Früher|Nächster

Deep learning semantic segmentation supported risk monitoring of tailings reservoir basin

  • role： First author第一作者
  • Affiliation：

    Henan Polytechnic University, School of Surveying and Mapping Land Information Engineering, Jiaozuo 454003, China

    Henan Poly-technic University, Key Laboratory of State Bureau of Surveying and mapping of mine spatial information technology, Jiaozuo 454003, China

  • Email：liupei@hpu.edu.cn
  • Introduction：刘培，1985年生，男，副教授，研究方向为遥感信息挖掘与信息处理。E-mail：liupei@hpu.edu.cn
LIU Pei12,  
  • Affiliation：

    Henan Polytechnic University, School of Surveying and Mapping Land Information Engineering, Jiaozuo 454003, China

    Shaoxing Natural Resources Survey Institute of Zhejiang Province, Shaoxing 312000, China

GU Can13,  
  • Affiliation：

    Aerospace Information Research Insitute, Chinese Academy of Science, Beijing 100094, China

LI Qingting4,  
  • Affiliation：

    Henan Polytechnic University, School of Surveying and Mapping Land Information Engineering, Jiaozuo 454003, China

ZHANG Hebing1,  
  • Affiliation：

    Henan Polytechnic University, School of Surveying and Mapping Land Information Engineering, Jiaozuo 454003, China

HAN Ruimei1,  
  • role： Corresponding author通信作者
  • Affiliation：

    Aerospace Information Research Insitute, Chinese Academy of Science, Beijing 100094, China

  • Email：chenzc@radi.ac.cn
  • Introduction：陈正超，1976年生，男，研究员，研究方向为遥感器辐射定标和遥感大数据处理与资源环境应用。E-mail： chenzc@radi.ac.cn
CHEN Zhengchao4*

Resümee

Tailings reservoir is a necessary facility for mining activity, and it also causes danger to surrounding environment. . Watershed risk of the tailings reservoir in Chicheng was monitored and analyzed using GF-1 high-resolution remotely sensed data with the help of multiscale fusion and deep learning method, as well as the support of Remote Sensing (RS) and Geographic Information System (GIS) technology for a comprehensive and detailed identification and extraction of the risk information of the tailings reservoir and to study the dam-break path of the tailings reservoir in watershed and the risk to land surface over mining area.In this research, a sample set library for target detection was constructed by analyzing texture, hue, shape, and size of the tailings reservoir on the remotely sensed data. Subsequently, an improved multi-scale fusion algorithm (e.g., Multi_Scale Feature Map_SSD (MSF_SSD)) was constructed by adding a deconvolution module and a connection module to the original single shot multiBox detector (SSD). Next, the Pyramid Scene Parsing network (PSPnet) algorithm was selected to achieve the structure of the tailings reservoir on the basis of the target detection results. The internal structure of the tailings reservoir was obtained. With the help of RS and GIS technology, the surface of upstream catchment and the possible danger runoff were extracted, and dam-break path of the tailings reservoir is simulated on the basis of the arc hydro model. Finally, the range area affected by the dam-break were obtained by constructing the buffer zone of the dam-break path.The research results shown that the dam-break path of the tailings reservoir in Chicheng is generally from west to east and from north to south, and the total area affected by the dam-break was 480 km2. The combination analysis with land use/ cover classification indicated that forest land was 176.52 km2, farm land was 175.52 km2, urban land was 43.74 km2, rural construction land was 2.47 km2, water body was 17.72 km2, grassland was 3.60 km2, and pasture was 1.22 km2.The sample library constructed using GF-1 remotely sensed data and Google Earth 16 level image can provide the basis for the automatic recognition of tailings reservoir with deep learning framework. With the help of improved MSF_SSD and PSPnet algorithm, the semantic segmentation accuracy of the test area for pixel accuracy, mean IoU, F1 score, and mean F1 score is 0.98, 0.97, 0.99, 0.98, respectively. A comprehensive analysis of tailings reservoir dam-break range and possible damage to land surface types are performed with the help of hydrological analysis method and random forest classification results. Outcomes of this research can be used to analyze the impact area caused by dam-break, promote the capabilities of risk management and emergency response of tailings reservoir, and provide fundamental theories for decisions making in relevant departments.

Schlüsselwort

tailings reservoir;SSD multi-scale fusion;PSPnet deep network;Arc Hydro model;risk analysis

References

  1. 1.
    Breiman L. 2001. Random forests. Machine Learning, 45(1): 5-32
  2. 2.
    Buselli G and Lu K L. 2001. Groundwater contamination monitoring with multichannel electrical and electromagnetic methods. Journal of Applied Geophysics, 48(1): 11-23
  3. 3.
    Chen L and Ames D P. 2006. “Open hydro”-An open source GIS implementation of the arc hydro data model//Science, Ecology, Management, Policy. Eccles Conference Center: [s.n.]
  4. 4.
    Fang X J. 2013. Environmental Risk Assessment of Metal Tailing Ponds in Daye Based on RS and GIS-a Case Study on Tongshankou Copper Tailing Pond. Wuhan: China University of Geosciences
  5. 5.
    Fang X J, Ding L and Zhang Z. 2013. An analysis of distribution characteristics and environmental effect of small tailing ponds in Chengui town, Daye. Remote Sensing for Land and Resources, 25(1): 155-159.
  6. 6.
    Gao Y Z, Chu Y and Liang W. 2015. Remote sensing monitoring and analysis of tailings ponds in the ore concentration area of Heilongjiang Province. Remote Sensing for Land and Resources, 27(1): 160-163
  7. 7.
    Gislason P O, Benediktsson J A and Sveinsson J R. 2006. Random Forests for land cover classification. Pattern Recognition Letters, 27(4): 294-300
  8. 8.
    Jia H J, Wang L J, Ma G C, Tang Y and Jin X. 2017. Study on safety production red line of tailing pond. Industrial Safety and Environmental Protection, 43(10): 55-58
  9. 9.
    Jing R, Gong Z N, Zhu W D, Guan H L, Zhao W J and Zhang T. 2020. Extraction of buildings from remote sensing imagery based on multi-scale SLIC-GMRF and FCNSVM. Journal of Remote Sensing, 24(1): 11-26
  10. 10.
    Li C K, Zhang D C, Tao J J and Wang F. 2012. Information extraction and its application of urban road networks based on Google images. Remote Sensing Technology and Application, 27(1): 100-105
  11. 11.
    Li S Y, Chen J F, Lin M Z and Wang F. 2016. Exploration on the teaching reform of “GIS spatial analysis principles and methods”. The Science Education Article Collects, (1): 60-61, 64
  12. 12.
    Li X S, Ji C C, Zeng Y, Yan N N and Wu B F. 2009. Dynamics of water and soil loss based on remote sensing and GIS: a case study in Chicheng country of Hebei province. Chinese Journal of Ecology, 28(9): 1723-1729
  13. 13.
    Liu J F, Zhang X N, Geng Q Z and Tang Z W. 2006. Method for generation of river and lake buffer regions based on DEM. Journal of Hohai University (Natural Sciences), 34(1): 25-27
  14. 14.
    Luo J L, Niu Y L and Sun H G. 2006. Safety assessment application of circular arc Swedish method in tailing pond. Journal of Safety Science and Technology, 2(3): 84-87
  15. 15.
    吕杰. 2014. 尾矿库遥感监测技术研究与应用——以河北省尾矿库为例. 北京: 中国地质大学(北京).
  16. 16.
    Shakesby R A and Whitlow J R. 1991. Failure of a mine waste dump in Zimbabwe: causes and consequences. Environmental Geology and Water Sciences, 18(2): 143-153
  17. 17.
    Shelhamer E, Long J and Darrell T. 2017. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4): 640-651
  18. 18.
    Wei Y, Xu K L, Zheng X and Guo L J. 2010. The characteristics and problems of tailing reservoir in China//Proceedings of 2010 (Shenyang) International Colloquium on Safety Science and Technology. Shenyang: Northeastern University: 512-515
  19. 19.
    Wu F Y, Wang X, Ding J W, Du P J and Tan K. 2020. Improved cascade forest deep learning model for hyperspectral imagery classification. Journal of Remote Sensing, 24(4): 439-453
  20. 20.
    Wu W W, Gong Y T and Qin X S. 2011. Analysis on existing problems of small tailings pond and safety precautions. Nonferrous Metals (Mining Section), 63(5): 49-51
  21. 21.
    Yang X H, Huang J, Tian L, Liu Z and Han L. 2015. A discussion on comprehensive governance of mine environment based on high resolution remote sensing data: a case of Maoniuping REE deposit, Mianning County. Remote Sensing for Land and Resources, 27(4): 115-121
  22. 22.
    Yu Y D, Lin G L, Chen B F, Tang X X and Zhang J L. 2014. Application of GNSS technology in deformation monitoring of tailings dam body. Bulletin of Surveying and Mapping, (S1): 60-62
  23. 23.
    Zhang D J, Lei X J and Zhang X J. 2003. Stability analysis and treatment research of Longxingzhai impounding dam. Rock and Soil Mechanics, 24(4): 670-672
  24. 24.
    Zhang H. 2011. GIS-Based Risk Analysis on Tailings Dam Failures. Tianjin: Nankai University
  25. 25.
    Zhang X N, Qi J and Zhang L. 2000. Method of deriving drainage network. Journal of Hohai University, 28(1): 26-31
  26. 26.
    Zhao H S, Shi J P, Qi X J, Wang X G and Jia J Y. 2017. Pyramid scene parsing network//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE: 2881-2890
  27. 27.
    Zhao L L and Xiao R L. 2013. Environmental risk assessment based on RS and GIS: a case study of Wengfu tailing pond. Geomatics World, 20(4): 70-77
  28. 28.
    Zhao Q B. 2018. Research on Improved Algorithm of Object Detection Based on SSD. Nanning: Guangxi University
  29. 29.
    Zhu S R and Wu H Y. 2006. Introduction of ERSI arc hydro data model. Geomatics and Spatial Information Technology, 29(5): 87-90

Lesen Sie die ganze Passage

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website