The Application of Artificial Neural Network Model to Predicting the Acid Mine Drainage from Long-Term Lab Scale Kinetic Test

TL;DR

This work addresses predicting acid mine drainage (AMD) from long-term lab-scale kinetic tests using artificial neural networks (ANNs). It compares feedforward, multivariate LSTM, and encoder–decoder LSTM architectures to forecast AMD indicators (pH, ORP, conductivity, TDS, SO4, Fe, Mn) from 83 weekly samples, after data preprocessing including anomaly detection, interpolation, and cosine time features. The encoder–decoder LSTM with a 7-day past window achieved the best performance, with NSE around $NSE \approx 0.99$ on training and validation, and enabled 60-day forecasts with low $MAE$/$MSE$ errors, demonstrating time-efficient, cost-effective AMD prediction compared to traditional methods. The results establish a foundation for applying ANN-based AMD forecasting in overburden management and post-mining planning.

Abstract

Acid mine drainage (AMD) is one of the common environmental problems in the coal mining industry that was formed by the oxidation of sulfide minerals in the overburden or waste rock. The prediction of acid generation through AMD is important to do in overburden management and planning the post-mining land use. One of the methods used to predict AMD is a lab-scale kinetic test to determine the rate of acid formation over time using representative samples in the field. However, this test requires a long-time procedure and large amount of chemical reagents lead to inefficient cost. On the other hand, there is potential for machine learning to learn the pattern behind the lab-scale kinetic test data. This study describes an approach to use artificial neural network (ANN) modeling to predict the result from lab-scale kinetic tests. Various ANN model is used based on 83 weeks experiments of lab-scale kinetic tests with 100\% potential acid-forming rock. The model approaches the monitoring of pH, ORP, conductivity, TDS, sulfate, and heavy metals (Fe and Mn). The overall Nash-Sutcliffe Efficiency (NSE) obtained in this study was 0.99 on training and validation data, indicating a strong correlation and accurate prediction compared to the actual lab-scale kinetic tests data. This show the ANN ability to learn patterns, trends, and seasonality from past data for accurate forecasting, thereby highlighting its significant contribution to solving AMD problems. This research is also expected to establish the foundation for a new approach to predict AMD, with time efficient, accurate, and cost-effectiveness in future applications.

Figures (8)

• Figure 1: (Left) Interconnected neurons. (Right) Feedforward network architecture.
• Figure 2: LSTM mechanism.
• Figure 3: Encoder-Decoder Architecture.
• Figure 4: Dataset visualization.
• Figure 5: Anomaly detection using Isolation Forest. Feature 1 (x-axis), Feature 2 (y-axis)