Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning
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 registere...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/23/6936 |
| _version_ | 1797545775596568576 |
|---|---|
| author | Remis Balaniuk Olga Isupova Steven Reece |
| author_facet | Remis Balaniuk Olga Isupova Steven Reece |
| author_sort | Remis Balaniuk |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T14:19:48Z |
| format | Article |
| id | doaj.art-c4b79001057641dda95af36562292a54 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T14:19:48Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-c4b79001057641dda95af36562292a542023-11-20T23:29:30ZengMDPI AGSensors1424-82202020-12-012023693610.3390/s20236936Mining and Tailings Dam Detection in Satellite Imagery Using Deep LearningRemis Balaniuk0Olga Isupova1Steven Reece2Graduate Program in Governance, Technology and Innovation, Universidade Católica de Brasília, Brasília 71966-700, BrazilDepartment Computer Science, University of Bath, Bath BA2 7PB, UKDepartment Engineering Science, Oxford University, Oxford OX1 3PJ, UKThis 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.https://www.mdpi.com/1424-8220/20/23/6936tailings dam detectionsurface mines detectionenvironmental impact of miningremote sensingmachine learningdeep learning |
| spellingShingle | Remis Balaniuk Olga Isupova Steven Reece Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning Sensors tailings dam detection surface mines detection environmental impact of mining remote sensing machine learning deep learning |
| title | Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning |
| title_full | Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning |
| title_fullStr | Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning |
| title_full_unstemmed | Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning |
| title_short | Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning |
| title_sort | mining and tailings dam detection in satellite imagery using deep learning |
| topic | tailings dam detection surface mines detection environmental impact of mining remote sensing machine learning deep learning |
| url | https://www.mdpi.com/1424-8220/20/23/6936 |
| work_keys_str_mv | AT remisbalaniuk miningandtailingsdamdetectioninsatelliteimageryusingdeeplearning AT olgaisupova miningandtailingsdamdetectioninsatelliteimageryusingdeeplearning AT stevenreece miningandtailingsdamdetectioninsatelliteimageryusingdeeplearning |