Bin Liu

Bio: Bin Liu is an academic researcher from Shandong University. The author has contributed to research in topics: Inversion (meteorology) & Ground-penetrating radar. The author has an hindex of 13, co-authored 68 publications receiving 618 citations.

Deep-Learning Inversion of Seismic Data

Abstract: We propose a new method to tackle the mapping challenge from time-series data to spatial image in the field of seismic exploration, i.e., reconstructing the velocity model directly from seismic data by deep neural networks (DNNs). The conventional way of addressing this ill-posed inversion problem is through iterative algorithms, which suffer from poor nonlinear mapping and strong nonuniqueness. Other attempts may either import human intervention errors or underuse seismic data. The challenge for DNNs mainly lies in the weak spatial correspondence, the uncertain reflection-reception relationship between seismic data and velocity model, as well as the time-varying property of seismic data. To tackle these challenges, we propose end-to-end seismic inversion networks (SeisInvNets) with novel components to make the best use of all seismic data. Specifically, we start with every seismic trace and enhance it with its neighborhood information, its observation setup, and the global context of its corresponding seismic profile. From the enhanced seismic traces, the spatially aligned feature maps can be learned and further concatenated to reconstruct a velocity model. In general, we let every seismic trace contribute to the reconstruction of the whole velocity model by finding spatial correspondence. The proposed SeisInvNet consistently produces improvements over the baselines and achieves promising performance on our synthesized and proposed SeisInv data set according to various evaluation metrics. The inversion results are more consistent with the target from the aspects of velocity values, subsurface structures, and geological interfaces. Moreover, the mechanism and the generalization of the proposed method are discussed and verified. Nevertheless, the generalization of deep-learning-based inversion methods on real data is still challenging and considering physics may be one potential solution.

Deep Learning Inversion of Electrical Resistivity Data

Abstract: The inverse problem of electrical resistivity surveys (ERSs) is difficult because of its nonlinear and ill-posed nature. For this task, traditional linear inversion methods still face challenges such as suboptimal approximation and initial model selection. Inspired by the remarkable nonlinear mapping ability of deep learning approaches, in this article, we propose to build the mapping from apparent resistivity data (input) to resistivity model (output) directly by convolutional neural networks (CNNs). However, the vertically varying characteristic of patterns in the apparent resistivity data may cause ambiguity when using CNNs with the weight sharing and effective receptive field properties. To address the potential issue, we supply an additional tier feature map to CNNs to help those aware of the relationship between input and output. Based on the prevalent U-Net architecture, we design our network (ERSInvNet) that can be trained end-to-end and can reach a very fast inference speed during testing. We further introduce a depth weighting function and a smooth constraint into loss function to improve inversion accuracy for the deep region and suppress false anomalies. Six groups of experiments are considered to demonstrate the feasibility and efficiency of the proposed methods. According to the comprehensive qualitative analysis and quantitative comparison, ERSInvNet with tier feature map, smooth constraints, and depth weighting function together achieve the best performance.

Detecting and monitoring of water inrush in tunnels and coal mines using direct current resistivity method: A review

Abstract: Detecting, real-time monitoring and early warning of underground water-bearing structures are critically important issues in prevention and mitigation of water inrush hazards in underground engineering. Direct current (DC) resistivity method is a widely used method for routine detection, advanced detection and real-time monitoring of water-bearing structures, due to its high sensitivity to groundwater. In this study, the DC resistivity method applied to underground engineering is reviewed and discussed, including the observation mode, multiple inversions, and real-time monitoring. It is shown that a priori information constrained inversion is desirable to reduce the non-uniqueness of inversion, with which the accuracy of detection can be significantly improved. The focused resistivity method is prospective for advanced detection; with this method, the flanking interference can be reduced and the detection distance is increased subsequently. The time-lapse resistivity inversion method is suitable for the regions with continuous conductivity changes, and it can be used to monitor water inrush in those regions. Based on above-mentioned features of various methods in terms of benefits and limitations, we propose a three-dimensional (3D) induced polarization method characterized with multi-electrode array, and introduce it into tunnels and mines combining with real-time monitoring with time-lapse inversion and cross-hole resistivity method. At last, the prospective applications of DC resistivity method are discussed as follows: (1) available advanced detection technology and instrument in tunnel excavated by tunnel boring machine (TBM), (2) high-resolution detection method in holes, (3) four-dimensional (4D) monitoring technology for water inrush sources, and (4) estimation of water volume in water-bearing structures.

Deep-Learning Inversion of Seismic Data

Abstract: We propose a new method to tackle the mapping challenge from time-series data to spatial image in the field of seismic exploration, i.e., reconstructing the velocity model directly from seismic data by deep neural networks (DNNs). The conventional way of addressing this ill-posed inversion problem is through iterative algorithms, which suffer from poor nonlinear mapping and strong nonuniqueness. Other attempts may either import human intervention errors or underuse seismic data. The challenge for DNNs mainly lies in the weak spatial correspondence, the uncertain reflection–reception relationship between seismic data and velocity model, as well as the time-varying property of seismic data. To tackle these challenges, we propose end-to-end seismic inversion networks (SeisInvNets) with novel components to make the best use of all seismic data. Specifically, we start with every seismic trace and enhance it with its neighborhood information, its observation setup, and the global context of its corresponding seismic profile. From the enhanced seismic traces, the spatially aligned feature maps can be learned and further concatenated to reconstruct a velocity model. In general, we let every seismic trace contribute to the reconstruction of the whole velocity model by finding spatial correspondence. The proposed SeisInvNet consistently produces improvements over the baselines and achieves promising performance on our synthesized and proposed SeisInv data set according to various evaluation metrics. The inversion results are more consistent with the target from the aspects of velocity values, subsurface structures, and geological interfaces. Moreover, the mechanism and the generalization of the proposed method are discussed and verified. Nevertheless, the generalization of deep-learning-based inversion methods on real data is still challenging and considering physics may be one potential solution.

Deep-learning seismic full-waveform inversion for realistic structural models

Abstract: Velocity model inversion is one of the most important tasks in seismic exploration. Full-waveform inversion (FWI) can obtain the highest resolution in traditional velocity inversion methods...

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

A review of Ground Penetrating Radar application in civil engineering: A 30-year journey from Locating and Testing to Imaging and Diagnosis

Abstract: The GPR (Ground Penetrating Radar) conference in Hong Kong year 2016 marked the 30th anniversary of the initial meeting in Tifton, Georgia, USA on 1986. The conference has been being a bi-annual event and has been hosted by sixteen cities from four continents. Throughout these 30 years, researchers and practitioners witnessed the analog paper printout to digital era that enables very efficient collection, processing and 3D imaging of large amount of data required in GPR imaging in infrastructure. GPR has systematically progressed forward from “Locating and Testing” to “Imaging and Diagnosis” with the Holy Grail of ’Seeing the unseen’ becoming a reality. This paper reviews the latest development of the GPR’s primary infrastructure applications, namely buildings, pavements, bridges, tunnel liners, geotechnical and buried utilities. We review both the ability to assess structure as built character and the ability to indicate the state of deterioration. Finally, we outline the path to a more rigorous development in terms of standardization, accreditation, and procurement policy.

Application of deep learning algorithms in geotechnical engineering: a short critical review

Abstract: With the advent of big data era, deep learning (DL) has become an essential research subject in the field of artificial intelligence (AI). DL algorithms are characterized with powerful feature learning and expression capabilities compared with the traditional machine learning (ML) methods, which attracts worldwide researchers from different fields to its increasingly wide applications. Furthermore, in the field of geochnical engineering, DL has been widely adopted in various research topics, a comprehensive review summarizing its application is desirable. Consequently, this study presented the state of practice of DL in geotechnical engineering, and depicted the statistical trend of the published papers. Four major algorithms, including feedforward neural (FNN), recurrent neural network (RNN), convolutional neural network (CNN) and generative adversarial network (GAN) along with their geotechnical applications were elaborated. In addition, a thorough summary containing pubilished literatures, the corresponding reference cases, the adopted DL algorithms as well as the related geotechnical topics was compiled. Furthermore, the challenges and perspectives of future development of DL in geotechnical engineering were presented and discussed.