Exploration
Shirin Jahanmirir; Ali Aalianvari; Hossein Ebrahimpour-Komleh
Abstract
This paper introduces the Human Mental Search (HMS) algorithm as a novel and superior optimization technique for predicting groundwater seepage in tunnel environments. Traditional methods for predicting such seepage often struggle with the complexities of subterranean water flow, particularly in heterogeneous ...
Read More
This paper introduces the Human Mental Search (HMS) algorithm as a novel and superior optimization technique for predicting groundwater seepage in tunnel environments. Traditional methods for predicting such seepage often struggle with the complexities of subterranean water flow, particularly in heterogeneous geological conditions, and while machine learning approaches have offered improvements, they often require significant computational resources. The HMS algorithm, inspired by human cognitive processes, employs memory recall, adaptive clustering, and strategic selection to efficiently refine solutions. Our results demonstrate that HMS significantly outperforms established algorithms in predicting groundwater seepage, achieving an R² value of 0.9988, a Mean Squared Error (MSE) of 0.0002, and a Root Mean Squared Error (RMSE) of 0.0137. In comparison, the Whale Optimization Algorithm (WOA) achieved an R² of 0.9951 with much higher MSE and RMSE, and other methods, like Genetic Programming and ANN-PSO, show higher error values. The HMS algorithm also showed a Variance Accounted for (VAF) of 99.88% and a Mean Absolute Error (MAE) of 0.0041, further validating its high predictive accuracy. This study highlights the HMS algorithm’s superior performance and computational efficiency for optimizing groundwater seepage predictions, positioning it as a powerful tool for geotechnical engineering applications, including real-time monitoring.
