Prediction of ground subsidence due to underground mining through time using multilayer feed-forward artificial neural networks and back-propagation algorithm – case study at Mong Duong underground coal mine (Vietnam)

The paper is devoted to studying the possibility of using artificial neural networks (ANN) to estimate ground subsidence caused by underground mining. The experiments showed that the most suitable network structure is a network with three layers of perceptrons and four neurons in the hidden layer with the back propagation algorithm (BP) as a training algorithm. The subsidence observation data in the Mong Duong underground coal mine and other parameters, including: (1) the distance from the centre of the stope to the ground monitoring points; (2) the volume of mined-out space; (3) the positions of the ground points in the direction of the main cross-section of the trough; and (4) the time (presented by cycle number), were used as the input data for the ANN. The findings showed that the selected model was suitable for predicting subsidence along the main profile within the subsidence trough. The prediction accuracy depended on the number of cycles used for the network training as well as the time interval between the predicted cycle and the last cycle in the training dataset. When the number of monitoring cycles used for the network training was greater than eight, the largest values of RMS and MAE were less than 10 % compared to the actual maximum subsidence value for each cycle. If the network training was less than eight cycles, the results of prediction did not meet the accuracy requirements.

underground mining, subsidence trough, subsidence prediction, artificial neural network, back propagation

1. Long N. Q., Ahmad A., Cuong C. X., Canh L. Van. Designing observation lines: a case study of the G9 seam in the Mong Duong colliery. Journal of Mining and Earth Sciences. 2019;60(3):18–24. URL: https://www.researchgate.net/publication/333560617_Designing_observation_lines_a_case_study_of_the_G9_seam_in_the_Mong_Duong_colliery

2. Ambrožič T., Turk G. Prediction of subsidence due to underground mining by artificial neural networks. Computers and Geosciences. 2003;29(5):627–637. https://doi.org/10.1016/S0098-3004(03)00044-X

3. King M. A., Watson C. S. Long GPS coordinate time series: Multipath and geometry effects. Journal of Geophysical Research: Solid Earth. 2010;115(4):1–23. https://doi.org/10.1029/2009JB006543

4. Yang W., Xia X. Prediction of mining subsidence under thin bedrocks and thick unconsolidated layers based on field measurement and artificial neural networks. Computers and Geosciences. 2013;52:199–203. https://doi.org/10.1016/j.cageo.2012.10.017

5. Cong Khai P., Tran D. T., Nguyen V. H. GNSS/CORS-Based Technology for Real-Time Monitoring of Landslides on Waste Dump – A Case Study at the Deo Nai South Dump, Vietnam. Inżynieria Mineralna. 2020;1(2):181–191. https://doi.org/10.29227/IM-2020-02-23

6. Hejmanowski R., Witkowski W. T. Suitability assessment of artificial neural network to approximate surface subsidence due to rock mass drainage. Journal of Sustainable Mining. 2015;14(2):101–107. https://doi.org/10.1016/j.jsm.2015.08.014

7. Zhao K., Chen S. N. Study on artificial neural network method for ground subsidence prediction of metal mine. Procedia Earth and Planetary Science. 2011;2(1):177–182. https://doi.org/10.1016/j.proeps.2011.09.029

8. Kim K. D., Lee S., Oh H. J. Prediction of ground subsidence in Samcheok City, Korea using artificial neural networks and GIS. Environmental Geology. 2009;58(1):61–70. https://doi.org/10.1007/s00254-008-1492-9

9. Kim Y., Son M., Moon H. K., Lee S. A. A study on the development of an artificial neural network model for the prediction of ground subsidence over abandoned mines in Korea. Geosystem Engineering. 2017;20(3):163–171. https://doi.org/10.1080/12269328.2016.1254573

10. Lee S., Park I., Choi J. K. Spatial prediction of ground subsidence susceptibility using an artificial neural network. Environmental Management. 2012;49(2):347–358. https://doi.org/10.1007/s00267-011-9766-5

11. Hu Q., Deng X., Feng R., Li C., Wang X., Jiang T. Model for calculating the parameter of the Knothe time function based on angle of full subsidence. International Journal of Rock Mechanics and Mining Sciences. 2015;78:19–26. https://doi.org/10.1016/j.ijrmms.2015.04.022

12. Wang C., Ji H. Analysis on the improved time function model of surface subsidence. Electronic Journal of Geotechnical Engineering. 2015;19:615–627.

13. Zhanqiang C., Jinzhuang W. Study on time function of surface subsidence the improved Knothe time function. Chinese Journal of Rock Mechanics and Engineering. 2003;9.

14. Long N. Q., My V. C., Luyen B. K. Divergency verification of predicted values and monitored deformation indicators in specific condition of Thong Nhat underground coal mine (Vietnam). Geoinformatica Polonica. 2016;15:15–22. https://doi.org/10.4467/21995923GP.16.002.5479

15. Cui X., Miao X., Wang J., Yang S. et al. Improved prediction of differential subsidence caused by underground mining. International Journal of Rock Mechanics and Mining Sciences. 2000;37(4):615–627. https://doi.org/10.1016/S1365-1609(99)00125-2

16. Gonzalez-Nicieza C., Alvarez-Fernandez M. I., Menendez-Diaz A., Alvarez-Vigil A. E. The influence of time on subsidence in the Central Asturian Coalfield. Bulletin of Engineering Geology and the Environment. 2007;66(3):319–329. https://doi.org/10.1007/s10064-007-0085-2

17. Liu X., Wang J., Guo J., Yuan H., Li P. Time function of surface subsidence based on Harris model in mined-out area. International Journal of Mining Science and Technology. 2013;23(2):245–248. https://doi.org/10.1016/j.ijmst.2013.04.012

18. Haykin S. Neural Networks: A Comprehensive Foundation. 2nd Edition. 2004.

19. Rumelhart D. E., Hinton G. E., Williams R. J. Learning representations by back-propagating errors. Nature. 1986;323:533–536. https://doi.org/10.1038/323533a0

20. Long N. Q. A novel approach of determining the parameters of Asadi profiling function for predictiong ground subsidence due to inclied coal seam mining at Quang Ninh coal basin. Journal of Mining and Earth Sciences. 2020;61(2):86–95. https://doi.org/10.46326/JMES.2020.61(2).10

21. Atiya A. F. Learning algorithms for neural networks. California Institute of Technology, Pasadena, California. 1991. URL: https://thesis.library.caltech.edu/3725/1/Atiya_a_1991.pdf

22. Heaton J. Introduction to neural networks with Java. 2nd Edition. Heaton Research, Inc. 2008. 439 p.

23. Dayong Y., Jun S. Prediction method for evolutionary neural net of strata subsidence of rock Mass. Mining Safety & Environmental Protection. 2002;29(3):11–13. (In Chin.).