Dilution prediction in underground open stope mining using gene expression programming and backpropagation artificial neural network algorithms
Прогнозирование разубоживания при подземной разработке рудных тел камерной системой с открытым очистным пространством с использованием генетического программирования и алгоритмов искусственной нейронной сети с обратным распространением ошибки
2025-06-01
SCID: 54.1/hndwav4a
Discuss with AI
backpropagation artificial neural networkdilution predictiongene expression programminggeotechnical and design dataunderground open stope mining
Figures from the paper
Abstract (AI)
Unplanned dilution in underground mining is detrimental to the business, as imprecise dilution factors may impair production forecasts for existing operations or the economic evaluation and viability of brownfield expansions and greenfield projects. While high prediction accuracy of over 90% has been achieved using machine learning algorithms, particularly artificial neural networks (ANNs), the studies mostly predicted the overall dilution of stopes or included performance-subjective determinants, such as drill and blast factors. These factors compromise the models’ reproducibility for extensional application to cover new mining projects that do not have historical drill and blast input. To address this, the study explores gene expression programming (GEP) and ANN with backpropagation (BPNN) to predict dilution on a per-stope granularity based on geotechnical and design data. A 138-stope sample from a sublevel open stoping gold mine operation in Western Australia was used to generate predictive models. Model and infield results showed that the GEP model performed better, with a coefficient of determination, R 2 , of 0.740 with a root mean square error (RMSE) of 0.361 compared to BPNN's 0.681 and 0.409, respectively. Accordingly, the GEP model is recommended for dilution prediction for mine planning and production scheduling at the prescribed level of accuracy.
Key Findings
1
GEP outperformed BPNN, achieving R² = 0.740 and RMSE = 0.361 versus R² = 0.681 and RMSE = 0.409, respectively.
2
Gene expression programming (GEP) and backpropagation neural networks (BPNN) were developed using data from 138 stopes at a Western Australian sublevel open stoping gold mine.
3
Model and field results support using GEP for dilution prediction in mine planning and production scheduling at the reported accuracy level.
4
The study predicts dilution at individual-stope resolution using only geotechnical and design variables, avoiding drill-and-blast factors that limit reproducibility.
Research Object
Unplanned dilution of individual underground open stopes in a sublevel open stoping gold mine
Research Subject
Per-stope prediction accuracy of unplanned dilution using geotechnical and design factors, and comparison of GEP and BPNN performance
Publication Details
Publication Date
2025-06-01
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai3
Minimizing dilution in open stope mining with a focus on stope design and narrow vein longhole blasting2009
Unplanned dilution and ore loss prediction in longhole stoping mines via multiple regression and artificial neural network analyses2015
Prediction of dilution in sublevel stoping through machine learning algorithms2023