Please wait a minute...
Remote Sensing for Natural Resources    2021, Vol. 33 Issue (4) : 252-257     DOI: 10.6046/zrzyyg.2021017
Recognition of the spatial scopes of tailing ponds based on U-Net and GF-6 images
ZHANG Chengye1,2(), XING Jianghe1, LI Jun1,2(), SANG Xiao1
1. College of Geoscience and Surveying Engineering, China University of Mining and Technology-Beijing, Beijing 100083, China
2. State Key Laboratory of Coal Resources and Safe Mining, China University of Mining and Technology-Beijing, Beijing 100083, China
Download: PDF(3498 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    

It is of great significance for the monitoring and supervision of tailing ponds in China to realize the rapid recognition of the spatial scopes of tailing ponds using the remote sensing technique. Based on the U-Net framework, this paper proposes a deep learning-based intelligent recognition method of the spatial ranges of tailing ponds using the remote sensing technique. The method proposed was verified in Honghe Hani and Yi Autonomous Prefecture in Yunnan Province using Chinese GF-6 satellite images. The results show that the precision, recall rate, and F1-score of the method were 0.874, 0.843, and 0.858, respectively, which were significantly better than those obtained using the methods of random forest, support vector machine, and maximum likelihood. Furthermore, the time consumption of the new method kept the same order of magnitude as that of the three methods. Therefore, the method proposed in this study has a broad application prospect in the rapid monitoring of the spatial scopes of tailing ponds in China.

Keywords deep neural network      GF-6 satellite      tailing pond      recognition based on remote sensing images     
ZTFLH:  TP79  
Corresponding Authors: LI Jun     E-mail:;
Issue Date: 23 December 2021
E-mail this article
E-mail Alert
Articles by authors
Chengye ZHANG
Jianghe XING
Jun LI
Cite this article:   
Chengye ZHANG,Jianghe XING,Jun LI, et al. Recognition of the spatial scopes of tailing ponds based on U-Net and GF-6 images[J]. Remote Sensing for Natural Resources, 2021, 33(4): 252-257.
URL:     OR
Fig.1  The location and GF-6 remotely-sensed image combined with B3(R),B2(G), B1(B) of the study area
波段名称 波长/nm 空间分辨率/m 幅宽/km
全色波段 450~900 2 90
多光谱波段 450~520 8 90
绿 520~590 8 90
630~690 8 90
近红外 770~890 8 90
Tab.1  The details of the panchromatic and multispectral images acquired by GF-6
Fig.2  The technical roadmap of this paper
Fig.3  Examples of the tailing ponds in the study area
Fig.4  Network structure of spatial range recognition of tailing ponds using GF-6 satellite image
分类器 参数设置
深度学习网络 学习率: 0.000 01,学习率衰减方式: CosineAnnealingLR,优化器: Adam
随机森林 决策树个数: 100,决策树最大深度: 15
支持向量机 惩罚系数: 100,核函数: poly,正则化参数: L2正则化
最大似然法 高斯贝叶斯分类器
Tab.2  Parameter setting of four recognition algorithms
Fig.5  The result of recognition of tailing ponds and the real boundary as reference
方法 真实结果/
识别结果/像元 Precision Recall F1-
尾矿库 非尾矿库
本文方法 尾矿库 384 533 71 585 0.874 0.843 0.858
非尾矿库 55 402 15 217 120
随机森林 尾矿库 363 962 92 156 0.815 0.798 0.806
非尾矿库 82 570 15 189 952
支持向量机 尾矿库 330 776 125 342 0.805 0.725 0.763
非尾矿库 79 948 15 192 574
最大似然法 尾矿库 312 467 143 651 0.794 0.685 0.735
非尾矿库 80 981 15 191 541
Tab.3  The comparision of the accuracy of different methods
类别 配置
CPU Intel(R) Xeon(R) Gold5118 CPU @2.30 GHz
显卡 NVIDIA GeForce RTX 2080 Ti
操作系统 Windows10
Tab.4  Details about computer configuration
方法 运行时间/s
本文方法 20
随机森林 35
支持向量机 65
最大似然法 13
Tab.5  Run time of different methods
[1] 沃廷枢, 汪贻水, 肖垂斌, 等. 尾矿库手册[M]. 北京: 冶金工业出版社, 2013:1-13.
[1] Wo T S, Wang Y S, Xiao C B, et al. Manual of tailings pond[M]. Beijing: Metallurgical Industry Press, 2013:1-13.
[2] Rotta S, Henrique L, Alcantara E, et al. The 2019 Brumadinho tailings dam collapse:Possible cause and impacts of the worst human and environmental disaster in Brazil[J]. International Journal of Applied Earth Observation and Geoinformation, 2020,90:102119.
doi: 10.1016/j.jag.2020.102119 url:
[3] 郝利娜, 张志, 何文熹, 等. 鄂东南尾矿库高分辨率遥感图像识别因子研究[J]. 国土资源遥感, 2012,24(3):154-158.doi: 10.6046/gtzyyg.2012.03.27.
doi: 10.6046/gtzyyg.2012.03.27
[3] Hao L N, Zhang Z, He W X, et al. Tailings reservoir recognition factors of the high resolution remote sensing image in southeastern of Hubei[J]. Remote Sensing for Land and Resources, 2012,24(3):154-158.doi: 10.6046/gtzyyg.2012.03.27.
doi: 10.6046/gtzyyg.2012.03.27
[4] Ma B D, Chen Y T, Zhang S, et al. Remote sensing extraction method of tailings ponds in ultra-low-grade iron mining area based on spectral characteristics and texture entropy[J]. Entropy, 2018,20(5):345.
doi: 10.3390/e20050345 url:
[5] Hao L N, Zhang Z, Yang X X. Mine tailing extraction indexes and model using remote-sensing images in southeast Hubei Province[J]. Environmental Earth Sciences, 2019,78(15):493.
doi: 10.1007/s12665-019-8439-1 url:
[6] 曹兰杰, 吴兵, 汪金花, 等. 面向对象的高分一号铁尾矿遥感信息提取与分析[J]. 测绘与空间地理信息, 2019,42(4):98-101.
[6] Cao L J, Wu B, Wang J H, et al. Object-oriented information extraction and analysis of the iron tailings with GF-1 remote sensing image[J]. Geomatics & Spatial Information Technology, 2019,42(4):98-101.
[7] Fuentes M, Millard K, Laurin E. Big geospatial data analysis for Canada’s air pollutant emissions inventory (APEI):Using google earth engine to estimate particulate matter from exposed mine disturbance areas[J]. Giscience & Remote Sensing, 2019,57(2):245-257.
[8] 王立廷. 支持向量机结合面向对象提取尾矿库的应用研究[D]. 北京:中国地质大学(北京), 2018.
[8] Wang L T. Research on application of support vector machine combined with object oriented method for tailing pond extraction[D]. Beijing:China University of Geosciences (Beijing), 2018.
[9] Orimoloye I R, Ololade O O. Spatial evaluation of land-use dynamics in gold mining area using remote sensing and GIS technology[J]. International Journal of Environmental Science and Technology, 2020,17(11):4465-4480.
doi: 10.1007/s13762-020-02789-8 url:
[10] 闫凯, 沈汀, 陈正超, 等. 基于深度学习的SSD模型尾矿库自动提取[J]. 中国科学院大学学报, 2020,37(3):360-367.
[10] Yan K, Shen T, Chen Z C, et al. Automatic extraction of tailing pond based on SSD of deep learning[J]. Journal of University of Chinese Academy of Sciences, 2020,37(3):360-367.
[11] Li Q T, Chen Z C, Zhang B, et al. Detection of tailings dams using high-resolution satellite imagery and a single shot multibox detector in the Jing-Jin-Ji region,China[J]. Remote Sensing, 2020,12(16).
[12] 王建伟, 刘红军, 郭科. 基于粗糙集理论的矿产资源地质调查综合评价模型及其应用——以滇东南地区为例[J]. 资源科学, 2014,36(8):1608-1617.
[12] Wang J W, Liu H J, Guo K. Mineral resource geological survey evaluation model based on a rough set theory:A case study in southeastern Yunnan[J]. Resources Science, 2014,36(8):1608-1617.
[13] 潘含江. 我国典型金属矿山尾矿地球化学特征及资源环境评价[D]. 北京:中国地质大学(北京), 2019.
[13] Pan H J. Geochemical characteristics and resource environment assessment of tailings from typical metal mines in China[D]. Beijing:China University of Geosciences(Beijing), 2019.
[14] Yang A X, Zhong B, Hu L F, et al. Radiometric cross-calibration of the wide field view camera onboard GaoFen-6 in multispectral bands[J]. Remote Sensing, 2020,12(6):1037.
doi: 10.3390/rs12061037 url:
[15] 杨可明. 遥感原理与应用[M]. 北京: 中国矿业大学出版社, 2016:231-234.
[15] Yang K M. Remote sensing principle and applications[M]. Beijing: China University of Mining and Technology Press, 2016:231-234.
[16] Ronneberger O, Fischer P, Brox T. U-Net:Convolutional networks for biomedical image segmentation[C]//Medical image Computing and Computer-Assisted Intervention, 2015:234-241.
[17] Deepsense A. Deep learning for satellite imagery via image segmentation[EB/OL].(2017-4-12)[2021-01-12].
[18] Zhu X L, Cheng Z Y, Wang S, et al. Coronary angiography image segmentation based on PSPNet[J]. Computer Methods and Programs in Biomedicine, 2020,200(4):105897.
doi: 10.1016/j.cmpb.2020.105897 url:
[19] Diaz V, Jairo J, Vlaminck M, et al. Solar panel detection within complex backgrounds using thermal images acquired by UAVs[J]. Sensors, 2020,20(21):6219.
doi: 10.3390/s20216219 url:
[20] Zhang L X, Shen J K, Zhu B J. A research on an improved Unet-based concrete crack detection algorithm[J]. Structural Health Monitoring-An International Journal, 2020: 1475921720940068.
[1] XU Qingyun, LI Ying, TAN Jing, ZHANG Zhe. Information extraction method of mangrove forests based on GF-6 data[J]. Remote Sensing for Natural Resources, 2023, 35(1): 41-48.
[2] Zhiwei LIN, Weihao TU, Jiahang HUANG, Qilu DING, Zhengwen ZHOU, Jinfu LIU. Tree species recognition of UAV aerial images based on FC-DenseNet[J]. Remote Sensing for Land & Resources, 2019, 31(3): 225-233.
[3] FANG Xuejuan, DING Lei, ZHANG Zhi. An analysis of distribution characteristics and environmental effect of small tailing ponds in Chengui town, Daye[J]. REMOTE SENSING FOR LAND & RESOURCES, 2013, 25(1): 155-159.
Full text



Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech