Detection of Tailings Dams Using High-Resolution Satellite Imagery and a Single Shot Multibox Detector in the Jing-Jin-Ji Region, China

The timely and accurate mapping and monitoring of mine tailings dams is crucial to the improvement of management practices by decision makers and to the prevention of disasters caused by failures of these dams. Due to the complex topography, varying geomorphological characteristics, and the diversity of ore types and mining activities, as well as the range of scales and production processes involved, as they appear in remote sensing imagery, tailings dams vary in terms of their scale, color, shape, and surrounding background. The application of high-resolution satellite imagery for automatic detection of tailings dams at large spatial scales has been barely reported. In this study, a target detection method based on deep learning was developed for identifying the locations of tailings ponds and obtaining their geographical distribution from high-resolution satellite imagery automatically. Training samples were produced based on the characteristics of tailings ponds in satellite images. According to the sample characteristics, the Single Shot Multibox Detector (SSD) model was fine-tuned during model training. The results showed that a detection accuracy of 90.2% and a recall rate of 88.7% could be obtained. Based on the optimized SSD model, 2221 tailing ponds were extracted from Gaofen-1 high resolution imagery in the Jing–Jin–Ji region in northern China. In this region, the majority of tailings ponds are located at high altitudes in remote mountainous areas. At the city level, the tailings ponds were found to be located mainly in Chengde, Tangshan, and Zhangjiakou. The results prove that the deep learning method is very effective at detecting complex land-cover features from remote sensing images.

[1]  Carlos Roberto de Souza Filho,et al.  The 2019 Brumadinho tailings dam collapse: Possible cause and impacts of the worst human and environmental disaster in Brazil , 2020, Int. J. Appl. Earth Obs. Geoinformation.

[2]  Linlin Ge,et al.  Risk assessment for tailings dams in Brumadinho of Brazil using InSAR time series approach. , 2020, The Science of the total environment.

[3]  Wenwen Li,et al.  Automated terrain feature identification from remote sensing imagery: a deep learning approach , 2018, Int. J. Geogr. Inf. Sci..

[4]  Shixin Wang,et al.  Spatiotemporal Change and Landscape Pattern Variation of Eco-Environmental Quality in Jing-Jin-Ji Urban Agglomeration From 2001 to 2015 , 2020, IEEE Access.

[5]  Huadong Guo,et al.  Big Earth Data from space: a new engine for Earth science , 2016 .

[6]  Robert C. Bachus,et al.  Why coal ash and tailings dam disasters occur , 2019, Science.

[7]  Dongping Ming,et al.  CNN-based Land Cover Classification Combining Stratified Segmentation and Fusion of Point Cloud and Very High-Spatial Resolution Remote Sensing Image Data , 2019, Remote. Sens..

[8]  Daniele Perissin,et al.  Monitoring dam structural health from space: Insights from novel InSAR techniques and multi-parametric modeling applied to the Pertusillo dam Basilicata, Italy , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[9]  Song Zhang,et al.  Remote Sensing Extraction Method of Tailings Ponds in Ultra-Low-Grade Iron Mining Area Based on Spectral Characteristics and Texture Entropy , 2018, Entropy.

[10]  Flávio Fonseca do Carmo,et al.  Fundão tailings dam failures: the environment tragedy of the largest technological disaster of Brazilian mining in global context , 2017 .

[11]  Peter Christian Hackspacher,et al.  The environmental impacts of one of the largest tailing dam failures worldwide , 2017, Scientific Reports.

[12]  Zhao-Liang Li,et al.  Generation of continuous surface soil moisture dataset using combined optical and thermal infrared images , 2017 .

[13]  Jon Atli Benediktsson,et al.  Remote Sensing Big Data Classification with High Performance Distributed Deep Learning , 2019, Remote Sensing.

[14]  Xiongwei Wu,et al.  Recent Advances in Deep Learning for Object Detection , 2019, Neurocomputing.

[15]  Xiang Zhang,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[16]  Chenxi Liu,et al.  A Modeling Method for Automatic Extraction of Offshore Aquaculture Zones Based on Semantic Segmentation , 2020, ISPRS Int. J. Geo Inf..

[17]  Wei Zhang,et al.  Earth and Rock-Filled Dam Monitoring by High-Resolution X-Band Interferometry: Gongming Dam Case Study , 2019, Remote. Sens..

[18]  Craig Goff,et al.  The potential to reduce the risks posed by tailings dams using satellite-based information , 2019, International Journal of Disaster Risk Reduction.

[19]  A. Müller,et al.  Pyrite mine waste and water mapping using Hymap and Hyperion hyperspectral data , 2012, Environmental Earth Sciences.

[20]  Jing Liu,et al.  A Bayesian Network-based risk dynamic simulation model for accidental water pollution discharge of mine tailings ponds at watershed-scale. , 2019, Journal of environmental management.

[21]  Yu Guangmin,et al.  REVIEW OF NEW PROGRESS IN TAILING DAM SAFETY IN FOREIGN RESEARCH AND CURRENT STATE WITH DEVELOPMENT TRENT IN CHINA , 2014 .

[22]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[23]  Lianru Gao,et al.  Automatic Detection of Track and Fields in China from High-Resolution Satellite Images Using Multi-Scale-Fused Single Shot MultiBox Detector , 2019, Remote. Sens..

[24]  Lina Hao,et al.  Mine tailing extraction indexes and model using remote-sensing images in southeast Hubei Province , 2019, Environmental Earth Sciences.

[25]  Huadong Guo,et al.  Assessment of urban environmental change using multi-source remote sensing time series (2000-2016): A comparative analysis in selected megacities in Eurasia. , 2019, The Science of the total environment.

[26]  D. Kemp,et al.  Catastrophic tailings dam failures and disaster risk disclosure , 2020 .

[27]  Jon Atli Benediktsson,et al.  Remotely sensed big data: evolution in model development for information extraction [point of view] , 2019, Proc. IEEE.

[28]  Andy Fourie,et al.  Catastrophe revisited – disastrous flow failures of mine and municipal solid waste , 2005 .

[29]  Huadong Guo,et al.  Urban sprawl in provincial capital cities in China: evidence from multi-temporal urban land products using Landsat data. , 2019, Science bulletin.

[30]  Hao Jiang,et al.  Insulator Detection in Aerial Images for Transmission Line Inspection Using Single Shot Multibox Detector , 2019, IEEE Access.

[31]  Fei Cao,et al.  The application of remote sensing in the environmental risk monitoring of tailings pond: a case study in Zhangjiakou area of China , 2012, Remote Sensing.

[32]  Huadong Guo,et al.  Monitoring bidecadal development of urban agglomeration with remote sensing images in the Jing-Jin-Tang area, China , 2014 .

[33]  Lianru Gao,et al.  A New Low-Rank Representation Based Hyperspectral Image Denoising Method for Mineral Mapping , 2017, Remote. Sens..

[34]  Ling Wan,et al.  Design, construction and management of tailings storage facilities for surface disposal in China: case studies of failures , 2013, Waste management & research : the journal of the International Solid Wastes and Public Cleansing Association, ISWA.

[35]  Pinliang Dong,et al.  Automated measurement of sand dune migration using multi-temporal lidar data and GIS , 2015 .

[36]  John Rogan,et al.  Resource extraction and infrastructure threaten forest cover and community rights , 2018, Proceedings of the National Academy of Sciences.

[37]  Shuhuan Wang,et al.  DF-SSD: An Improved SSD Object Detection Algorithm Based on DenseNet and Feature Fusion , 2020, IEEE Access.

[38]  Gavin M. Mudd,et al.  Global-scale remote sensing of mine areas and analysis of factors explaining their extent , 2020 .

[39]  Jing Cao,et al.  A Comprehensive Review on Reasons for Tailings Dam Failures Based on Case History , 2019, Advances in Civil Engineering.

[40]  Maria Alfredsson,et al.  Mine tailings dams: Characteristics, failure, environmental impacts, and remediation , 2014 .

[41]  Stefan Sommer,et al.  Use of airborne hyperspectral data to estimate residual heavy metal contamination and acidification potential in the Guadiamar floodplain Andalusia, Spain after the Aznacollar mining accident , 2004, SPIE Remote Sensing.

[42]  Remis Balaniuk,et al.  Mining and Tailings Dam Detection in Satellite Imagery Using Deep Learning , 2020, Sensors.

[43]  Alfonso Fernández-Manso,et al.  Evaluation of potential of multiple endmember spectral mixture analysis (MESMA) for surface coal mining affected area mapping in different world forest ecosystems , 2012 .

[44]  Lifu Zhang,et al.  Progress in Hyperspectral Remote Sensing Science and Technology in China Over the Past Three Decades , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[45]  Zhong Lu,et al.  Consolidation settlement of Salt Lake County tailings impoundment revealed by time-series InSAR observations from multiple radar satellites , 2017 .

[46]  Manny Mathuthu,et al.  An Assessment of Radiological Hazards from Gold Mine Tailings in the Province of Gauteng in South Africa , 2016, International journal of environmental research and public health.