At present,the acquisition of seismic data is developing toward high-precision and high-density methods.However,complex natural environments and cultural factors in many exploration areas cause difficulties in achievi...At present,the acquisition of seismic data is developing toward high-precision and high-density methods.However,complex natural environments and cultural factors in many exploration areas cause difficulties in achieving uniform and intensive acquisition,which makes complete seismic data collection impossible.Therefore,data reconstruction is required in the processing link to ensure imaging accuracy.Deep learning,as a new field in rapid development,presents clear advantages in feature extraction and modeling.In this study,the convolutional neural network deep learning algorithm is applied to seismic data reconstruction.Based on the convolutional neural network algorithm and combined with the characteristics of seismic data acquisition,two training strategies of supervised and unsupervised learning are designed to reconstruct sparse acquisition seismic records.First,a supervised learning strategy is proposed for labeled data,wherein the complete seismic data are segmented as the input of the training set and are randomly sampled before each training,thereby increasing the number of samples and the richness of features.Second,an unsupervised learning strategy based on large samples is proposed for unlabeled data,and the rolling segmentation method is used to update(pseudo)labels and training parameters in the training process.Through the reconstruction test of simulated and actual data,the deep learning algorithm based on a convolutional neural network shows better reconstruction quality and higher accuracy than compressed sensing based on Curvelet transform.展开更多
This research investigated anthropogenic inputs and chemical weathering in the upper reaches of the Datong River Basin,a tributary of the upper Yellow River,NW China.Multiple approaches were applied to data from 52 wa...This research investigated anthropogenic inputs and chemical weathering in the upper reaches of the Datong River Basin,a tributary of the upper Yellow River,NW China.Multiple approaches were applied to data from 52 water and 12 soil samples from the Muli,Jiangcang,and Mole basins to estimate the chemical component concentrations and to analyze hydrochemical characteristics,distribution patterns,and origins in this coal mining-affected river basin.Coal mining has enhanced the weathering of the lithosphere in the study region.The total dissolved solids in the river range from 145.4 to 701.9 mg/L,which is higher than the global average for rivers.Ion concentration spatial distributions increase around mining areas.River geochemistry is mainly controlled by coal mining activity,carbonate weathering,and silicate weathering,with variances of 33.4%,26.2%,and 21.3%,respectively.Ca^(2+),Mg^(2+),and HCO_(3)^(-)are mainly due to the dissolution of carbonate minerals(calcite>dolomite);Si and K+are mainly from potassium(sodium)feldspar weathering;and Na+and SO_(4)^(2-)mainly from coal mine production.A conceptual model of the river water ion origins from the study area is presented and management implications for improving the adverse effects of coal mining are proposed.These results provide an important standard reference for water resource and environmental management in the study region.展开更多
Structural control on groundwater distribution and flow in the south of Ningxia Hui Autonomous Region,China was investigated and analyzed.Intensive geological movement in geological history has resulted in a complex t...Structural control on groundwater distribution and flow in the south of Ningxia Hui Autonomous Region,China was investigated and analyzed.Intensive geological movement in geological history has resulted in a complex tectonic structure,and a complex distribution and flow pattern of groundwater.Based on the hydrogeological investigation,4 types of water bearing structure(WBS) were discovered:Porous WBS,Fissure WBS,Karst WBS and Fissure-porous WBS.These WBSs and their combinations provided the varied storage spaces and flowing channels for groundwater in SNHAR.展开更多
基金This study was supported by the National Natural Science Foundation of China under the project‘Research on the Dynamic Location of Receiver Points and Wave Field Separation Technology Based on Deep Learning in OBN Seismic Exploration’(No.42074140).
文摘At present,the acquisition of seismic data is developing toward high-precision and high-density methods.However,complex natural environments and cultural factors in many exploration areas cause difficulties in achieving uniform and intensive acquisition,which makes complete seismic data collection impossible.Therefore,data reconstruction is required in the processing link to ensure imaging accuracy.Deep learning,as a new field in rapid development,presents clear advantages in feature extraction and modeling.In this study,the convolutional neural network deep learning algorithm is applied to seismic data reconstruction.Based on the convolutional neural network algorithm and combined with the characteristics of seismic data acquisition,two training strategies of supervised and unsupervised learning are designed to reconstruct sparse acquisition seismic records.First,a supervised learning strategy is proposed for labeled data,wherein the complete seismic data are segmented as the input of the training set and are randomly sampled before each training,thereby increasing the number of samples and the richness of features.Second,an unsupervised learning strategy based on large samples is proposed for unlabeled data,and the rolling segmentation method is used to update(pseudo)labels and training parameters in the training process.Through the reconstruction test of simulated and actual data,the deep learning algorithm based on a convolutional neural network shows better reconstruction quality and higher accuracy than compressed sensing based on Curvelet transform.
基金This research was funded by the National Natural Science Foundation of China’s NSFC,grant number(No.41302190)China Geological project(grant nos.1212011220971 and DD20190252).
文摘This research investigated anthropogenic inputs and chemical weathering in the upper reaches of the Datong River Basin,a tributary of the upper Yellow River,NW China.Multiple approaches were applied to data from 52 water and 12 soil samples from the Muli,Jiangcang,and Mole basins to estimate the chemical component concentrations and to analyze hydrochemical characteristics,distribution patterns,and origins in this coal mining-affected river basin.Coal mining has enhanced the weathering of the lithosphere in the study region.The total dissolved solids in the river range from 145.4 to 701.9 mg/L,which is higher than the global average for rivers.Ion concentration spatial distributions increase around mining areas.River geochemistry is mainly controlled by coal mining activity,carbonate weathering,and silicate weathering,with variances of 33.4%,26.2%,and 21.3%,respectively.Ca^(2+),Mg^(2+),and HCO_(3)^(-)are mainly due to the dissolution of carbonate minerals(calcite>dolomite);Si and K+are mainly from potassium(sodium)feldspar weathering;and Na+and SO_(4)^(2-)mainly from coal mine production.A conceptual model of the river water ion origins from the study area is presented and management implications for improving the adverse effects of coal mining are proposed.These results provide an important standard reference for water resource and environmental management in the study region.
文摘Structural control on groundwater distribution and flow in the south of Ningxia Hui Autonomous Region,China was investigated and analyzed.Intensive geological movement in geological history has resulted in a complex tectonic structure,and a complex distribution and flow pattern of groundwater.Based on the hydrogeological investigation,4 types of water bearing structure(WBS) were discovered:Porous WBS,Fissure WBS,Karst WBS and Fissure-porous WBS.These WBSs and their combinations provided the varied storage spaces and flowing channels for groundwater in SNHAR.
