The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-3/W12-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W12-2020, 343–348, 2020
https://doi.org/10.5194/isprs-archives-XLII-3-W12-2020-343-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W12-2020, 343–348, 2020
https://doi.org/10.5194/isprs-archives-XLII-3-W12-2020-343-2020

  06 Nov 2020

06 Nov 2020

BRAZILDAM: A BENCHMARK DATASET FOR TAILINGS DAM DETECTION

E. Ferreira1, M. Brito1, R. Balaniuk2, M. S. Alvim1, and J. A. dos Santos1 E. Ferreira et al.
  • 1Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte, MG, Brazil
  • 2Universidade Católica de Brasília and Tribunal de Contas da União, Brasília, DF, Brazil

Keywords: Tailings Dam Detection, Remote Sensing, Deep Learning

Abstract. In this work we present BrazilDAM, a novel public dataset based on Sentinel-2 and Landsat-8 satellite images covering all tailings dams cataloged by the Brazilian National Mining Agency (ANM). The dataset was built using georeferenced images from 769 dams, recorded between 2016 and 2019. The time series were processed in order to produce cloud free images. The dams contain mining waste from different ore categories and have highly varying shapes, areas and volumes, making BrazilDAM particularly interesting and challenging to be used in machine learning benchmarks. The original catalog contains, besides the dam coordinates, information about: the main ore, constructive method, risk category, and associated potential damage. To evaluate BrazilDAM’s predictive potential we performed classification essays using state-of-the-art deep Convolutional Neural Network (CNNs). In the experiments, we achieved an average classification accuracy of 94.11% in tailing dam binary classification task. In addition, others four setups of experiments were made using the complementary information from the original catalog, exhaustively exploiting the capacity of the proposed dataset.