Self-potential inversion based on Attention U-Net deep learning network

Abstract

Landfill leaks pose a serious threat to environmental health, risking the contamination of both groundwater and soil resources. Accurate investigation of these sites is essential for implementing effective prevention and control measures. The self-potential (SP) stands out for its sensitivity to contamination plumes, offering a solution for monitoring and detecting the movement and seepage of subsurface pollutants. However, traditional SP inversion techniques heavily rely on precise subsurface resistivity information. In this study, we propose the Attention U-Net deep learning network for rapid SP inversion. By incorporating an attention mechanism, this algorithm effectively learns the relationship between array-style SP data and the location and extent of subsurface contaminated sources. We designed a synthetic landfill model with a heterogeneous resistivity structure to assess the performance of Attention U-Net deep learning network. Additionally, we conducted further validation using a laboratory model to assess its practical applicability. The results demonstrate that the algorithm is not solely dependent on resistivity information, enabling effective locating of the source distribution, even in models with intricate subsurface structures. Our work provides a promising tool for SP data processing, enhancing the applicability of this method in the field of near-subsurface environmental monitoring.

Keywords

self-potential / attention mechanism / U-Net deep learning network / inversion / landfill

References

[1] Arora T, Linde N, Revil A, et al. Non-intrusive characterization of the redox potential of landfill leachate plumes from self-potential data [J]. Journal of Contaminant Hydrology, 2007, 92(3): 274-292 4

[2] Naudet V, Revil A, Bottero J Y, et al. Relationship between self-potential (SP) signals and redox conditions in contaminated groundwater [J]. Geophysical Research Letters, 2003, 30(21): 2091

[3] Akinbile C O. Environmental impact of landfill on groundwater quality and agricultural soils in Nigeria [J]. Soil and Water Research, 2012, 7(1): 18-26

[4] Parvin F, Tareq S M. Impact of landfill leachate contamination on surface and groundwater of Bangladesh: A systematic review and possible public health risks assessment [J]. Applied Water Science, 2021, 11(6): 100

[5] Mao D, Revil A, Hort R D, et al. Resistivity and self-potential tomography applied to groundwater remediation and contaminant plumes: Sandbox and field experiments [J]. Journal of Hydrology, 2015, 530: 1-14

[6] Shao S, Yang X, Jia Chao. Combining multi-source data to evaluate the leakage pollution and remediation effects of landfill [J]. Journal of Hydrology, 2022, 610: 127889

[7] Atekwana E A, Sauck W A, Werkema D D. Investigations of geoelectrical signatures at a hydrocarbon contaminated site [J]. Journal of Applied Geophysics, 2000, 44(2): 167-180 3

[8] Gallas J D F, Taioli F, Malagutti Filho W. Induced polarization, resistivity, and self-potential: A case history of contamination evaluation due to landfill leakage [J]. Environmental Earth Sciences, 2011, 63(2): 251-261

[9] Barry A, Yameogo S, Ayach M, et al. Mapping contaminant plume at a landfill in a crystalline basement terrain in Ouagadougou, Burkina Faso, using self-potential geophysical technique [J]. Water, 2021, 13(9): 1212

[10] Cui Y-a, Zhu X-x, Wei W-s, et al. Dynamic imaging of metallic contamination plume based on self-potential data [J]. Transactions of Nonferrous Metals Society of China, 2017, 27(8): 1822-1830

[11] Touzani M, Mohsine I, Ouardi J, et al. Mapping the pollution plume using the self-potential geophysical method: Case of oum azza landfill, Rabat, Morocco [J]. Water, 2021, 13(7): 961

[12] Sato M, Mooney H. The electrochemical mechanism of sulfide self-potentials [J]. Geophysics, 1960, 25: 226-249

[13] Guo Y-j, Cui Y-a, Xie J, et al. Seepage detection in earth-filled dam from self-potential and electrical resistivity tomography [J]. Engineering Geology, 2022, 306: 106750

[14] Soueid Ahmed A, Revil A, Bolève A, et al. Determination of the permeability of seepage flow paths in dams from self-potential measurements [J]. Engineering Geology, 2020, 268: 105514

[15] Di Maio R, Rani P, Piegari E, et al. Self-potential data inversion through a Genetic-Price algorithm [J]. Computers & Geosciences, 2016, 94: 86-95

[16] Luo Y-j, Cui Y-a, Xie J, et al. Inversion of self-potential anomalies caused by simple polarized bodies based on particle swarm optimization [J]. Journal of Central South University, 2021, 28(6): 1797-1812

[17] Essa K S, Diab Z E, Mehanee S A. Self-potential data inversion utilizing the Bat optimizing algorithm (BOA) with various application cases [J]. Acta Geophysica, 2023, 71(2): 567-586

[18] Biswas A, Sharma S P. Resolution of multiple sheettype structures in self-potential measurement [J]. Journal of Earth System Science, 2014, 123(4): 809-825

[19] Xie J, Cui Y-a, Liu J-x, et al. A review on theory, modeling, inversion, and application of self-potential in marine mineral exploration [J]. Transactions of Nonferrous Metals Society of China, 2023, 33(4): 1214-1232

[20] Jardani A, Revil A, Bolève A, et al. Three-dimensional inversion of self-potential data used to constrain the pattern of groundwater flow in geothermal fields [J]. Journal of Geophysical Research (Solid Earth), 2008, 113(B9): B09204

[21] Minsley B J, Sogade J, Morgan F D. Three-dimensional source inversion of self-potential data [J]. Journal of Geophysical Research: Solid Earth, 2007, 112(B2): B02202

[22] Lecun Y, Bengio Y, Hinton G. Deep learning [J]. Nature, 2015, 521(7553): 436-444

[23] Zhang J-p, Xie Y-t, Wu Q, et al. Medical image classification using synergic deep learning [J]. Medical Image Analysis, 2019, 54: 10-19

[24] Ghosh S, Das N, Das I, et al. Understanding deep learning techniques for image segmentation [J]. ACM Computing Surveys, 2020, 52(4): 1-35

[25] Kersloot M G, van Putten F J P, Abu-Hanna A, et al. Natural language processing algorithms for mapping clinical text fragments onto ontology concepts: A systematic review and recommendations for future studies [J]. Journal of Biomedical Semantics, 2020, 11(1): 14

[26] Song Z-juan. English speech recognition based on deep learning with multiple features [J]. Computing, 2020, 102(3): 663-682

[27] Yu S-w, Ma J-wei. Deep learning for geophysics: Current and future trends [J]. Reviews of Geophysics, 2021, 59(3): e2021RG000742

[28] Zhang Z-h, Shi Z-y, Ma Ning. Deep learning inversion of Rayleigh dispersion curves [J]. Chinese Journal of Geophysics, 2022, 65(6): 2244-2259 (in Chinese)

[29] Chen H, Guo R-w, Liu J-x, et al. SEG 2019 Mathematical Geophysics: Traditional vs learning [C]. Workshop: Beijing, China, 2019 116-118

[30] Puzyrev V. Deep learning electromagnetic inversion with convolutional neural networks [J]. Geophysical Journal International, 2019, 218(2): 817-832

[31] Zhang L-p, Zhang L-f, Du Bo. Deep learning for remote sensing data: A technical tutorial on the state of the art [J]. IEEE Geoscience and Remote Sensing Magazine, 2016, 4(2): 22-40

[32] Kang X-y, Kokkinaki A, Kitanidis P K, et al. Hydrogeophysical characterization of nonstationary DNAPL source zones by integrating a convolutional variational autoencoder and ensemble smoother [J]. Water Resources Research, 2021, 57(2): e2020WR028538

[33] Liu B-c, Guo Q, Tang Y-t, et al. Deep learning inversion method of tunnel resistivity synthetic data based on modelling data [J]. Near Surface Geophysics, 2023, 21(4): 249-260

[34] Reichstein M, Camps-Valls G, Stevens B, et al. Deep learning and process understanding for data-driven Earth system science [J]. Nature, 2019, 566(7743): 195-204

[35] Wang P, Cui Y-a, Liu J-xin. Fluid discrimination based on inclusion-based method for tight sandstone reservoirs [J]. Surveys in Geophysics, 2022, 43(5): 1469-1496

[36] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation [M], 2015, Cham: Springer International Publishing 234-241

[37] Wu X-m, Yan S-s, Qi J, et al. Deep learning for characterizing paleokarst collapse features in 3-D seismic images [J]. Journal of Geophysical Research: Solid Earth, 2020, 125(9): e2020JB019685

[38] Li Y, Han L-g, Zhou S, et al. Gravity data density interface inversion based on U-Net deep learning network [J]. Chinese Journal of Geophysics, 2023, 66(1): 401-411 (in Chinese)

[39] OKTAY O, SCHLEMPER J, LE FOLGOC L, et al. Attention U-net: Learning where to look for the pancreas [EB/OL]. 2018: 1804.03999. https://arxiv.org/abs/1804.03999v3

[40] Linde N, Revil A. Inverting self-potential data for redox potentials of contaminant plumes [J]. Geophysical Research Letters, 2007, 34(14): L14302

[41] Revil A, Pezard P A, Glover P W J. Streaming potential in porous media: 1. Theory of the zeta potential [J]. Journal of Geophysical Research: Solid Earth, 1999, 104(B9): 20021-20031

[42] Revil A, Schwaeger H, Cathles L M III, et al. Streaming potential in porous media: 2. Theory and application to geothermal systems [J]. Journal of Geophysical Research: Solid Earth, 1999, 104(B9): 20033-20048

[43] Crespy A, Revil A, Linde N, et al. Detection and localization of hydromechanical disturbances in a sandbox using the self-potential method [J]. Journal of Geophysical Research: Solid Earth, 2008, 113(B1): H23C-1510

[44] Soueid Ahmed A, Jardani A, Revil A, et al. SP2DINV: A 2D forward and inverse code for streaming potential problems [J]. Computers & Geosciences, 2013, 59: 9-16

[45] Xie J, Cui Y-a, Zhang L-j, et al. 3D forward modeling of seepage self-potential using finite-infinite element coupling method [J]. Journal of Environmental and Engineering Geophysics, 2020, 25(3): 381-390

[46] Xie J, Cui Y-a, Zhang L-j, et al. Numerical modeling of biogeobattery system from microbial degradation of underground organic contaminant [J]. SN Applied Sciences, 2020, 2(2): 208

[47] Xie J, Cui Y-a, Fanidi M, et al. Numerical modeling of marine self-potential from a seafloor hydrothermal ore deposit [J]. Pure and Applied Geophysics, 2021, 178(5): 1731-1744

[48] Revil A, Mines C S O, Jardani A, et al. The self-potential method: theory and applications in environmental geosciences [M], 2013, Cambridge: Cambridge University Press

[49] KINGMA D P, BA J. Adam: A method for stochastic optimization [OJ/OL] arXiv, 2014: 1412.6980. DOI: https://doi.org/10.48550/arXiv.1412.6980.