Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning

Abstract

This work explores the combination of free cloud computing, free open-source software, and deep learning methods to analyze a real, large-scale problem: the automatic country-wide identification and classification of surface mines and mining tailings dams in Brazil. Locations of officially registered mines and dams were obtained from the Brazilian government open data resource. Multispectral Sentinel-2 satellite imagery, obtained and processed at the Google Earth Engine platform, was used to train and test deep neural networks using the TensorFlow 2 application programming interface (API) and Google Colaboratory (Colab) platform. Fully convolutional neural networks were used in an innovative way to search for unregistered ore mines and tailing dams in large areas of the Brazilian territory. The efficacy of the approach is demonstrated by the discovery of 263 mines that do not have an official mining concession. This exploratory work highlights the potential of a set of new technologies, freely available, for the construction of low cost data science tools that have high social impact. At the same time, it discusses and seeks to suggest practical solutions for the complex and serious problem of illegal mining and the proliferation of tailings dams, which pose high risks to the population and the environment, especially in developing countries.

Google Earth Engine and Artificial Intelligence (AI): A Comprehensive Review

“…This in turn can make it easier for illegal mines to operate as legal mining operations with tailings dams are not heavily monitored. In order to keep track of mines and dams in Brazil, two different CNNs were used in [200] to first classify potential mining sites and then to classify perceived/potential environmental risk.…”

“…In order to keep track on mines and dams in Brazil, [200] used two different CNNs to first classify potential mining sites and then to classify its perceived/potential environmental risk. In this two-phase approach, the authors were able to identify 263 unregistered mines and designed the CNN to work on variable-sized RS images.…”

“…Compute limits [17,55,78,83,85,87,93,141,155,171,200,217,234,239,240]: Authors often ran into memory errors when analyzing too many field samples/observations. This also happened when the size of authors' input data was too large more generally and it was difficult to know beforehand if intermediate processing steps would trigger this error.…”

Watch Out for the Tailings Pond, a Sharp Edge Hanging over Our Heads: Lessons Learned and Perceptions from the Brumadinho Tailings Dam Failure Disaster

“…Therefore, it is urgent to find out the basic data of tailings ponds through a detailed investigation and real-time dynamic update and adjustment. Based on the above problems, remote sensing image interpretation [99], literatures and field investigation [100], telephone polls, etc. could be used to obtain the location of the tailings pond, year of construction, condition of use, storage of the pond, height of the tailings dam, type of tailings, and the geographic database could be used for the unified organization and management of the above date [101].…”

Incorporating Remote Sensing Techniques To The DRASTIC Index To Assess Groundwater Vulnerability In The Mining Area of the Rio Sonora Aquifer in Northwestern Mexico

“…Some of these features are clearly detectable with remote sensing techniques (Werner et al, 2019). Indeed, many efforts have been undertaken to detect mining wastes, its impacts and site remediation by remote sensing (Balaniuk et al, 2020;Buczyńska, 2020;Connette et al, 2016;Firozjaei et al, 2021;Hao et al, 2019;Khosravi et al, 2021;McKenna et al, 2020). Normalized difference vegetation index (NDVI) is mostly used in vegetation growth research (Wang et al, 2021), it is calculated as the level of greenness using imagery.…”