Abstract
Mining operations cause negative changes in the environment. Therefore, such areas require constant monitoring, which can benefit from remote sensing data. In this article, research was carried out on the environmental impact of underground hard coal mining in the Bogdanka mine, located in the southeastern Poland. For this purpose, spectral indexes, satellite radar interferometry, Geographic Information System (GIS) tools and machine learning algorithms were utilized. Based on optical, radar, geological, hydrological and meteorological data, a spatial model was developed to determine the statistical significance of the selected factors’ individual impact on the occurrence of wetlands. Obtained results show that Normalized Difference Vegetation Index (NDVI) change, terrain height, groundwater level and terrain displacement had a considerable influence on the occurrence of wetlands in the research area. Moreover, the machine learning model developed using the Random Forest algorithm allowed for an efficient determination of potential flooding zones based on a set of spatial variables, correctly detecting 76% area of wetlands. Finally, the GWR (Geographically Weighted Regression (GWR) modelling enabled identification of local anomalies of selected factors’ influence on the occurrence of wetlands, which in turn helped to understand the causes of wetland formation.
Highlights
The mining industry, through the exploitation of raw materials, has a negative impact on the natural environment and urbanized areas [1,2,3]
Environmental protection is associated with the implementation of solutions in technological processes related to the operation, which will both minimize the undesirable impact on the environment and mitigate the negative effects through reclamation
Based on the Sentinel-1 Synthetic Aperture Radar (SAR) data, a Line-of-Sight displacement time-series was calculated using the Small Baseline InSAR technique for the study area, which showed how the terrain surface subsided over the analyzed period (2015–2019)
Summary
The mining industry, through the exploitation of raw materials, has a negative impact on the natural environment and urbanized areas [1,2,3]. Monitoring and research of the above effects arising in the environment of mining areas in large domains using field methods is difficult, depends on the space and location, consumes plenty of time and requires significant financial outlays This difficulty is answered by passive and active remote sensing from outer space, which gives the possibility of frequent observations of the Earth, and a Geographic Information System (GIS), which offers tools for various types of spatial analysis and graphic visualization of the results. The classification and regression machine learning algorithms [20,26,32,33,34] enable the appropriate adjustment and generalization of the dataset in the statistical analysis of dynamic phenomena These methods determine the statistically significant factors influencing the phenomenon studied, and make it possible to effectively forecast values of the dependent variable based on a set of independent variables. The above advantages of the use of remote sensing, GIS and machine learning, as well as satisfactory results obtained in the referenced papers, prompted the authors to combine all the techniques in the case study in this paper
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
