Waveforms of artificially induced explosions and collapse events recorded by the seismic network share similarities with natural earthquakes.Failure to identify and screen them in a timely manner can introduce confusi...Waveforms of artificially induced explosions and collapse events recorded by the seismic network share similarities with natural earthquakes.Failure to identify and screen them in a timely manner can introduce confusion into the earthquake catalog established using these recordings,thereby impacting future seismological research.Therefore,the identification and separation of natural earthquakes from continuous seismic signals contribute to the monitoring and early warning of destructive tectonic earthquakes.A 1D convolutional neural network(CNN)is proposed for seismic event classification using an efficient channel attention mechanism and an improved light inception block.A total of 9937 seismic sample records are obtained after waveform interception,filtering,and normalization.The proposed model can obtain better classification performance than other major existing methods,exhibiting 96.79%overall classification accuracy and 96.73%,94.85%,and 96.35%classification accuracy for natural seismic events,collapse events,and blasting events,respectively.Meanwhile,the proposed model is lighter than the 2D convolutional and common inception networks.We also apply the proposed model to the seismic data recorded at the University of Utah seismograph stations and compare its performance with that of the CNN-waveform model.展开更多
Discrimination of seismicity distributed in different areas is essential for reliable seismic risk assessment in mines.Although machine learning has been widely applied in seismic data processing,feasibility and relia...Discrimination of seismicity distributed in different areas is essential for reliable seismic risk assessment in mines.Although machine learning has been widely applied in seismic data processing,feasibility and reliability of applying this technique to classify spatially clustered seismic events in underground mines are yet to be investigated.In this research,two groups of seismic events with a minimum local magnitude(ML) of-3 were observed in an underground coal mine.They were respectively located around a dyke and the longwall face.Additionally,two types of undesired signals were also recorded.Four machine learning methods,i.e.random forest(RF),support vector machine(SVM),deep convolutional neural network(DCNN),and residual neural network(ResNN),were used for classifying these signals.The results obtained based on a primary dataset showed that these seismic events could be classified with at least 91% accuracy.The DCNN using seismogram images as the inputs reached the best performance with more than 94% accuracy.As mining is a dynamic progress which could change the characteristics of seismic signals,the temporal variance in the prediction performance of DCNN was also investigated to assess the reliability of this classifier during mining.A cascaded workflow consisting of database update,model training,signal prediction,and results review was established.By progressively calibrating the DCNN model,it achieved up to 99% prediction accuracy.The results demonstrated that machine learning is a reliable tool for the automatic discrimination of spatially clustered seismicity in underground mining.展开更多
To better understand characteristics of seismic signals of tracked vehicles measured when passing a sensor line,we numerically modelled force-pulse responses of a layered soil that is similar in its seismic properties...To better understand characteristics of seismic signals of tracked vehicles measured when passing a sensor line,we numerically modelled force-pulse responses of a layered soil that is similar in its seismic properties to that found at the original measurement site.The vertical-force pulses from the road wheels rolling over the track elements are fitted to the measured ones.Single-pulse seismic waves vary with distance due to diff erent wave types,refl ections at layer boundaries,vehicle velocity and relative position of the left and right track elements.They are computed by a modelling program and superposed at sensor positions with the appropriate slant distance and time shift for each track element.These sum signals are in qualitative agreement with those from the original measurements.However,they are several magnitudes weaker and much smoother.Furthermore,higher frequencies are damped much less at larger distances.Due to the large variability of the sum signals,recognition of tracked-vehicle types exclusively through their seismic signals seems diffi cult.展开更多
The study of the relationship of local ground conditions with the parameters </span><span style="font-family:Verdana;">of seismic vibrations carried out by the section of engineering seismology&l...The study of the relationship of local ground conditions with the parameters </span><span style="font-family:Verdana;">of seismic vibrations carried out by the section of engineering seismology</span><span style="font-family:Verdana;"> called seismic microzonation. In</span><i> </i><span style="font-family:Verdana;">this branch of applied science radical changes have taken place at the end of the last century. The Commission on Seismic Safety of the National Institute of Building Sciences of the United States has developed new recommendations, which are significantly different from all that used in the world practice of anti-seismic construction. The main provisions of this NEHRP (National Earthquake Hazards Reduction Program) classifica</span><span style="font-family:Verdana;">tion adopted in many national building codes, including Eurocode 8. At the same time, a number of papers appeared in subsequent years criticizing the </span><span style="font-family:Verdana;">use of the NEHRP soil classification. This article examines in detail and, </span><span style="font-family:Verdana;">most</span><span style="font-family:Verdana;"> importantly, comprehensively the shortcomings of the NEHRP classification.展开更多
Gravity anomalies reflect the geophysical response to subsurface density structures.Traditionally,the terrain density is assumed to be a constant when calculating Bouguer gravity anomaly.But deviations from this assum...Gravity anomalies reflect the geophysical response to subsurface density structures.Traditionally,the terrain density is assumed to be a constant when calculating Bouguer gravity anomaly.But deviations from this assumption may induce high-frequency signals in the Bouguer gravity anomaly.This study introduces a Bayesian method for computing Bouguer gravity anomaly.It incorporates a smoothness prior for the Bouguer gravity anomaly and estimates near-surface density parameters to minimize the Akaike's Bayesian Information Criterion(ABIC)value.The effectiveness of this method is validated through theoretical model tests and calculations on two observed gravity profiles in Yunnan.The results indicate that the Bouguer gravity anomaly profiles estimated using the Bayesian approach need no extra filtering,exhibit correlations with the crustal structure along the profiles,and effectively reveal subsurface crustal density variations.Moreover,the obtained density variations offer insights into the near-surface rock density in different geological periods.Specifically,Cenozoic formations have a density of roughly 2.65–2.90 g·cm^(-3),Mesozoic formations 2.61-2.91 g·cm^(-3),and Paleozoic formations 2.61–2.92 g·cm^(-3).Magmatic rock regions generally show higher density values.Additionally,these estimated densities show a positive correlation with the global VS30 seismic velocity estimates,suggesting a new geophysical approach for seismic site classification.The findings of this study are significantly valuable for near-surface density estimation and Bouguer gravity anomaly calculations.展开更多
Oil and gas shows are rich in drilling wells in Kaiping sag,however,large oilfield was still not found in this area.For a long time,it is thought that source rocks were developed in the middle-deep lacustrine facies i...Oil and gas shows are rich in drilling wells in Kaiping sag,however,large oilfield was still not found in this area.For a long time,it is thought that source rocks were developed in the middle-deep lacustrine facies in the Eocene Wenchang Formation,while there is no source rocks that in middle-deep lacustrine facies have been found in well.Thickness of Wenchang Formation is big and reservoirs with good properties could be found in this formation.Distribution and scale of source rock are significant for further direction of petroleum exploration.Distribution characterization of middle-deep lacustrine facies is the base for source rock research.Based on the sedimentary background,fault activity rate,seismic response features,and seismic attributes were analyzed.No limited classification method and multi-attributes neural network deep learning method were used for predicting of source rock distribution in Wenchang Formation.It is found that during the deposition of lower Wenchang Formation,activity rate of main fault controlling the sub sag sedimentation was bigger than 100 m/Ma,which formed development background for middle-deep lacustrine facies.Compared with the seismic response of middle-deep lacustrine source rocks developed in Zhu I depression,those in Kaiping sag are characterized in low frequency and good continuity.Through RGB frequency decomposition,areas with low frequency are main distribution parts for middle-deep lacustrine facies.Dominant frequency,instantaneous frequency,and coherency attributes of seismic could be used in no limited classification method for further identification of middle-deep lacustrine facies.Based on the limitation of geology knowledge,multi-attributes of seismic were analyzed through neural network deep learning method.Distribution of middle-deep lacustrine facies in the fourth member of Wenchang Formation is oriented from west to east and is the largest.Square of the middle-deep lacustrine facies in that member is 154 km^(2)and the volume is 50 km^(3).Achievements could be bases for hydrocarbon accumulation study and for exploration target optimization in Kaiping sag.展开更多
基金supported by the Jiangsu Provincial Key R&D Programme 261(BE2020116,BE2022154).
文摘Waveforms of artificially induced explosions and collapse events recorded by the seismic network share similarities with natural earthquakes.Failure to identify and screen them in a timely manner can introduce confusion into the earthquake catalog established using these recordings,thereby impacting future seismological research.Therefore,the identification and separation of natural earthquakes from continuous seismic signals contribute to the monitoring and early warning of destructive tectonic earthquakes.A 1D convolutional neural network(CNN)is proposed for seismic event classification using an efficient channel attention mechanism and an improved light inception block.A total of 9937 seismic sample records are obtained after waveform interception,filtering,and normalization.The proposed model can obtain better classification performance than other major existing methods,exhibiting 96.79%overall classification accuracy and 96.73%,94.85%,and 96.35%classification accuracy for natural seismic events,collapse events,and blasting events,respectively.Meanwhile,the proposed model is lighter than the 2D convolutional and common inception networks.We also apply the proposed model to the seismic data recorded at the University of Utah seismograph stations and compare its performance with that of the CNN-waveform model.
基金the Australia Coal Association Research Program(ACARP)(Grant Nos.C26006 and C26053)Supports from CSIRO。
文摘Discrimination of seismicity distributed in different areas is essential for reliable seismic risk assessment in mines.Although machine learning has been widely applied in seismic data processing,feasibility and reliability of applying this technique to classify spatially clustered seismic events in underground mines are yet to be investigated.In this research,two groups of seismic events with a minimum local magnitude(ML) of-3 were observed in an underground coal mine.They were respectively located around a dyke and the longwall face.Additionally,two types of undesired signals were also recorded.Four machine learning methods,i.e.random forest(RF),support vector machine(SVM),deep convolutional neural network(DCNN),and residual neural network(ResNN),were used for classifying these signals.The results obtained based on a primary dataset showed that these seismic events could be classified with at least 91% accuracy.The DCNN using seismogram images as the inputs reached the best performance with more than 94% accuracy.As mining is a dynamic progress which could change the characteristics of seismic signals,the temporal variance in the prediction performance of DCNN was also investigated to assess the reliability of this classifier during mining.A cascaded workflow consisting of database update,model training,signal prediction,and results review was established.By progressively calibrating the DCNN model,it achieved up to 99% prediction accuracy.The results demonstrated that machine learning is a reliable tool for the automatic discrimination of spatially clustered seismicity in underground mining.
文摘To better understand characteristics of seismic signals of tracked vehicles measured when passing a sensor line,we numerically modelled force-pulse responses of a layered soil that is similar in its seismic properties to that found at the original measurement site.The vertical-force pulses from the road wheels rolling over the track elements are fitted to the measured ones.Single-pulse seismic waves vary with distance due to diff erent wave types,refl ections at layer boundaries,vehicle velocity and relative position of the left and right track elements.They are computed by a modelling program and superposed at sensor positions with the appropriate slant distance and time shift for each track element.These sum signals are in qualitative agreement with those from the original measurements.However,they are several magnitudes weaker and much smoother.Furthermore,higher frequencies are damped much less at larger distances.Due to the large variability of the sum signals,recognition of tracked-vehicle types exclusively through their seismic signals seems diffi cult.
文摘The study of the relationship of local ground conditions with the parameters </span><span style="font-family:Verdana;">of seismic vibrations carried out by the section of engineering seismology</span><span style="font-family:Verdana;"> called seismic microzonation. In</span><i> </i><span style="font-family:Verdana;">this branch of applied science radical changes have taken place at the end of the last century. The Commission on Seismic Safety of the National Institute of Building Sciences of the United States has developed new recommendations, which are significantly different from all that used in the world practice of anti-seismic construction. The main provisions of this NEHRP (National Earthquake Hazards Reduction Program) classifica</span><span style="font-family:Verdana;">tion adopted in many national building codes, including Eurocode 8. At the same time, a number of papers appeared in subsequent years criticizing the </span><span style="font-family:Verdana;">use of the NEHRP soil classification. This article examines in detail and, </span><span style="font-family:Verdana;">most</span><span style="font-family:Verdana;"> importantly, comprehensively the shortcomings of the NEHRP classification.
基金supported by the National Key Research and Development Program of China(2023YFE0101800)the National Natural Science Foundation of China(Young Scientists Fund,42450233,General Program,42474120)+3 种基金the Basic Scientific Research Fund Special Project of the Institute of Geophysics,China Earthquake Administration(DQJB24B20)the Natural Science Foundation of Beijing(Grant No.1242033)the Natural Science Foundation of Tianjin(25JCQNJC00540)the National Science and Technology Major Project for Deep Earth Probe and Mineral Resources Exploration(2024ZD1002700).
文摘Gravity anomalies reflect the geophysical response to subsurface density structures.Traditionally,the terrain density is assumed to be a constant when calculating Bouguer gravity anomaly.But deviations from this assumption may induce high-frequency signals in the Bouguer gravity anomaly.This study introduces a Bayesian method for computing Bouguer gravity anomaly.It incorporates a smoothness prior for the Bouguer gravity anomaly and estimates near-surface density parameters to minimize the Akaike's Bayesian Information Criterion(ABIC)value.The effectiveness of this method is validated through theoretical model tests and calculations on two observed gravity profiles in Yunnan.The results indicate that the Bouguer gravity anomaly profiles estimated using the Bayesian approach need no extra filtering,exhibit correlations with the crustal structure along the profiles,and effectively reveal subsurface crustal density variations.Moreover,the obtained density variations offer insights into the near-surface rock density in different geological periods.Specifically,Cenozoic formations have a density of roughly 2.65–2.90 g·cm^(-3),Mesozoic formations 2.61-2.91 g·cm^(-3),and Paleozoic formations 2.61–2.92 g·cm^(-3).Magmatic rock regions generally show higher density values.Additionally,these estimated densities show a positive correlation with the global VS30 seismic velocity estimates,suggesting a new geophysical approach for seismic site classification.The findings of this study are significantly valuable for near-surface density estimation and Bouguer gravity anomaly calculations.
文摘Oil and gas shows are rich in drilling wells in Kaiping sag,however,large oilfield was still not found in this area.For a long time,it is thought that source rocks were developed in the middle-deep lacustrine facies in the Eocene Wenchang Formation,while there is no source rocks that in middle-deep lacustrine facies have been found in well.Thickness of Wenchang Formation is big and reservoirs with good properties could be found in this formation.Distribution and scale of source rock are significant for further direction of petroleum exploration.Distribution characterization of middle-deep lacustrine facies is the base for source rock research.Based on the sedimentary background,fault activity rate,seismic response features,and seismic attributes were analyzed.No limited classification method and multi-attributes neural network deep learning method were used for predicting of source rock distribution in Wenchang Formation.It is found that during the deposition of lower Wenchang Formation,activity rate of main fault controlling the sub sag sedimentation was bigger than 100 m/Ma,which formed development background for middle-deep lacustrine facies.Compared with the seismic response of middle-deep lacustrine source rocks developed in Zhu I depression,those in Kaiping sag are characterized in low frequency and good continuity.Through RGB frequency decomposition,areas with low frequency are main distribution parts for middle-deep lacustrine facies.Dominant frequency,instantaneous frequency,and coherency attributes of seismic could be used in no limited classification method for further identification of middle-deep lacustrine facies.Based on the limitation of geology knowledge,multi-attributes of seismic were analyzed through neural network deep learning method.Distribution of middle-deep lacustrine facies in the fourth member of Wenchang Formation is oriented from west to east and is the largest.Square of the middle-deep lacustrine facies in that member is 154 km^(2)and the volume is 50 km^(3).Achievements could be bases for hydrocarbon accumulation study and for exploration target optimization in Kaiping sag.
