting soil properties, which has potential implications in precision agriculture where salinity needs to be modeled for crop management practices.
•Prediction of soil electrical conductivity through a novel hybrid machine learning model•The effectiveness and generalization ability of the proposed model for different soil properties are reported.•Prediction accuracy for soil electrical conductivity is substantially improved.