Using neural networks to determine dust pollution near open-pit coal mining areas based on Earth remote sensing data

The article examines the use of neural networks for detecting dust pollution near open-pit coal mining areas based on remote sensing data. The study involved coal mining sites located in various regions of the Russian Federation. Satellite images from the Sentinel-2 mission served as the primary data source and were processed using Quantum GIS software. An algorithm for forming the training dataset was developed, utilizing the visible and near-infrared spectral bands from the satellite imagery. The mask creation technology in the developed algorithm is based on the Enhanced Coal Dust Index and its subsequent clustering. U-Net is used as a neural network model. The trained model was tested on a validation dataset. The recognition accuracy was 59.3% for the Intersection over Union metric, 78.9% for the Precision metric, 80.6% for the F1 metric, and 95.5% for the Accuracy metric. This level of accuracy is attributed to the limited volume of training data. The potential for improving accuracy through increasing the sample size in conjunction with optimizing the parameters of the neural network is discussed. The results obtained provide a basis for assessing the environmental impacts of coal mining activities and for developing measures to ensure ecological safety based on these findings.

1. Abramov N., Makarov D., Talalaev A., Fralenko V. Modern methods for intelligent processing of Earth remote sensing data. Program Systems: Theory and Applications. 2018;9(4):417–442. (In Russ.). http://doi.org/10.25209/2079-3316-2018-9-4-417-442

2. Yu H., Zahidi I. Environmental hazards posed by mine dust, and monitoring method of mine dust pollution using remote sensing technologies: An overview. Science of The Total Environment. 2023;864. https://doi.org/10.1016/j.scitotenv.2022.161135

3. Oparin V.N., Potapov V.P., Giniyatullina O.L., Andreeva N.V., Schastlivtsev E.L., Bykov A.A. Evaluation of dust pollution of air in Kuzbass coal-mining areas in winter by data of remote earth sensing. Journal of Mining Science. 2014;50(3):549–558. https://doi.org/10.1134/S1062739114030168

4. Nie X., Hu Z., Ruan M., Zhu Q., Sun H. Remote-Sensing Evaluation and Temporal and Spatial Change Detection of Ecological Environment Quality in Coal-Mining Areas. Remote Sensing. 2022;14(2). https://doi.org/10.3390/rs14020345

5. Moosina G.A., Ozhigin D.S., Ozhigina S.B. Enviromental monitoring on the bases of the pictures received by of pilotless flying devices. Interexpo GEO-Siberia. 2019;4(2):196–204. (In Russ.). https://doi.org/10.33764/2618-981X-2019-4-2-196-204

6. Savorskiy V.P., Loupian E.A., Gornyy V.I., Ermakov D.M., Panova O.Yu., Konstantinova A.M. Methods and information tools for analyzing remote sensing data to detect changes in vegetation caused by industrial waste and dumps. Sovremennye Problemy Distantsionnogo Zondirovaniya Zemli iz Kosmosa. 2019;16(6):31–47. (In Russ.). https://doi.org/10.21046/2070-7401-2019-16-6-31-47

7. Wang Y., Zhang D., Dai G. Classification of High Resolution Satellite Images Using Improved U–Net. International Journal of Applied Mathematics and Computer Science. 2020;30(3):399–413. https://doi.org/10.34768/amcs-2020-0030

8. Popov S.E., Potapov V.P., Zamaraev R.Yu. A software development approach for open pits monitoring based on Normalized Difference Activity Index and Sentinel-1 SAR data. Sovremennye Problemy Distantsionnogo Zondirovaniya Zemli iz Kosmosa. 2022;19(3):62–76. (In Russ.). https://doi.org/10.21046/2070-7401-2022-19-3-62-76

9. Hao L., Zhang Z., Yang X. Mine tailing extraction indexes and model using remote-sensing images in southeast Hubei Province. Environmental Earth Sciences. 2019;78(15):1–11. https://doi.org/10.1007/s12665-019-8439-1

10. He D., Le B.T., Xiao D., Mao Y., Shan F., Ha T.T.L. Coal mine area monitoring method by machine learning and multispectral remote sensing images. Infrared Physics & Technology. 2019;103. https://doi.org/10.1016/j.infrared.2019.103070