Deep learning CNN-APSO-LSSVM hybrid fusion model for feature optimization and gas-bearing prediction

Conventional machine learning(CML)methods have been successfully applied for gas reservoir prediction.Their prediction accuracy largely depends on the quality of the sample data;therefore,feature optimization of the input samples is particularly important.Commonly used feature optimization methods increase the interpretability of gas reservoirs;however,their steps are cumbersome,and the selected features cannot sufficiently guide CML models to mine the intrinsic features of sample data efficiently.In contrast to CML methods,deep learning(DL)methods can directly extract the important features of targets from raw data.Therefore,this study proposes a feature optimization and gas-bearing prediction method based on a hybrid fusion model that combines a convolutional neural network(CNN)and an adaptive particle swarm optimization-least squares support vector machine(APSO-LSSVM).This model adopts an end-to-end algorithm structure to directly extract features from sensitive multicomponent seismic attributes,considerably simplifying the feature optimization.A CNN was used for feature optimization to highlight sensitive gas reservoir information.APSO-LSSVM was used to fully learn the relationship between the features extracted by the CNN to obtain the prediction results.The constructed hybrid fusion model improves gas-bearing prediction accuracy through two processes of feature optimization and intelligent prediction,giving full play to the advantages of DL and CML methods.The prediction results obtained are better than those of a single CNN model or APSO-LSSVM model.In the feature optimization process of multicomponent seismic attribute data,CNN has demonstrated better gas reservoir feature extraction capabilities than commonly used attribute optimization methods.In the prediction process,the APSO-LSSVM model can learn the gas reservoir characteristics better than the LSSVM model and has a higher prediction accuracy.The constructed CNN-APSO-LSSVM model had lower errors and a better fit on the test dataset than the other individual models.This method proves the effectiveness of DL technology for the feature extraction of gas reservoirs and provides a feasible way to combine DL and CML technologies to predict gas reservoirs.

Linear numerical calculation method for obtaining critical point,pore fluid,and framework parameters of gas-bearing media

Up to now, the primary method for studying critical porosity and porous media are experimental measurements and data analysis. There are few references on how to numerically calculate porosity at the critical point, pore fluid-related parameters, or framework-related parameters. So in this article, we provide a method for calculating these elastic parameters and use this method to analyze gas-bearing samples. We first derive three linear equations for numerical calculations. They are the equation of density p versus porosity Ф, density times the square of compressional wave velocity p Vp^2 versus porosity, and density times the square of shear wave velocity pVs^2 versus porosity. Here porosity is viewed as an independent variable and the other parameters are dependent variables. We elaborate on the calculation steps and provide some notes. Then we use our method to analyze gas-bearing sandstone samples. In the calculations, density and P- and S-velocities are input data and we calculate eleven relative parameters for porous fluid, framework, and critical point. In the end, by comparing our results with experiment measurements, we prove the viability of the method.

Types,Characteristics and Significances of Migrating Pathways of Gas-bearing Fluids in the Shenhu Area,Northern Continental Slope of the South China Sea

The first marine gas hydrate expedition in China has been conducted by Guangzhou Marine Geological Survey in the Shenhu Area, northern continental slope of the South China Sea. Previous study has analyzed the P-T conditions, geophysical anomalies and saturation calculations of these gas hydrates, but has not documented in detail the migration of gas-bearing fluids in the study area. Based on the interpretations of 2D/3D seismic data, this work identified two types of migration pathways for gas-bearing fluids in the Shenhu area, i.e., vertical and lateral pathways. The vertical pathways（largescale faults, gas chimneys and mud diapirs） presented as steep seismic reflection anomalies, which could be traced downward to the Eocene source rocks and may penetrate into the Late Miocene strata. The deeper gases/fluids might be allowed migrating into the shallower strata through these vertical conduits. However, the distributions showed distinct differences between these pathways. Large-scale faults developed only in the north and northeast of the Shenhu area, while in the drilling area gas chimneys were the sole vertical migration pathways. Since the Pliocene, normal faults, detachment faults and favorable sediments have constituted the lateral pathways in the Shenhu gas hydrate drilling area. Although these lateral pathways were connected with gas chimneys, they exerted different effects on hydrate formation and accumulation. Gas-bearing fluids migrated upward along gas chimneys might further migrate laterally because of the normal faults, thereby enlarging the range of the chimneys. Linking gas chimneys with the seafloor, the detachment faults might act as conduits for escaping gases/fluids. Re-deposited sediments developed at the early stage of the Quaternary were located within the gas hydrate stability zone, so hydrates would be enriched in these favorable sediments. Compared with the migration pathways（large-scale faults and mud diapirs） in the LW3-1 deep-sea oil/gas field, the migration efficiency of the vertical pathways（composed of gas chimneys） in the gas hydrate drilling area might be relatively low. Description and qualitative discrimination of migration pathways in the Shenhu gas hydrate drilling area are helpful to further understand the relationship between good-quality deep source rocks and shallow, mainly biogenicallyproduced, hydrates. As the main source rocks of the Baiyun sag, lacustrine mudstones in the Wenchang and Enping Formations may provide thermogenic methane. Gas chimneys with relatively low migration efficiency created the vertical pathways. Caused by the Dongsha tectonic movement, the release of overpressured fluids might reduce the vertical migration rates of the thermogenic methane. The thick bathyal/abyssal fine-grained sediments since the Late Miocene provided migration media with low permeability. These preconditions may cause carbon isotopic fractionation ofthermogenic methane during long-distance vertical migrations. Therefore, although geochemical analyses indicate that the methane forming gas hydrate in the Shenhu area was mainly produced biogenically, or was mixed methane primarily of microbial origin, thermogenic methane still contribute significantly.

Pore Connectivity of Deep Lacustrine Shale and its Effect on Gas-bearing Characteristics in the Songliao Basin:Implications from Continental Scientific Drilling

The lacustrine shale of deep Shahezi Formation in the Songliao basin has great gas potential,but its pore evolution,heterogeneity,and connectivity characteristics remain unclear.In this work,total organic carbon analysis,rock pyrolysis,X-ray diffraction field emission scanning electron microscopy,the particle and crack analysis system software,low-temperature nitrogen adsorption experiment,fractal theory,high-pressure mercury injection experiment and nuclear magnetic resonance experiment were used to study the Shahezi shale from Well SK-2.The result indicated that the organic pores in Shahezi shale are not developed,and the intergranular and intragranular pores are mainly formed by illitedominated clay.As the burial depth increases,the pore size and slit-shaped pores formed by clay decrease,and dissolved pores in the feldspar and carbonate minerals and dissolved fractures in the quartz increase.The pore evolution is affected by clay,compaction,and high-temperature corrosion.Based on the pore structure characteristics reflected by the pore size distribution and pore structure parameters obtained by multiple experimental methods,the pore development and evolution are divided into three stages.During stageⅠandⅡ,the pore heterogeneity of the shale reservoirs increases with the depth,the physical properties and pore connectivity deteriorate,but the gas-bearing property is good.In stageⅢ,the pore heterogeneity is the highest,its gas generation and storage capacity are low,but the increase of micro-fractures makes pore connectivity and gas-bearing better.

Study of A Geo-Acoustic Model of Gas-Bearing Sediment and Its Application in Sediment with Low Acoustic Veloctiy

A new geo-acoustic model for gas-bearing sediment is proposed based on the work of Dvorkin and Prasad, and Biot theory. Only five geophysical parameters： sediment mineral composition, free gas saturation, tortuosity （also known as the structure factor）, permeability, and porosity, are considered in the model. A benefit of this model is that we need only five parameters instead of ten parameters in the Blot＇ s formulas for acoustic velocity and attenuation calculation. Here the model is demonstrated with the in-situ experimental data collected from the Hangzhou Bay, China. The results of this study suggest that free gas content in sediment is the most critical condition resulting in a low acoustic velocity （compressional wave）. The respective contributions of the other four parameters in the model are also discussed.

Sinian gas sources and effectiveness of primary gas-bearing system in Sichuan Basin, SW China

Based on correlation between geochemical characteristics of Sinian and Cambrian source rocks and discovered gas reservoirs,paleoand the analysis on geological conditions of reservoir formation,the sources of natural gas in the Sinian of Sichuan Basin have been discussed to sort out the contribution of Sinian source rocks to the gas reservoirs and effectiveness of Sinian primary gas-bearing system.Through the analysis of natural gas composition,carbon and hydrogen isotopes and effectiveness of Sinian accumulation assemblages,it is concluded that:(1)The natural gas derived from the Sinian source rock is characterized by low ethane content,heavy ethane carbon isotope and light methane hydrogen isotope,and obviously different from the gas generated by the Cambrian source rock.(2)The gas reservoirs discovered in Sinian Dengying Formation are sourced by Sinian and Cambrian source rocks,and the Sinian source rock contributes different proportions to the gas in the 4th member and the 2nd member of the Dengying Formation,specifically,39%and 55%to the 4th member in marginal zone and intra-platform,54%and 68%to the 2th member in the marginal zone and intra-platform respectively.(3)The effectiveness of the Sinian primary gas-bearing system depends on the gas generating effectiveness of the source kitchen,reservoir and combination of gas accumulation elements.For high-over mature marine source rocks at the Ro of less than 3.5%,besides gas generated from the thermal cracking of liquid hydrocarbon,the kerogen still has some gas generation potential by thermal degradation.In addition,the Sinian microbial dolomite still preserves relatively good-quality reservoirs despite large burial depths,which match well with other basic conditions for gas accumulation in central Sichuan paleo-uplift,increasing the possibility of Sinian primary gas-bearing system.The research results confirm that the Sinian primary gas-bearing system is likely to form large-scale accumulation.

The influence factors of gas-bearing and geological characteristics of Niutitang Formation shale in the southern margin of Xuefeng Mountain ancient uplift: A case of Well Huangdi 1

In order to evaluate the geological characteristics and gas-bearing factors of Niutitang Formation within the Lower Cambrian of northern Guizhou,the Huangping area located at the southern edge of the ancient uplift belt of Xuefeng Mountain was selected as the target area,and Well Huangdi 1 was drilled for the geological survey of shale gas.Through geological background analysis and well logging and laboratory analysis such as organic geochemical test,gas content analysis,isothermal adsorption,and specific surface area experiments on Well Huangdi 1,the results show that the Niutitang Formation is a deep-water shelf,trough-like folds and thrust fault.The thickness of black shale is 119.95 m,of which carbonaceous shale is 89.6 m.The average value of organic carbon content is 3.55%,kerogen vitrinite reflectance value is 2.37% and kerogen type is sapropel-type.The brittle mineral content is 51%(quartz 38%),clay mineral content is 38.3%.The value of porosity and permeability are 0.5%and 0.0014 mD,which the reservoir of the Niutitang Formation belongs to low permeability with characteristics of ultra-low porosity.The gas content is 0.09‒1.31 m^3/t with a high-value area and a second high-value area.By comparing with the geological parameters of adjacent wells in the adjacent area,the accumulation model of“sediment control zone,Ro control zone,structure controlling reservoir”in the study area is proposed.Therefore,deep-water shelf-slope facies,Ro is between high maturity-early stage of overmaturity and well-preserved zones in the Niutitang Formation in this area are favorable direction for the next step of shale gas exploration.

Sustained release of vascular endothelial growth factor A and basic fibroblast growth factor from nanofiber membranes reduces oxygen/glucose deprivation-induced injury to neurovascular units

Upregulation of vascular endothelial growth factor A/basic fibroblast growth factor(VEGFA/b FGF)expression in the penumbra of cerebral ischemia can increase vascular volume,reduce lesion volume,and enhance neural cell proliferation and differentiation,thereby exerting neuroprotective effects.However,the beneficial effects of endogenous VEGFA/b FGF are limited as their expression is only transiently increased.In this study,we generated multilayered nanofiber membranes loaded with VEGFA/b FGF using layer-by-layer self-assembly and electrospinning techniques.We found that a membrane containing 10 layers had an ideal ultrastructure and could efficiently and stably release growth factors for more than 1 month.This 10-layered nanofiber membrane promoted brain microvascular endothelial cell tube formation and proliferation,inhibited neuronal apoptosis,upregulated the expression of tight junction proteins,and improved the viability of various cellular components of neurovascular units under conditions of oxygen/glucose deprivation.Furthermore,this nanofiber membrane decreased the expression of Janus kinase-2/signal transducer and activator of transcription-3(JAK2/STAT3),Bax/Bcl-2,and cleaved caspase-3.Therefore,this nanofiber membrane exhibits a neuroprotective effect on oxygen/glucose-deprived neurovascular units by inhibiting the JAK2/STAT3 pathway.

An alternative approach to match field production data from unconventional gas-bearing systems

Nowadays,the unconventional gas-bearing system plays an increasingly important role in energy market.The performances of the current history-matching techniques are not satisfied when applied to such systems.To overcome this shortfall,an alternative approach was developed and applied to investigate production data from an unconventional gas-bearing system.In this approach,the fluid flow curve obtained from the field is the superposition of a series of Gaussian functions.An automatic computing program was developed in the MATLAB,and both gas and water field data collected from a vertical well in the Linxing Block,Ordos Basin,were used to present the data processing technique.In the reservoir study,the automatic computing program was applied to match the production data from a single coal seam,multiple coal seams and multiple vertically stacked reservoirs with favourable fitting results.Compared with previous approaches,the proposed approach yields better results for both gas and water production data and can calculate the contributions from different reservoirs.The start time of the extraction for each gas-containing unit can also be determined.The new approach can be applied to the field data prediction and designation for the well locations and patterns at the reservoir scale.

The neurovascular unit-on-a-chip:modeling ischemic stroke to stem cell therapy

The neurovascular unit and stem cell therapy in ischemic stroke:Ischemic stroke,accounts for approximately 85% of all stroke incidents and is a major global health burden.It is the leading cause of disability and death worldwide,posing immense societal and economic challenges due to the long-term care required for stro ke survivors and the significant healthcare costs associated with its treatment and management(Amarenco et al.,2009).

Methods of identifying gas-bearing reservoirs by logs and applications of volcanic formations

The authors generalized the methods how to identify and evaluate gas zones using logs,and put forward the methods of crossplots and overlays of porosity logs on the identification of volcanic gas-bearing reservoirs in the northern Songliao Basin with good results.This study provides technical clues in deep formations and offers references for other areas to identify oil and gas layers.

Assessment of Wet Season Precipitation in the Central United States by the Regional Climate Simulation of the WRFG Member in NARCCAP and Its Relationship with Large-Scale Circulation Biases

Assessment of past-climate simulations of regional climate models(RCMs)is important for understanding the reliability of RCMs when used to project future regional climate.Here,we assess the performance and discuss possible causes of biases in a WRF-based RCM with a grid spacing of 50 km,named WRFG,from the North American Regional Climate Change Assessment Program(NARCCAP)in simulating wet season precipitation over the Central United States for a period when observational data are available.The RCM reproduces key features of the precipitation distribution characteristics during late spring to early summer,although it tends to underestimate the magnitude of precipitation.This dry bias is partially due to the model’s lack of skill in simulating nocturnal precipitation related to the lack of eastward propagating convective systems in the simulation.Inaccuracy in reproducing large-scale circulation and environmental conditions is another contributing factor.The too weak simulated pressure gradient between the Rocky Mountains and the Gulf of Mexico results in weaker southerly winds in between,leading to a reduction of warm moist air transport from the Gulf to the Central Great Plains.The simulated low-level horizontal convergence fields are less favorable for upward motion than in the NARR and hence,for the development of moist convection as well.Therefore,a careful examination of an RCM’s deficiencies and the identification of the source of errors are important when using the RCM to project precipitation changes in future climate scenarios.

Reservoir characteristics and genetic mechanisms of gas-bearing shales with different laminae and laminae combinations: A case study of Member 1 of the Lower Silurian Longmaxi shale in Sichuan Basin, SW China

Based on thin-section,argon-ion polished large-area imaging and nano-CT scanning data,the reservoir characteristics and genetic mechanisms of the Lower Silurian Longmaxi shale layers with different laminae and laminae combinations in the Sichuan Basin were examined.It is found that the shale has two kinds of laminae,clayey lamina and silty lamina,which are different in single lamina thickness,composition,pore type and structure,plane porosity and pore size distribution.The clayey laminae are about 100μm thick each,over 15%in organic matter content,over 70%in quartz content,and higher in organic pore ratio and plane porosity.They have abundant bedding fractures and organic matter and organic pores connecting with each other to form a network.In contrast,the silty laminae are about 50μm thick each,5%to 15%in organic matter content,over 50%in carbonate content,higher in inorganic pore ratio,undeveloped in bedding fracture,and have organic matter and organic pores disconnected from each other.The formation of mud lamina and silt lamina may be related to the flourish of silicon-rich organisms.The mud lamina is formed during the intermittent period,and silt lamina is formed during the bloom period of silicon-rich organisms.The mud laminae and silt laminae can combine into three types of assemblages:strip-shaped silt,gradating sand-mud and sand-mud thin interlayers.The strip-shaped silt assemblage has the highest porosity and horizontal/vertical permeability ratio,followed by the gradating sand-mud assemblage and sand-mud thin interlayer assemblage.The difference in the content ratio of the mud laminae to silt laminae results in the difference in the horizontal/vertical permeability ratio.

A gated recurrent unit model to predict Poisson’s ratio using deep learning

Static Poisson’s ratio(vs)is crucial for determining geomechanical properties in petroleum applications,namely sand production.Some models have been used to predict vs;however,the published models were limited to specific data ranges with an average absolute percentage relative error(AAPRE)of more than 10%.The published gated recurrent unit(GRU)models do not consider trend analysis to show physical behaviors.In this study,we aim to develop a GRU model using trend analysis and three inputs for predicting n s based on a broad range of data,n s(value of 0.1627-0.4492),bulk formation density(RHOB)(0.315-2.994 g/mL),compressional time(DTc)(44.43-186.9 μs/ft),and shear time(DTs)(72.9-341.2μ s/ft).The GRU model was evaluated using different approaches,including statistical error an-alyses.The GRU model showed the proper trends,and the model data ranges were wider than previous ones.The GRU model has the largest correlation coefficient(R)of 0.967 and the lowest AAPRE,average percent relative error(APRE),root mean square error(RMSE),and standard deviation(SD)of 3.228%,1.054%,4.389,and 0.013,respectively,compared to other models.The GRU model has a high accuracy for the different datasets:training,validation,testing,and the whole datasets with R and AAPRE values were 0.981 and 2.601%,0.966 and 3.274%,0.967 and 3.228%,and 0.977 and 2.861%,respectively.The group error analyses of all inputs show that the GRU model has less than 5% AAPRE for all input ranges,which is superior to other models that have different AAPRE values of more than 10% at various ranges of inputs.

基于Unity3D的油田抽油机三维可视化监控系统设计

针对抽油机监测形式单一、三维可视化程度低和联动性差的缺陷,引入信息―物理实时映射思想,开发了油田抽油机三维可视化监控系统。设计了抽油机数字空间,搭建虚实交互层设计架构;搭建三维可视化系统数据组成及关系框架;结合逆运动学,构建数学模型,基于五维模型和Unity 3D平台设计抽油机三维可视化系统总体架构;以游梁式抽油机为对象进行实验验证,实现了实时动态监测、虚实混合控制、运动轨迹追踪和在线预警等服务功能。为三维可视化监控在石油机械领域的落地应用和数字孪生系统的开发提供借鉴。

GENERALIZED FORELLI-RUDIN TYPE OPERATORS BETWEEN SEVERAL FUNCTION SPACES ON THE UNIT BALL OF C^(N)

In this paper,we investigate sufficient and necessary conditions such that generalized Forelli-Rudin type operators T_(λ,τ,k),S_(λ,τ,k),Q_(λ,τ,k)and R_(λ,τ,k)are bounded between Lebesgue type spaces.In order to prove the main results,we first give some bidirectional estimates for several typical integrals.

Uncertainties of landslide susceptibility prediction:influences of different study area scales and mapping unit scales

This study aims to investigate the effects of different mapping unit scales and study area scales on the uncertainty rules of landslide susceptibility prediction(LSP).To illustrate various study area scales,Ganzhou City in China,its eastern region(Ganzhou East),and Ruijin County in Ganzhou East were chosen.Different mapping unit scales are represented by grid units with spatial resolution of 30 and 60 m,as well as slope units that were extracted by multi-scale segmentation method.The 3855 landslide locations and 21 typical environmental factors in Ganzhou City are first determined to create spatial datasets with input-outputs.Then,landslide susceptibility maps(LSMs)of Ganzhou City,Ganzhou East and Ruijin County are pro-duced using a support vector machine(SVM)and random forest(RF),respectively.The LSMs of the above three regions are then extracted by mask from the LSM of Ganzhou City,along with the LSMs of Ruijin County from Ganzhou East.Additionally,LSMs of Ruijin at various mapping unit scales are generated in accordance.Accuracy and landslide suscepti-bility indexes(LSIs)distribution are used to express LSP uncertainties.The LSP uncertainties under grid units significantly decrease as study area scales decrease from Ganzhou City,Ganzhou East to Ruijin County,whereas those under slope units are less affected by study area scales.Of course,attentions should also be paid to the broader representativeness of large study areas.The LSP accuracy of slope units increases by about 6%–10%compared with those under grid units with 30 m and 60 m resolution in the same study area's scale.The significance of environmental factors exhibits an averaging trend as study area scale increases from small to large.The importance of environmental factors varies greatly with the 60 m grid unit,but it tends to be consistent to some extent in the 30 m grid unit and the slope unit.

Risk Factors for Mortality in Acute Kidney Injury in Intensive Care Units in Togo

Context: Acute kidney injury (AKI) in intensive care unit (ICU) is common and associated with very high mortality. In Togo, a tropical country with limited resources and only one nephrology department in the north, acute kidney injury seems to be a real tragedy with high mortality. Aims: to determine risk factors for mortality in acute kidney injury in the intensive care units. Methods and Material: We made a multicentric cross sectional study during 6 months in the four referral centers in northern Togo. Univariate and multivariate logistic regression was used to identify factors associated with mortality. Data were analyzed using RStudio 2023.04.1. Results: A total of 12.6% of patients admitted to intensive care had presented with AKI. The mean age was 49.6 ± 17.9. The sex ratio (M/F) was 2.1. Community-acquired AKI was in the majority (67.7%). Oligo anuria was the most frequent functional sign (38.4%). In our series, 81.6% of patients were in KDIGO stages 2 to 3. AKI was organic in 56.2% of cases. Mortality was 44.3%. In multivariate analysis, the main factors predictive of death were: respiratory distress (OR = 2.36;p Conclusions: Acute kidney injury in intensive care is common in northern Togo, and mortality is high. Identification of associated factors should help anticipate prognosis.

A Retrospective Analysis of Intoxicated Patients Admitted to the Intensive Care Unit: A Single-Institution Assessment in the Post-Pandemic Period

Background: The aim of this study was to evaluate the clinical and epidemiological characteristics of patients with acute intoxication admitted to the Intensive Care Unit (ICU). Material and Methods: An observational retrospective study was conducted on intoxicated patients who admitted to ICU between January 2022 and January 2024. Data were collected from the patients medical records. The demographic characteristics, causes of intoxications, clinical parameters, the mean stay in the ICU, treatment modalities and prognosis were recorded. Results: A total of 2875 critically ill patients were admitted during the study period, and 109 (3.79%) of them were acute intoxications. Their mean of ages was 38.09 ± 12.29. The female-to-male ratio was 1.37/1. Drugs were found to be the primary cause (62.39%) of intoxications, and analgesics, antidepressants, and antibiotics were the most frequent agents. Suicidal attempts were present in 66 patients, most of them were female (62.13%) and between 17 - 24 years (40.91%). The other common causes of intoxications were carbon monoxide (CO) (22.02%), methyl/ethyl alcohol (8.26%) and mushroom (5.50%). The mean stay in the ICU was 2.69 ± 0.89 days. Mechanical ventilation was applied to 10 of our patients. Renal replacement therapy was required in 6 patients. Despite all treatments, 6 of our patients died, and we found the mortality rate to be 5.50%. Conclusion: Intoxications were more frequent in young female patients and drugs were the most common cause with suicidal intent. Unfortunately, CO poisoning continues to be a very important problem in our city. These findings provided significant information about the characteristics of intoxications in Karabuk.