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; Majid Noorian-Bidgoli; Jamal Rostami
Abstract
Accurate prediction of rock brittleness is essential for tunneling, excavation, and rock engineering applications. This study develops and compares four intelligent predictive models, namely Gene Expression Programming (GEP), Artificial Rabbit Optimization–GEP (ARO-GEP), Grey Wolf Optimizer–GEP ...
Read More
Accurate prediction of rock brittleness is essential for tunneling, excavation, and rock engineering applications. This study develops and compares four intelligent predictive models, namely Gene Expression Programming (GEP), Artificial Rabbit Optimization–GEP (ARO-GEP), Grey Wolf Optimizer–GEP (GWO-GEP), and Crayfish Optimization Algorithm–GEP (COA-GEP), for estimating the rock brittleness index using uniaxial compressive strength (UCS) and tensile strength (TS). A comprehensive database containing 854 samples from 23 rock types was compiled from published literature. The dataset was divided into training (70%), validation (15%), and testing (15%) subsets. Model performance was evaluated using R², RMSE, MAE, and MAPE metrics. The results demonstrate that all models successfully captured the nonlinear relationship between UCS, TS, and rock brittleness. Among the investigated models, GEP achieved the highest predictive accuracy with a testing R² of 0.95 and RMSE of 1.24, followed closely by ARO-GEP and GWO-GEP. Sensitivity and SHAP analyses confirmed that UCS is the dominant parameter controlling rock brittleness, contributing approximately 60% of the predictive influence. The developed models provide practical tools for preliminary brittleness estimation in situations where direct laboratory determination is unavailable
