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

基于深度学习Attention U-Net自然电场反演方法

作　　者：GUO You-jun CUI Yi-an CHEN Hang XIE Jing ZHANG Chi LIU Jian-xin 郭友军;崔益安;陈杭;谢静;张弛;柳建新(School of Geosciences and Info-physics,Central South University,Changsha 410083,China;Department of Geosciences,Boise State University,Boise 83725,USA;Key Laboratory of Non-ferrous and Geological Hazard Detection,Changsha 410083,China;Department of Meteorology and Geophysics,University of Vienna,Vienna 1090,Austria;School of Earth and Space Sciences,Peking University,Beijing 100871,China)

机构地区：[1]School of Geosciences and Info-physics,Central South University,Changsha 410083,China [2]Department of Geosciences,Boise State University,Boise 83725,USA [3]Key Laboratory of Non-ferrous and Geological Hazard Detection,Changsha 410083,China [4]Department of Meteorology and Geophysics,University of Vienna,Vienna 1090,Austria [5]School of Earth and Space Sciences,Peking University,Beijing 100871,China

出　　处：《Journal of Central South University》2024年第9期3156-3167,共12页中南大学学报（英文版）

基　　金：Projects(42174170,41874145,72088101)supported by the National Natural Science Foundation of China;Project(CX20200228)supported by the Hunan Provincial Innovation Foundation for Postgraduate,China。

摘　　要：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.垃圾填埋场渗漏会造成对周边地下水和土壤造成严重污染,对其进行精确探查是实现有效防治的关键。自然电场法对污染物具有高敏感性,可高效应用于监测、检测地下污染物渗漏运移情况。然而,传统的自然电场反演方法严重依赖准确的地电模型电阻率信息。本文基于深度学习,引入注意力机制,设计了一种Attention U-Net算法可以快速反演自然电场阵列式数据,高效识别地下异常源位置。该算法采用U型网络为基础结构,将自然电场反演地下异常源的问题转化为类似图像分割问题。通过具有复杂电阻率分布的垃圾填埋场模型的数值模拟数据,测试了算法的有效性,并进一步采用物理实验实测数据验证了方法的实用性。结果表明,Attention U-Net算法不依赖地下电阻率信息,在复杂地电结构分布的情况下能够高效反演获取异常位置及范围。该方法为自然电场法的数据处理提供一种新的策略,并提高其在环境污染监测领域的适用性。

关 键 词：SELF-POTENTIAL attention mechanism U-Net deep learning network INVERSION landfill 

分 类 号：X830[环境科学与工程—环境工程]