Recently,exploration breakthroughs have been made in the Lower Cretaceous sandstone reservoirs in the Doseo Basin,but the identification of reservoir fluid property is difficult due to variable reservoir lithology,com...Recently,exploration breakthroughs have been made in the Lower Cretaceous sandstone reservoirs in the Doseo Basin,but the identification of reservoir fluid property is difficult due to variable reservoir lithology,complex oil-water contact within and faint responses of the oil zone,which causes the lower accuracy of reservoir fluid property identification with conventional mudlogging and wirelogging techniques.Applying the geochemical logging,fluorescent logging,mud logging and cutting logging technology,in combination with formation test data,this paper distinguishes the crude oil types,analyzes the logging response characteristics of oil zone after water washing,and establishes the interpretation charts and parameter standards for reservoir fluid properties.The crude oil can be divided into two types,namely viscous-heavy and thin-light,based on total hydrocarbon content and component concentration tested by mud logging,features of pyrolysis gas chromatogram and fluorescence spectroscopy.The general characteristics of oil layers experienced water washing include the decrease of total hydrocarbon content and component concentration from mud logging,the decrease of S1 and PS values from geochemical logging,the decrease of hydrocarbon abundance and absence of some light components in pyrolysis gas chromatogram,and the decrease of fluorescence area and intensity from fluorescence logging.According to crude oil types,the cross plots of S1 versus peak-baseline ratio,and the cross plots of rock wettability versus fluorescence area ratio are drawn and used to interpret reservoir fluid property.Meanwhile,the standards of reservoir fluid parameter are established combining with the parameters of PS and the parameters in above charts,and comprehensive multiparameter correlation in both vertical and horizontal ways is also performed to interpret reservoir fluid property.The application in the Doseo Basin achieved great success,improving interpretation ability of fluid property in the reservoir with complex oil-water contact,and also provided technical reference for the efficient exploration and development of similar reservoirs.展开更多
Arrhythmias may lead to sudden cardiac death if not detected and treated in time.A supraventricular premature beat(SPB)and premature ventricular contraction(PVC)are important categories of arrhythmia disease.Recently,...Arrhythmias may lead to sudden cardiac death if not detected and treated in time.A supraventricular premature beat(SPB)and premature ventricular contraction(PVC)are important categories of arrhythmia disease.Recently,deep learning methods have been applied to the PVC/SPB heartbeats detection.However,most researchers have focused on time-domain information of the electrocardiogram and there has been a lack of exploration of the interpretability of the model.In this study,we design an interpretable and accurate PVC/SPB recognition algorithm,called the interpretable multilevel wavelet decomposition deep network(IMWDDN).Wavelet decomposition is introduced into the deep network and the squeeze and excitation(SE)-Residual block is designed for extracting time-domain and frequency-domain features.Additionally,inspired by the idea of residual learning,we construct a novel loss function for the constant updating of the multilevel wavelet decomposition parameters.Finally,the IMWDDN is evaluated on the Third China Physiological Signal Challenge Dataset and the MIT-BIH Arrhythmia database.The comparison results show IMWDDN has better detection performance with 98.51%accuracy and a 93.75%F1-macro on average,and its areas of concern are similar to those of an expert diagnosis to a certain extent.Generally,the IMWDDN has good application value in the clinical screening of PVC/SPB heartbeats.展开更多
基金funded by a project entitled exploration field evaluation and target optimization of key basins in Chad and Niger(No.2019D-4308)initiated by the scientific research and technology development project of china national petroleum corporation.
文摘Recently,exploration breakthroughs have been made in the Lower Cretaceous sandstone reservoirs in the Doseo Basin,but the identification of reservoir fluid property is difficult due to variable reservoir lithology,complex oil-water contact within and faint responses of the oil zone,which causes the lower accuracy of reservoir fluid property identification with conventional mudlogging and wirelogging techniques.Applying the geochemical logging,fluorescent logging,mud logging and cutting logging technology,in combination with formation test data,this paper distinguishes the crude oil types,analyzes the logging response characteristics of oil zone after water washing,and establishes the interpretation charts and parameter standards for reservoir fluid properties.The crude oil can be divided into two types,namely viscous-heavy and thin-light,based on total hydrocarbon content and component concentration tested by mud logging,features of pyrolysis gas chromatogram and fluorescence spectroscopy.The general characteristics of oil layers experienced water washing include the decrease of total hydrocarbon content and component concentration from mud logging,the decrease of S1 and PS values from geochemical logging,the decrease of hydrocarbon abundance and absence of some light components in pyrolysis gas chromatogram,and the decrease of fluorescence area and intensity from fluorescence logging.According to crude oil types,the cross plots of S1 versus peak-baseline ratio,and the cross plots of rock wettability versus fluorescence area ratio are drawn and used to interpret reservoir fluid property.Meanwhile,the standards of reservoir fluid parameter are established combining with the parameters of PS and the parameters in above charts,and comprehensive multiparameter correlation in both vertical and horizontal ways is also performed to interpret reservoir fluid property.The application in the Doseo Basin achieved great success,improving interpretation ability of fluid property in the reservoir with complex oil-water contact,and also provided technical reference for the efficient exploration and development of similar reservoirs.
基金supported by the National Postdoctoral Program for Innovative Talents(Grant No.BX20230215)China Postdoctoral Science Foundation(Grant No.2023M732219)Shanghai Municipal Science and Technology Major Project(Grant No.2021SHZDZX0102)。
文摘Arrhythmias may lead to sudden cardiac death if not detected and treated in time.A supraventricular premature beat(SPB)and premature ventricular contraction(PVC)are important categories of arrhythmia disease.Recently,deep learning methods have been applied to the PVC/SPB heartbeats detection.However,most researchers have focused on time-domain information of the electrocardiogram and there has been a lack of exploration of the interpretability of the model.In this study,we design an interpretable and accurate PVC/SPB recognition algorithm,called the interpretable multilevel wavelet decomposition deep network(IMWDDN).Wavelet decomposition is introduced into the deep network and the squeeze and excitation(SE)-Residual block is designed for extracting time-domain and frequency-domain features.Additionally,inspired by the idea of residual learning,we construct a novel loss function for the constant updating of the multilevel wavelet decomposition parameters.Finally,the IMWDDN is evaluated on the Third China Physiological Signal Challenge Dataset and the MIT-BIH Arrhythmia database.The comparison results show IMWDDN has better detection performance with 98.51%accuracy and a 93.75%F1-macro on average,and its areas of concern are similar to those of an expert diagnosis to a certain extent.Generally,the IMWDDN has good application value in the clinical screening of PVC/SPB heartbeats.
