Predicting and Forecasting Mine Water Parameters Using a Hybrid Intelligent System

More, Kagiso Samuel; Wolkersdorfer, Christian

doi:10.1007/s11269-022-03177-2

Cited by 8 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The key was to establish a relationship model between shallow water level depth reduction and the shape, size, and quantity of mining units. Clarifying the effects of mining units on shallow water overlays was fundamental [29][30][31]. A leak model of a shallow aquifer in the mining area was constructed, the leakage mechanism of shallow groundwater leakage in the mining area was analyzed, and the water head changes in the shallow aquifer under the disturbance of exploitation were quantified.…”

Section: Discussionmentioning

confidence: 99%

Quantitative Evaluation Method and Response Mechanism of Shallow Groundwater in Multi-Mine Mining of “Soil–Rock” Composite Water-Resisting Strata

Zhang,

Zhang

et al. 2024

Water

View full text Add to dashboard Cite

The sustainability of shallow groundwater systems, pivotal to maintaining ecosystem equilibrium and facilitating the sustainable development of mine sites, is the core of various dynamic indicators in response to mining activity and mining area planning. This study quantitatively evaluates the impact of mining activities on shallow groundwater systems at the orefield scale, taking the equivalent permeability coefficient (EPC) of “Soil–Rock” composite water-resisting strata and the response mechanism of shallow groundwater in multi-mine mining as the entry points. A modified six-step evaluation method for the response mechanism of shallow groundwater in multi-mine mining is proposed using mathematical statistics, numerical simulation, and theoretical analysis methods. The method is used to evaluate the sustainability of the shallow water system in the Yushen mining area, to study the distribution characteristics of the water resource carrying capacity (WRCC) in different mining areas of the Yushen area, and to analyze the number of mines allowed to be mined under geological conditions with a WRCC of more than moderate bearing capacity. The results show that when the mining area of a mine in the Yushen area is set to 1 × 108, 7.5 × 107, 5 × 107, and 2.5 × 107 m2, as the mining area of the designed mine decreases, the area bearing surplus gradually increases, with values of 1.70 × 109, 1.98 × 109, 2.28 × 109, and 2.58 × 109 m2. The number of mines allowed to be mined under geological conditions with a WRCC above moderate capacity is 20, 31, 51, and 112, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

Quantitative Evaluation Method and Response Mechanism of Shallow Groundwater in Multi-Mine Mining of “Soil–Rock” Composite Water-Resisting Strata

Zhang,

Zhang

et al. 2024

Water

View full text Add to dashboard Cite

show abstract

“…Integration of advanced sensors, artificial intelligence, predictive machine-learning (ML) models and automation can advance the technologies [88,89], optimising the efficiency of resource-recovery processes. For example, predictive ML models can be used to forecast the chemistry of wastewater which will be pumped from the main source to the treatment plant (e.g., [89,90]) and membranes can be developed based on this information. The combination of efficient membranes with freeze technology can ensure that wastewater is treated effectively and efficiently.…”

Section: Future Prospectsmentioning

confidence: 99%

Indirect Freeze Crystallization—An Emerging Technology for Valuable Resource Recovery from Wastewater

More,

Mahlangu

2024

Minerals

Self Cite

View full text Add to dashboard Cite

This paper explores the efficiency and potential of indirect freeze crystallization (IFC) as a valuable resource-recovery technology in wastewater treatment, particularly focusing on acid mine water and hazardous material wastewater-treatment plants. Wastewater treatment poses challenges to recovering valuable resources effectively, enforcing the need for sustainable and resource-efficient technologies like freeze crystallization. Through a thorough examination of IFC principles and mechanisms, this paper aims to highlight its applications, advantages, and limitations. The investigation includes a comprehensive literature review and detailed methodology from one of the IFC pilot plants, as well as a critical analysis of the environmental and economic implications of IFC. By addressing scaling challenges in reverse osmosis and proposing an environmentally friendly brine disposal method through IFC, this paper contributes to reducing the environmental footprint associated with wastewater treatment. Additionally, this paper highlights the importance of extracting valuable resources from highly saline water and emphasises the potential economic and environmental benefits of resource recovery, particularly focusing on the promising technology of IFC.

show abstract

“…In northern Tunisia RF, SVM and MLP were used to predict toxic heavy metal content and the behaviour of mine waste in relation to the dissolution of iron-bearing minerals and found that heavy metal concentrations and sulphate dissolution increase as the oxidation of sulphate-bearing minerals such as pyrite increases (Trifi et al, 2022 ). RF, XG and ANN were used to create a web application that predicted electrical conductivity and pH in Johannesburg, South Africa in order to improve forecasting procedures that ensure the smooth operation of AMD treatment plants (More & Wolkersdorfer, 2022 ). In one study in the Philippines, a neural network with particle swarm optimization was used to improve mapping prediction capabilities for spatial maps to predict ground water quality (De Jesus et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

Comparison of individual and ensemble machine learning models for prediction of sulphate levels in untreated and treated Acid Mine Drainage

Hasrod,

Nuapia,

Tutu

2024

Environ Monit Assess

View full text Add to dashboard Cite

Machine learning was used to provide data for further evaluation of potential extraction of octathiocane (S8), a commercially useful by-product, from Acid Mine Drainage (AMD) by predicting sulphate levels in an AMD water quality dataset. Individual ML regressor models, namely: Linear Regression (LR), Least Absolute Shrinkage and Selection Operator (LASSO), Ridge (RD), Elastic Net (EN), K-Nearest Neighbours (KNN), Support Vector Regression (SVR), Decision Tree (DT), Extreme Gradient Boosting (XGBoost), Random Forest (RF), Multi-Layer Perceptron Artificial Neural Network (MLP) and Stacking Ensemble (SE-ML) combinations of these models were successfully used to predict sulphate levels. A SE-ML regressor trained on untreated AMD which stacked seven of the best-performing individual models and fed them to a LR meta-learner model was found to be the best-performing model with a Mean Squared Error (MSE) of 0.000011, Mean Absolute Error (MAE) of 0.002617 and R2 of 0.9997. Temperature (°C), Total Dissolved Solids (mg/L) and, importantly, iron (mg/L) were highly correlated to sulphate (mg/L) with iron showing a strong positive linear correlation that indicated dissolved products from pyrite oxidation. Ensemble learning (bagging, boosting and stacking) outperformed individual methods due to their combined predictive accuracies. Surprisingly, when comparing SE-ML that combined all models with SE-ML that combined only the best-performing models, there was only a slight difference in model accuracies which indicated that including bad-performing models in the stack had no adverse effect on its predictive performance.

show abstract

Predicting and Forecasting Mine Water Parameters Using a Hybrid Intelligent System

Cited by 8 publications

References 22 publications

Quantitative Evaluation Method and Response Mechanism of Shallow Groundwater in Multi-Mine Mining of “Soil–Rock” Composite Water-Resisting Strata

Quantitative Evaluation Method and Response Mechanism of Shallow Groundwater in Multi-Mine Mining of “Soil–Rock” Composite Water-Resisting Strata

Indirect Freeze Crystallization—An Emerging Technology for Valuable Resource Recovery from Wastewater

Comparison of individual and ensemble machine learning models for prediction of sulphate levels in untreated and treated Acid Mine Drainage

Contact Info

Product

Resources

About