Exploration
Ali Aalianvari; Shirin Jahanmiri
Abstract
The increasing environmental risks associated with mining operations demand real-time, accurate risk assessment frameworks to prevent ecological damage and ensure operational safety. This study proposes an integrated real-time environmental risk assessment system utilizing multi-source sensor data and ...
Read More
The increasing environmental risks associated with mining operations demand real-time, accurate risk assessment frameworks to prevent ecological damage and ensure operational safety. This study proposes an integrated real-time environmental risk assessment system utilizing multi-source sensor data and advanced machine learning techniques. Sensor arrays monitoring parameters such as turbidity, pH, conductivity, temperature, and geotechnical vibrations provide continuous high-frequency data streams, which are preprocessed and analyzed using feature engineering methods to handle noise and heterogeneity. A comparative evaluation of several supervised and unsupervised models—namely XGBoost, Random Forest, Long Short-Term Memory (LSTM), Autoencoder, and Isolation Forest—was conducted. The XGBoost model outperformed others with an accuracy of 95%, precision of 94%, recall of 94%, F1-score of 94%, and an AUC-ROC of 0.97, while maintaining a low inference time of 18.7 ms per instance, suitable for real-time deployment. Autoencoder models achieved the highest anomaly detection rate of 92%, indicating their effectiveness in identifying rare environmental hazards. Feature importance analysis highlighted turbidity, pH, and conductivity as the most influential predictors, corroborating environmental science insights. This framework demonstrates a robust, scalable, and interpretable solution for mining environmental risk management, enabling prompt hazard detection and facilitating proactive interventions
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.
