/mining-discovery-with-deep-learning

Mining and tailings dam detection in satellite imagery using deep learning

Primary LanguageJupyter Notebook

mining-discovery-with-deep-learning

Mining and Tailings Dam Detection In Satellite ImageryUsing Deep Learning

Authors:

  • Remis Balaniuk: Universidade Catolica de Brasılia and Tribunal de Contas da Uniao, Brasılia, Brazil;remisb@tcu.gov.br,
  • Olga Isupova: University of Bath, Bath, UK; oi260@bath.ac.uk
  • Steven Reece: Dept. Engineering Science, Oxford University, Oxford, UK; reece@robots.ox.ac.uk

This work explores the combination of free cloud computing, free open-sourcesoftware, and deep learning methods to analyse 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 atthe Google Earth Engine platform, was used to train and test deep neural networks using the TensorFlow 2 API and Google Colab platform. FullyConvolutional 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 im-pact. 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 environ-ment, especially in developing countries.

When using the material provided here, please reference the following publication: Balaniuk, R.; Isupova, O.; Reece, S. Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning. Sensors 2020, 20, 6936. https://doi.org/10.3390/s20236936

Open access at: https://www.mdpi.com/1424-8220/20/23/6936#cite