Determining the Features Influencing the Structural Stability of Soils of Arid Regions Using a Hybrid GA-ANN Algorithm

Aggregate stability of soils informs about their relative strengths against erosive forces and mechanical disruption. In this research, a hybrid Genetic Algorithm-Artificial Neural Network method was used to select the best subset of features affecting the mean weight diameter (MWD. In addition, the ability of ANNs and multiple linear regression (MLR) for quantifying the relationship between the MWD index and some soil properties was assessed. After the modeling process, the importance of the selected features in relation to spatial variability of aggregate stability was investigated. In order to prepare a suitable data set; MWD index and some soil features were measured in collected soils from 90 sampling points. Feature selection results showed that six soil features including clay, sand, organic matter, calcium carbonate, electrical conductivity, and sodium adsorption ratio had the greatest effect on the aggregates stability of the studied soils. According to the MWD modeling results, the obtained values of coefficient of determination (R2), mean absolute error percentage (MAEP), and root mean square error (RMSE) for the ANN model performance were 0.94, 21.39, and 0.07% respectively. These findings indicated that the developed ANN model was able to predict the complex and nonlinear relationships between the MWD index and the soil properties selected by the algorithm. Based on the sensitivity analysis results, calcium carbonate equivalent, sand particles, and organic matter were identified as key factors in estimating aggregate stability. Overall, this study provides a robust framework for the prediction of aggregate stability and identifying the most determinant parameters influencing it in arid and semi-arid soils that could be applied to other regions with similar challenges.