A site pollution nonlinear inversion method based on deep convolutional neural network
NAI Chang-xin1,2, SUN Xiao-chen3, XU Ya2, LIU Jia-lin1, DONG Lu2, LIU Yu-qiang2
1. School of Information and Electronic Engineering, Shandong Technology and Business University, Shandong 264005, China;
2. State Key Laboratory of Environmental Benchmarks and Risk Assessment, Research Institute of Solid Waste Management, Chinese Research Academy of Environment Science, Beijing 100012, China;
3. School of Computer Science and Technology, Shandong Technology and Business University, Shandong 264005, China
A novel nonlinear method named E-ConvNet was proposed for ERT inversion of contaminated sites, which combined Sobel edge detection operator with deep convolutional neural network algorithm (CNN). The edge features of apparent resistivity data in contaminated sites were extracted by the Sobel operator as the prior information feed into CNN, which improved computational efficiency and identification accuracy of E-ConvNet. The performance of E-ConvNet algorithm were testedon five theoretical model data (single anomaly, double anomalies, and layered structures with double anomalies) and field data, and then compared with results from the traditional Least Squares (LS) algorithm. The results showed that E-ConvNet can accurately identify the area, location and resistance of pollution, and its accuracy and computing efficiency were better than those of LS. The single anomaly recognition accuracy of E-ConvNet and LS were 81.8%~84.9% and 9.6%~36.2%, respectively; the multiple anomalies recognition accuracy of E-ConvNet and LS were 68.6%~84.4% and 2.8%~27.6%, respectively; the computing time of E-ConvNetis about 112~190ms,and the computing time of LS was 6000~7000ms. Therefore, E-ConvNet proposed in this study can accurately and efficiently inversed the polluted areas in the investigation of contaminated sites and provide technical support for the follow-up assessment/restoration work.
能昌信, 孙晓晨, 徐亚, 刘家琳, 董路, 刘玉强. 基于深度卷积神经网络的场地污染非线性反演方法[J]. 中国环境科学, 2019, 39(12): 5162-5172.
NAI Chang-xin, SUN Xiao-chen, XU Ya, LIU Jia-lin, DONG Lu, LIU Yu-qiang. A site pollution nonlinear inversion method based on deep convolutional neural network. CHINA ENVIRONMENTAL SCIENCECE, 2019, 39(12): 5162-5172.
徐亚,刘玉强,胡立堂,等.填埋场井筒效应及其对污染监测井监测效果的影响[J]. 中国环境科学, 2018,38(8):3113-3120. Xu Y, Liu Y Q, Hu L T, et al. Wellbore effect and its influence on contamination monitor well-a case study on groundwater monitor well around landfill[J]. China Environmental Science, 2018,38(8):3113-3120.
[2]
王泽亚,徐亚,董路,等.金属离子污染砂土复电阻率的时变特征及形成机制[J]. 中国环境科学, 2019,39(3):1147-1153. Wang Z Y, Xu Y, Dong L, et al. Complex resistivity of cationic metal contaminated sandy soils:Time-varying characteristics and formation mechanism[J]. China Environmental Science, 2019,39(3):1147-1153.
[3]
徐亚,朱雪梅,刘玉强,等.基于随机-模糊耦合的污染场地健康风险评价及案例[J]. 中国环境科学, 2014,34(10):2692-2700. Xu Y, Zhu X M, Liu Y Q, et al. A fuzzy-stochastic integratedmodel of contaminated site risk assessment model and case study[J]. China Environmental Science, 2014,34(10):2692-2700.
[4]
王玉玲,王蒙,闫岩,等.基于聚类算法的ERT污染区域识别方法[J]. 中国环境科学, 2019,39(3):1315-1322. Wang Y L, Wang M, Yan Y, et al. An ERT pollution area identification method based on clustering algorithm[J]. China Environmental Science, 2019,39(3):1315-1322.
[5]
李金铭.地电场与电法勘探[M]. 北京:地质出版社, 2005:136-144. Li J M. Geoelectric field and electrical exploration[M]. Beijing:Geological Publishing House, 2005:136-144.
[6]
Shima H. 2-D and 3-D resistivity image reconstruction using crosshole data[J]. Geophysics, 1992,57(10):1270−1281.
[7]
Loke M H. Least-squares deconvolution of apparent resistivity pseudosections[J]. Geophysics, 1995,60(6):1682−1690.
[8]
Li Y G, Oldenburg D W. Approximate inverse mappings in DC resistivity problems[J]. Geophysical Journal International, 1992, 109(2):343-362.
[9]
Jari K P, Ville K, Erkki S, Marko V. Statistical inversion and Monte Carlo sampling methods in electrical impedance tomography[J]. Inverse Problems, 2000,16(5):1487-1522.
[10]
El-Qady G, Ushijima K. Inversion of DC resistivity data using neural networks[J]. Geophysical Prospecting, 2001,49:417-430.
[11]
Shaw R, Srivastava S. Particle swarm optimization:A new tool to invert geophysical data[J]. Geophysics, 2007,72(2):75-83.
[12]
Sharma S P. VFSARES-a very fast simulated annealing FORTRAN program for interpretation of 1-D DC resistivity sounding data from various electrode arrays[J]. Computers & Geosciences, 2012,42:177-188.
[13]
Liu B, Li S, Nie L, et al. 3D resistivity inversion using an improved genetic algorithm based on control method of mutation direction[J]. Journal of Applied Geophysics, 2012,87:1-8.
[14]
Calderón-Macías C, Sen M K, Stoffa P L. Artificial neural networks for parameter estimation in geophysics[J]. Geophysical Prospecting, 2001,48(1):21−47.
[15]
徐海浪,吴小平.电阻率二维神经网络反演[J]. 地球物理学报, 2006,49(2):584-589. Xu H L, Wu X P. 2-D resistivity using the neural network method[J]. Chinese Journal of Geophysics, 2006,49(2):584-589.
[16]
江沸菠,戴前伟,董莉.基于剪枝贝叶斯神经网络的电阻率成像非线性反演[J]. 应用地球物理, 2016,13(2):267-278. Jiang F B, Dai Q W, Dong L. Nonlinear inversion of electrical resistivity imaging using pruning Bayesian neural networks[J]. Applied Geophysics, 2016,13(2):267-278.
[17]
戴前伟,江沸菠.基于混沌振荡PSOBP算法的电阻率层析成像非线性反演[J]. 中国有色金属学报, 2013,23(10):2897-2904. Dai Q W, Jiang F B. Nonlinear inversion for electrical resistivity tomography based on chaotic oscillation PSO-BP algorithm[J]. 2013,23(10):2897-2904.
[18]
Neyamadpour A, Abdullah W A T, Taib S. Inversion of quasi-3D DC resistivity imaging data using artificial neural networks[J]. Journal of Earth System Science, 2010,119(1):27-40.
[19]
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.
[20]
Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012,25(2):1097-1105.
[21]
Burger H C, Schuler C J, Harmeling S. Image denoising:Can plain neural networks compete with BM3D?[C]//IEEE Conference on Computer Vision and Pattern Recognition, 2012:2392-2399.
[22]
Kyong H J, McCann M T, Froustey E, et al. Deep convolutional neural network for inverse problems in imaging[J]. IEEE Trans Image Process, 2017,26(9):4509-4522.
[23]
伍广明,陈奇,Ryosuke S,等.基于U型卷积神经网络的航空影像建筑物检测[J]. 测绘学报, 2018,47(6):864-872. Wu G M, Chen Q, Ryosuke S, et al. High precision building detection from aerial imagery using a U-Net like convolutional architecture[J]. Acta Geodaetica et Cartographica Sinica, 2018,47(6):864-872.
[24]
Jeong C, Yang H S, Moon K. A novel approach for detecting the horizon using a convolutional neural network and multi-scale edge detection[J]. Multidimensional Systems and Signal Processing, 2018:1-18.
[25]
Wang W, Lu X B, Song J J, et al. A two-column convolutional neural network for facial point detection[C]//International Conference on Progress in Informatics and Computing, 2016.
[26]
Vardhana M, Arunkumar N, Lasrado S, et al. Convolutional neural network for bio-medical image segmentation with hardware acceleration[J]. Cognitive Systems Research, 2018,50:10-14.
[27]
Kanopoulos N, Vasanthavada N, Baker R L. Design of an image edge detection filter using the Sobel operator[J]. IEEE Journal of Solid-State Circuits, 1988,23(2):358-367.
[28]
Craig W B, Stanley H W. Three-dimensional mise-à-la-masse modeling applied to mapping fracture zones[J]. Geophysics, 1986, 51(1):98-113.
[29]
毕卓,韩冰.抗噪Roberts算子边沿检测器[J]. 计算机技术与发展, 2016,23(6):258-261. Bi Z, Han B. Anti-noise roberts edge detector[J]. Computer Technology and Development, 2016,23(6):258-261.
[30]
Perona P, Malik J. Scale-space and edge detection using anisotropic diffusion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990,12(7):629-639.
[31]
Abdou I E, Pratt W K. Quantitative design and evaluation of enhancement/thresholding edge detectors[J]. Proceedings of the IEEE, 1979,67(5):753-763.
[32]
Peil T, Malah D. A study of edge detection algorithms[J]. Computer Graphics and Image Processing, 1982,20(1):1-21.
[33]
Butler S L, Sinha G. Forward modeling of applied geophysics methods using comsol and comparison with analytical and laboratory analog models[J]. Computers & Geosciences, 2012,42:168-176.
[34]
肖宏跃,雷宛.地电学教程[M]. 北京:地质出版社, 2008:98-163. Xiao H Y, Lei W. Geoelectrical tutorial[M]. Beijing:Geological Publishing House, 2008:150-163.
