Search

Identification of reservoir types in deep carbonates has always been a great challenge due to complex logging responses caused by the heterogeneous scale and distribution of storage spaces. Traditional cross-plot analysis and empirical formula methods for identifying reservoir types using geophysical logging data have high uncertainty and low efficiency, which cannot accurately reflect the nonlinear relationship between reservoir types and logging data. Recently, the kernel Fisher discriminant analysis (KFD), a kernel-based machine learning technique, attracts attention in many fields because of its strong nonlinear processing ability. However, the overall performance of KFD model may be limited as a single kernel function cannot simultaneously extrapolate and interpolate well, especially for highly complex data cases. To address this issue, in this study, a mixed kernel Fisher discriminant analysis (MKFD) model was established and applied to identify reservoir types of the deep Sinian carbonates in central Sichuan Basin, China. The MKFD model was trained and tested with 453 datasets from 7 coring wells, utilizing GR, CAL, DEN, AC, CNL and RT logs as input variables. The particle swarm optimization (PSO) was adopted for hyper-parameter optimization of MKFD model. To evaluate the model performance, prediction results of MKFD were compared with those of basic-kernel based KFD, RF and SVM models. Subsequently, the built MKFD model was applied in a blind well test, and a variable importance analysis was conducted. The comparison and blind test results demonstrated that MKFD outperformed traditional KFD, RF and SVM in the identification of reservoir types, which provided higher accuracy and stronger generalization. The MKFD can therefore be a reliable method for identifying reservoir types of deep carbonates. [ABSTRACT FROM AUTHOR]

How to fit a properly nonlinear classification model from conventional well logs to lithofacies is a key problem for machine learning methods. Kernel methods (e.g., KFD, SVM, MSVM) are effective attempts to solve this issue due to abilities of handling nonlinear features by kernel functions. Deep mining of log features indicating lithofacies still needs to be improved for kernel methods. Hence, this work employs deep neural networks to enhance the kernel principal component analysis (KPCA) method and proposes a deep kernel method (DKM) for lithofacies identification using well logs. DKM includes a feature extractor and a classifier. The feature extractor consists of a series of KPCA models arranged according to residual network structure. A gradient-free optimization method is introduced to automatically optimize parameters and structure in DKM, which can avoid complex tuning of parameters in models. To test the validation of the proposed DKM for lithofacies identification, an open-sourced dataset with seven conventional logs (GR, CAL, AC, DEN, CNL, LLD, and LLS) and lithofacies labels from the Daniudi Gas Field in China is used. There are eight lithofacies, namely clastic rocks (pebbly, coarse, medium, and fine sandstone, siltstone, mudstone), coal, and carbonate rocks. The comparisons between DKM and three commonly used kernel methods (KFD, SVM, MSVM) show that (1) DKM (85.7%) outperforms SVM (77%), KFD (79.5%), and MSVM (82.8%) in accuracy of lithofacies identification; (2) DKM is about twice faster than the multi-kernel method (MSVM) with good accuracy. The blind well test inWell D13 indicates that compared with the other three methods DKM improves about 24% in accuracy, 35% in precision, 41% in recall, and 40% in F1 score, respectively. In general, DKM is an effective method for complex lithofacies identification. This work also discussed the optimal structure and classifier for DKM. Experimental results show that (m1, m2, 0) is the optimal model structure and linear SVM is the optimal classifier. (m1, m2, 0) means there are m1 KPCAs, and then m2 residual units. A workflow to determine an optimal classifier in DKM for lithofacies identification is proposed, too. [ABSTRACT FROM AUTHOR]

Consumerism is not only a kind of values, but also a practice which emphasizes possession. As a combination of concept and behavior, consumerism has at its core over-possession and over-consumption by which people obtain their social and cultural identities. In order to understand the consumerism in current China, the political-economic conditions and the consumption practice should be both taken into account, and moreover, normal material requirements should be distinguished from over-possession. Only in this way can a valid conclusion be reached. Compared with those in the western societies, China' s consumerism is produced and shaped by its special historical conditions and social basis. It does not take place mainly among the masses, but among the elite class who enjoy high incomes. However, this trend is spreading from the high-income stratum to the middle-income stratum and even influences the whole society. [ABSTRACT FROM AUTHOR]

Fulminant myocarditis is an acute diffuse inflammatory disease of myocardium. It is characterized by acute onset, rapid progress and high risk of death. Its pathogenesis involves excessive immune activation of the innate immune system and formation of inflammatory storm. According to China's practical experience, the adoption of the "life support-based comprehensive treatment regimen" (with mechanical circulation support and immunomodulation therapy as the core) can significantly improve the survival rate and long-term prognosis. Special emphasis is placed on very early identification,very early diagnosis,very early prediction and very early treatment., (© 2024. Science China Press.)

Objective: To explore the spatial distribution character of dengue fever and the change of Aedes' population, so as to provide macroscopical decision-making evidences of prevention and supervision on dengue fever., Methods: (1) Collecting data on morbidity of dengue and supervision on vector's population in the corresponding period. (2) Drawing digitized map of Chaozhou in scale of 1:50,000, including elements of boundary, residential areas, road and traffic, altitude, water systems etc. (3) Measuring the latitude and longitude of center position of surveillance safes on the scene. (4) Processing spatial analysis by the ArcGIS 8.5 software., Results: Distribution of Aedes showed spatial cluster in Chaozhou, while its density was related to the distance to the watersides. The closer to the watersides, the higher the density was. Map on spatial distribution showed that although the Aedes epidemic situation changed yearly, but primarily be kept in high, middle, low regions. Cross-validation effects of the distribution maps were satisfactory., Conclusion: Geographic information system was promising in analyzing data on dengue fever, and better than other routine research methods.

Objective: To establish digitized virtual Chinese No.1 female (VCH-F1) image database., Methods: A 19 years old female cadaver was scanned by CT, MRI, and perfused with red filling material through formal artery before freezing and em- bedding. The whole body was cut by JZ1500A vertical milling machine with a 0.2 mm inter-spacing. All the images was produced by Fuji FinePix S2 Pro camera., Results: The body index of VCH-F1 was 94%. We cut 8 556 sections of the whole body, and each image was 17.5 MB in size and the whole database reached 149.7 GB. We have totally 6 versions of the database for different applications., Conclusions: Compared with other databases, VCH-F1 has good representation of the Chinese body shape, colorful filling material in blood vessels providing enough information for future registration and segmentation. Vertical embedding and cutting helped to retain normal human physiological posture, and the image quality and operation efficiency were improved by using various techniques such as one-time freezing and fixation, double-temperature icehouse, large-diameter milling disc and whole body cutting.