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.
Exploration
shirin Jahanmiri; Ali Aalianvari; Malihehe Abbaszadeh
Abstract
Groundwater inflow is a critical subject within the domains of hydrology, hydraulic engineering, hydrogeology, rock engineering, and related disciplines. Tunnels excavated below the groundwater table, in particular, face the inherent risk of groundwater seepage during both the excavation process and ...
Read More
Groundwater inflow is a critical subject within the domains of hydrology, hydraulic engineering, hydrogeology, rock engineering, and related disciplines. Tunnels excavated below the groundwater table, in particular, face the inherent risk of groundwater seepage during both the excavation process and subsequent operational phases. Groundwater inflows, often perceived as rare geological hazards, can induce instability in the surrounding rock formations, leading to severe consequences such as injuries, fatalities, and substantial financial expenditures. The primary objective of this research is to explore the application of machine learning techniques to identify the most accurate method of forecasting tunnel water seepage. The prediction of water loss into the tunnel during the forecasting phase employed a tree equation based on gene expression programming (GEP). These results were compared with those obtained from a hybrid model comprising particle swarm optimization (PSO) and artificial neural networks (ANN). The Whale Optimization Algorithm (WOA) was selected and developed during the optimization phase. Upon contrasting the aforementioned methods, the Whale Optimization Algorithm demonstrated superior performance, precisely forecasting the volume of water lost into the tunnel with a correlation coefficient of 0.99. This underscores the effectiveness of advanced optimization techniques in enhancing the accuracy of groundwater inflow predictions and mitigating potential risks associated with tunneling activities.
Exploration
Naman Chandel; Sushindra Kumar Gupta; Anand Kumar Ravi
Abstract
Groundwater is an essential resource for human survival, but its quality is often degraded by the human activities such as improper disposal of waste. Leachate generated from landfill sites can contaminate groundwater, causing severe environmental and health problems. Machine learning techniques can ...
Read More
Groundwater is an essential resource for human survival, but its quality is often degraded by the human activities such as improper disposal of waste. Leachate generated from landfill sites can contaminate groundwater, causing severe environmental and health problems. Machine learning techniques can be used to predict groundwater quality and leachate characteristics to manage this issue efficiently. This study proposes a machine learning-based model for the prediction of groundwater quality and leachate characteristics using the effective water quality index (EWQI). The leachate dataset used in this study was obtained from a landfill site, and the groundwater quality dataset was collected from literature review. The mean values of TDS, Ca, Mg, NO3-, and PO4- exceeded the prescribed limit for drinking water purposes. The proposed model utilizes a machine learning architecture based on a convolutional neural network (CNN) to extract relevant features from the input data. The extracted features are then fed into a fully connected network to estimate the EWQI of the input samples. The model, trained and tested on leachate and groundwater quality datasets, achieves a high accuracy and computational efficiency, aiding in predicting groundwater quality and leachate characteristics for waste management.
