Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Ou...Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.展开更多
We review three derivative-free methods developed for uncertainty estimation of non-linear error propagation, namely, MC(Monte Carlo), SUT(scaled unscented transformation), and SI(sterling interpolation). In order to ...We review three derivative-free methods developed for uncertainty estimation of non-linear error propagation, namely, MC(Monte Carlo), SUT(scaled unscented transformation), and SI(sterling interpolation). In order to avoid preset parameters like as these three methods need, we introduce a new method to uncertainty estimation for the first time, namely, SCR(spherical cubature rule), which is no need for setting parameters. By theoretical derivation, we prove that the precision of uncertainty obtained by SCR can reach second-order. We conduct four synthetic experiments, for the first two experiments, the results obtained by SCR are consistent with the other three methods with optimal setting parameters, but SCR is easier to operate than other three methods, which verifies the superiority of SCR in calculating the uncertainty. For the third experiment, real-time calculation is required, so the MC is hardly feasible. For the forth experiment, the SCR is applied to the inversion of seismic fault parameter which is a common problem in geophysics, and we study the sensitivity of surface displacements to fault parameters with errors. Our results show that the uncertainty of the surface displacements is the magnitude of ±10 mm when the fault length contains a variance of 0.01 km^(2).展开更多
Based on the seismic source model in the Fifth Generation Seismic Ground Motion Parameters Zonation Map of China(FGSGMPZMC),a new seismic fault model,the new zonation of seismic risk areas(SRAs),and the estimation of ...Based on the seismic source model in the Fifth Generation Seismic Ground Motion Parameters Zonation Map of China(FGSGMPZMC),a new seismic fault model,the new zonation of seismic risk areas(SRAs),and the estimation of seismicity rates for 2021-2030,this study constructed a new time-dependent seismic source model of China’s mainland,and used the probabilistic seismic hazard analysis method to calculate seismic hazard by selecting the ground motion models(GMMs)suitable for seismic sources in China.It also provided the probabilities of China’s mainland being affected by earthquakes of modified Mercalli intensity(MMI)Ⅵ,Ⅶ,Ⅷ,Ⅸ,and≥Ⅹin 2021-2030.The spatial pattern of seismic hazards presented in this article is similar to the pattern of the FGSGMPZMC,but shows more details.The seismic hazards in this study are higher than those in the FGSGMPZMC in the SRAs and fault zones that can produce large earthquakes.This indicates that the seismic source model construction in this study is scientific and reasonable.There are certain similarities between the results in this study and those of Rong et al.(2020)and Feng et al.(2020),but also disparities for specific sites due to differences in seismic source models,seismicity parameters,and GMMs.The results of seismic hazard may serve as parameter input for future seismic risk assessments.The hazard results can also be used as a basis for the formulation of earthquake prevention and mitigation policies for China’s mainland.展开更多
Buried water pipelines are vulnerable to fail or break due to excessive loading or ground displacements.Accurate evaluation of pipe performance and serviceability relies on the proper understanding of pipe-soil intera...Buried water pipelines are vulnerable to fail or break due to excessive loading or ground displacements.Accurate evaluation of pipe performance and serviceability relies on the proper understanding of pipe-soil interactions(PSI).Analytical methods are important approaches to studying PSI.However,a systematic and thorough literature review to analyze the existing research trends,technological achievements and future research opportunities is not available.This work investigates analytical methods that analyze the stress and deformation of pipes in terms of cross-sectional,transverse and longitudinal PSI problems.First,scientometric analysis is performed to acquire relevant research works from online databases and analyze the existing data of influential authors,productive research sources and frequent key word occurrence in the fields of interest.Second,a qualitative discussion is performed in the three categories of PSI:(1)cross-sectional,including ovalization and circumferential behaviours;(2)transverse,including seismic fault crossing,weak soil zones,ground settlement and pipe uplift;and(3)longitudinal.Third,six research opportunities are discussed,including the role of friction in cross-sectional deformation,combined effects of bending and compression,choice of soil reaction models and calibration of key parameters,effect of pipe flaws,soil spatial variability and behaviours of curved pipes.This study helps beginners familiarize themselves with PSI analytical methods and provides experienced researchers with ideas for future research directions.展开更多
文摘Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.
基金supported by the National Natural Science Foundation of China (41721003, 41974022, 41774024, 41874001)Open Research Fund Program of the Key Laboratory of Geospace Environment and Geodesy, Ministry of Education, China(20-02-05)
文摘We review three derivative-free methods developed for uncertainty estimation of non-linear error propagation, namely, MC(Monte Carlo), SUT(scaled unscented transformation), and SI(sterling interpolation). In order to avoid preset parameters like as these three methods need, we introduce a new method to uncertainty estimation for the first time, namely, SCR(spherical cubature rule), which is no need for setting parameters. By theoretical derivation, we prove that the precision of uncertainty obtained by SCR can reach second-order. We conduct four synthetic experiments, for the first two experiments, the results obtained by SCR are consistent with the other three methods with optimal setting parameters, but SCR is easier to operate than other three methods, which verifies the superiority of SCR in calculating the uncertainty. For the third experiment, real-time calculation is required, so the MC is hardly feasible. For the forth experiment, the SCR is applied to the inversion of seismic fault parameter which is a common problem in geophysics, and we study the sensitivity of surface displacements to fault parameters with errors. Our results show that the uncertainty of the surface displacements is the magnitude of ±10 mm when the fault length contains a variance of 0.01 km^(2).
基金sponsored by the Special Fund of the Institute of Geophysics,China Earthquake Administration(Grant Nos.DQJB22Z03 and DQJB22B25)。
文摘Based on the seismic source model in the Fifth Generation Seismic Ground Motion Parameters Zonation Map of China(FGSGMPZMC),a new seismic fault model,the new zonation of seismic risk areas(SRAs),and the estimation of seismicity rates for 2021-2030,this study constructed a new time-dependent seismic source model of China’s mainland,and used the probabilistic seismic hazard analysis method to calculate seismic hazard by selecting the ground motion models(GMMs)suitable for seismic sources in China.It also provided the probabilities of China’s mainland being affected by earthquakes of modified Mercalli intensity(MMI)Ⅵ,Ⅶ,Ⅷ,Ⅸ,and≥Ⅹin 2021-2030.The spatial pattern of seismic hazards presented in this article is similar to the pattern of the FGSGMPZMC,but shows more details.The seismic hazards in this study are higher than those in the FGSGMPZMC in the SRAs and fault zones that can produce large earthquakes.This indicates that the seismic source model construction in this study is scientific and reasonable.There are certain similarities between the results in this study and those of Rong et al.(2020)and Feng et al.(2020),but also disparities for specific sites due to differences in seismic source models,seismicity parameters,and GMMs.The results of seismic hazard may serve as parameter input for future seismic risk assessments.The hazard results can also be used as a basis for the formulation of earthquake prevention and mitigation policies for China’s mainland.
基金The authors gratefully acknowledge the Innovation and Technology Support Programme(ITSP)[Grant No.ITS/033/20FP]the Water Supplies Department of Hong Kong,China.Suggestions given by Dr.Andy Y.F.Leung are also appreciated.
文摘Buried water pipelines are vulnerable to fail or break due to excessive loading or ground displacements.Accurate evaluation of pipe performance and serviceability relies on the proper understanding of pipe-soil interactions(PSI).Analytical methods are important approaches to studying PSI.However,a systematic and thorough literature review to analyze the existing research trends,technological achievements and future research opportunities is not available.This work investigates analytical methods that analyze the stress and deformation of pipes in terms of cross-sectional,transverse and longitudinal PSI problems.First,scientometric analysis is performed to acquire relevant research works from online databases and analyze the existing data of influential authors,productive research sources and frequent key word occurrence in the fields of interest.Second,a qualitative discussion is performed in the three categories of PSI:(1)cross-sectional,including ovalization and circumferential behaviours;(2)transverse,including seismic fault crossing,weak soil zones,ground settlement and pipe uplift;and(3)longitudinal.Third,six research opportunities are discussed,including the role of friction in cross-sectional deformation,combined effects of bending and compression,choice of soil reaction models and calibration of key parameters,effect of pipe flaws,soil spatial variability and behaviours of curved pipes.This study helps beginners familiarize themselves with PSI analytical methods and provides experienced researchers with ideas for future research directions.
