Genetic mechanisms of high-quality tight siliciclastic reservoirs:A case study from the Upper Triassic Xujiahe Formation in the Yuanba area,Sichuan Basin,China

This study analyzed the petrological characteristics,diagenesis,pore types,and physical properties of the tight coarse-grained siliciclastic sequences in the third member of the Upper Triassic Xujiahe Formation(also referred to as the Xu-3 Member)in the western Yuanba area in the northeastern Sichuan Basin,China,based on the results of 242.61-m-long core description,292 thin-section observations,scanning electron microscopy(SEM),and 292 physical property tests.The types and genetic mechanisms of high-quality tight coarse-grained siliciclastic reservoirs in this member was determined thereafter.The research objective is to guide the exploration and development of the tight coarse-grained siliciclastic sequences in the Xu-3 Member.The results of this study are as follows.Two types of high-quality reservoirs are developed in the coarse-grained siliciclastic sequences of the Xu-3 Member,namely the fractured fine-grained sandy conglomerate type and porous medium-grained calcarenaceous sandstone type.Hydrodynamic energy in the sedimentary environment is the key factor controlling the formation of high-quality reservoirs.These high-quality reservoirs are developed mainly in the transitional zone with moderately high hydrodynamic energy between delta-plain braided channels and delta-front subaqueous distributary channels.The dolomitic debris(gravel)content is the main factor affecting the reservoirs’physical properties.The micritic algal debris and sandy debris in the dolomitic debris(or gravels)tend to recrystallize during burial,forming intercrystalline pores within.In the medium-grained calcarenaceous sandstones,intercrystalline pores in the dolomitic debris are formed at the early diagenetic stage,and a pore system consisting of structural fractures connecting intergranular pores,intergranular dissolution pores,and kaolinite intergranular micropores is developed at the late stage of diagenesis.The formation of intercrystalline pores in dolomite gravels and gravel-edge fractures,a pore system connected by gravel-edge and tectonic fractures,is closely related to the dolomite gravels in the sandy fine-grained conglomerates.

Identification of reservoir types in deep carbonates based on mixedkernel machine learning using geophysical logging data

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.

A Transient-Pressure-Based Numerical Approach for Interlayer Identification in Sand Reservoirs

Almost all sandstone reservoirs contain interlayers. The identification and characterization of these interlayers iscritical for minimizing the uncertainty associated with oilfield development and improving oil and gas recovery.Identifying interlayers outside wells using identification methods based on logging data and machine learning isdifficult and seismic-based identification techniques are expensive. Herein, a numerical model based on seepageand well-testing theories is introduced to identify interlayers using transient pressure data. The proposed modelrelies on the open-source MATLAB Reservoir Simulation Toolbox. The effects of the interlayer thickness, position,and width on the pressure response are thoroughly investigated. A procedure for inverting interlayer parametersin the reservoir using the bottom-hole pressure is also proposed. This method uses only transient pressuredata during well testing and can effectively identify the interlayer distribution near the wellbore at an extremelylow cost. The reliability of the model is verified using effective oilfield examples.

Fracture identification of carbonate reservoirs by deep forest model:An example from the D oilfield in Zagros Basin

Identifying fractures along a well trajectory is of immense significance in determining the subsurface fracture network distribution.Typically,conventional logs exhibit responses in fracture zones,and almost all wells have such logs.However,detecting fractures through logging responses can be challenging since the log response intensity is weak and complex.To address this problem,we propose a deep learning model for fracture identification using deep forest,which is based on a cascade structure comprising multi-layer random forests.Deep forest can extract complex nonlinear features of fractures in conventional logs through ensemble learning and deep learning.The proposed approach is tested using a dataset from the Oligocene to Miocene tight carbonate reservoirs in D oilfield,Zagros Basin,Middle East,and eight logs are selected to construct the fracture identification model based on sensitivity analysis of logging curves against fractures.The log package includes the gamma-ray,caliper,density,compensated neutron,acoustic transit time,and shallow,deep,and flushed zone resistivity logs.Experiments have shown that the deep forest obtains high recall and accuracy(>92%).In a blind well test,results from the deep forest learning model have a good correlation with fracture observation from cores.Compared to the random forest method,a widely used ensemble learning method,the proposed deep forest model improves accuracy by approximately 4.6%.

A systematic machine learning method for reservoir identification and production prediction

Reservoir identification and production prediction are two of the most important tasks in petroleum exploration and development.Machine learning(ML)methods are used for petroleum-related studies,but have not been applied to reservoir identification and production prediction based on reservoir identification.Production forecasting studies are typically based on overall reservoir thickness and lack accuracy when reservoirs contain a water or dry layer without oil production.In this paper,a systematic ML method was developed using classification models for reservoir identification,and regression models for production prediction.The production models are based on the reservoir identification results.To realize the reservoir identification,seven optimized ML methods were used:four typical single ML methods and three ensemble ML methods.These methods classify the reservoir into five types of layers:water,dry and three levels of oil(I oil layer,II oil layer,III oil layer).The validation and test results of these seven optimized ML methods suggest the three ensemble methods perform better than the four single ML methods in reservoir identification.The XGBoost produced the model with the highest accuracy;up to 99%.The effective thickness of I and II oil layers determined during the reservoir identification was fed into the models for predicting production.Effective thickness considers the distribution of the water and the oil resulting in a more reasonable production prediction compared to predictions based on the overall reservoir thickness.To validate the superiority of the ML methods,reference models using overall reservoir thickness were built for comparison.The models based on effective thickness outperformed the reference models in every evaluation metric.The prediction accuracy of the ML models using effective thickness were 10%higher than that of reference model.Without the personal error or data distortion existing in traditional methods,this novel system realizes rapid analysis of data while reducing the time required to resolve reservoir classification and production prediction challenges.The ML models using the effective thickness obtained from reservoir identification were more accurate when predicting oil production compared to previous studies which use overall reservoir thickness.

Genesis, evolution and reservoir identification of a Neogene submarine channel in the southwestern Qiongdongnan Basin, South China Sea

A rarely reported middle-late Miocene-Pliocene channel(incised valley fill),the Huaguang Channel(HGC),has been found in the deep-water area of the southwestern Qiongdongnan Basin(QDNB).This channel is almost perpendicular to the orientation of another well-known,large,and nearly coeval submarine channel in this area.Based on the interpretation of high-resolution 3D seismic data,this study describes and analyzes the stratigraphy,tectonics,sedimentation,morphology,structure and evolution of HGC by means of well-seismic synthetic calibration,one-and two-dimensional forward modeling,attribute interpretation,tectonic interpretation,and gas detection.The HGC is located on the downthrown side of an earlier activated normal fault and grew northwestward along the fault strike.The channel is part of a slope that extends from the western Huaguang Sag to the eastern Beijiao Uplift.The HGC underwent four developmental stages:the(1)incubation(late Sanya Formation,20.4–15.5 Ma),(2)embryonic(Meishan Formation,15.5–10.5 Ma),(3)peak(Huangliu Formation,10.5–5.5 Ma)and(4)decline(Yinggehai Formation,5.5–1.9 Ma)stages.The channel sandstones have a provenance from the southern Yongle Uplift and filled the channel via multistage vertical amalgamation and lateral migration.The channel extended 42.5 km in an approximately straight pattern in the peak stage.At 10.5 Ma,sea level fell relative to its lowest level,and three oblique progradation turbidite sand bodies filled the channel from south to north.A channel sandstone isopach map demonstrated a narrow distribution in the early stages and a fan-shaped distribution in the late stage.The formation and evolution of the HGC were controlled mainly by background tectonics,fault strike,relative sea level change,and mass supply from the Yongle Uplift.The HGC sandstone reservoir is near the Huaguangjiao Sag,where hydrocarbons were generated.Channel-bounding faults and underlying faults link the source rock with the reservoir.A regionally extensive mudstone caprock overlies the channel sandstone.Two traps likely containing gas were recognized in a structural high upstream of the channel from seismic attenuation anomalies.The HGC will likely become an important oil and gas accumulation setting in the QDNB deep-water area.

Rapid identification of high-quality marine shale gas reservoirs based on the oversampling method and random forest algorithm

The identification of high-quality marine shale gas reservoirs has always been a key task in the exploration and development stage.However,due to the serious nonlinear relationship between the logging curve response and high-quality reservoirs,the rapid identification of high-quality reservoirs has always been a problem of low accuracy.This study proposes a combination of the oversampling method and random forest algorithm to improve the identification accuracy of high-quality reservoirs based on logging data.The oversampling method is used to balance the number of samples of different types and the random forest algorithm is used to establish a highprecision and high-quality reservoir identification model.From the perspective of the prediction effect,the reservoir identification method that combines the oversampling method and the random forest algorithm has increased the accuracy of reservoir identification from the 44%seen in other machine learning algorithms to 78%,and the effect is significant.This research can improve the identifiability of high-quality marine shale gas reservoirs,guide the drilling of horizontal wells,and provide tangible help for the precise formulation of marine shale gas development plans.

Spatial-temporal coupling between high-quality source rocks and reservoirs for tight sandstone oil and gas accumulations in the Songliao Basin, China

The spatial-temporal relationship between high-quality source rocks and reservoirs is a key factor when evaluating the formation,occurrence,and prospectivity of tight oil and gas reservoirs.In this study,we analyze the fundamental oil and gas accumulation processes occurring in the Songliao Basin,contrasting tight oil sand reservoirs in the south with tight gas sand reservoirs in the north.This is done using geochemical data,constant-rate and conventional mercury injection experiments,and fluid inclusion analyses.Our results demonstrate that as far as fluid mobility is concerned,the expulsion center coincides with the overpressure zone,and its boundary limits the occurrence of tight oil and gas accumulations.In addition,the lower permeability limit of high-quality reservoirs,controlled by pore-throat structures,is 0.1×10^-3μm^2 in the fourth member of the Lower Cretaceous Quantou Formation(K1q^4)in the southern Songliao Basin,and 0.05×10^-3μm^2 in the Lower Cretaceous Shahezi Formation(K1sh)in the northern Songliao Basin.Furthermore,the results indicate that the formation of tight oil and gas reservoirs requires the densification of reservoirs prior to the main phase of hydrocarbon expulsion from the source rocks.Reservoir“sweet spots”develop at the intersection of high-quality source rocks(with high pore pressure)and reservoirs(with high permeability).

Characteristics of Shale Reservoir and Sweet Spot Identification of the Lower Cambrian Niutitang Formation in Northwestern Hunan Province, China

The accumulation and productivity of shale gas are mainly controlled by the characteristics of shale reservoirs;study of these characteristics forms the basis for the shale gas exploitation of the Lower Cambrian Niutitang Formation(Fm),Southern China.In this study,core observation and lithology study were conducted along with X-ray diffraction(XRD)and electronic scanning microscopy(SEM)examinations and liquid nitrogen(N2)adsorption/desorption and CH4 isothermal adsorption experiments for several exploration wells in northwestern Hunan Province,China.The results show that one or two intervals with high-quality source rocks(TOC>2 wt%)were deposited in the deep-shelf facies.The source rocks,which were mainly composed of carbonaceous shales and siliceous shales,had high quartz contents(>40 wt%)and low clay mineral(<30 wt%,mainly illites)and carbonate mineral(<20 wt%)contents.The SEM observations and liquid nitrogen(N2)adsorption/desorption experiments showed that the shale is tight,and nanoscale pores and microscale fractures are well developed.BJH volume(VBJH)of shale ranged from 2.144×10^-3 to 20.07×10^-3 cm^3/g,with an average of 11.752×10^-3 cm3/g.Pores mainly consisted of opened and interconnected mesopores(2–50 nm in diameter)or macropores(>50 nm in diameter).The shale reservoir has strong adsorption capacity for CH4.The Langmuir volume(VL)varied from 1.63 to 7.39 cm^3/g,with an average of 3.95 cm^3/g.The characteristics of shale reservoir are controlled by several factors:(1)A deep muddy continental shelf is the most favorable environment for the development of shale reservoirs,which is controlled by the development of basic materials.(2)The storage capacity of the shale reservoir is positively related to the TOC contents and plastic minerals and negatively related to cement minerals.(3)High maturity or overmaturity leads to the growth of organic pores and microfractures,thereby improving the reservoir storage capacity.It can be deduced that the high percentage of residual gas in Niutitang Fm results from the strong reservoir storage capacity of adsorbed gas.Two layers of sweet spots with strong storage capacity of free gas,and they are characterized by the relatively high TOC contents ranging from 4 wt%to 8 wt%.

Comprehensive security risk factor identification for small reservoirs with heterogeneous data based on grey relational analysis model

Identification of security risk factors for small reservoirs is the basis for implementation of early warning systems.The manner of identification of the factors for small reservoirs is of practical significance when data are incomplete.The existing grey relational models have some disadvantages in measuring the correlation between categorical data sequences.To this end,this paper introduces a new grey relational model to analyze heterogeneous data.In this study,a set of security risk factors for small reservoirs was first constructed based on theoretical analysis,and heterogeneous data of these factors were recorded as sequences.The sequences were regarded as random variables,and the information entropy and conditional entropy between sequences were measured to analyze the relational degree between risk factors.Then,a new grey relational analysis model for heterogeneous data was constructed,and a comprehensive security risk factor identification method was developed.A case study of small reservoirs in Guangxi Zhuang Autonomous Region in China shows that the model constructed in this study is applicable to security risk factor identification for small reservoirs with heterogeneous and sparse data.

Features and genesis of Paleogene high-quality reservoirs in lacustrine mixed siliciclastic–carbonate sediments, central Bohai Sea, China

The characteristics and formation mechanisms of the mixed siliciclastic-carbonate reservoirs of the Paleogene Shahejie Formation in the central Bohai Sea were examined based on polarized light microscopy and scanning electron microscopy observations, X-ray diffrac- tometry, carbon and oxygen stable isotope geochemistry, and integrated fluid inclusion analysis. High-quality reservoirs are mainly distributed in Type I and Type II mixed siliciclastic-carbonate sediments, and the dominant pore types include residual primary intergranular pores and intrafossil pores, feldspar dissolution pores mainly devel- oped in Type II sediments. Type I mixed sediments are characterized by precipitation of early pore-lining dolo- mite, relatively weak mechanical compaction during deep burial, and the occurrence of abundant oil inclusions in high-quality reservoirs. Microfacies played a critical role in the formation of the mixed reservoirs, and high-quality reservoirs are commonly found in high-energy environ- ments, such as fan delta underwater distributary channels, mouth bars, and submarine uplift beach bars. Abundant intrafossil pores were formed by bioclastic decay, and secondary pores due to feldspar dissolution further enhance reservoir porosity. Mechanical compaction was inhibited by the precipitation of pore-lining dolomite formed during early stage, and oil emplacement has further led to the preservation of good reservoir quality.

Identification of the Quaternary low gas-saturation reservoirs in the Sanhu area of the Qaidam Basin,China

Low gas-saturation reservoirs are gas bearing intervals whose gas saturation is less than 47%. They are common in the Quaternary of the Sanhu area in the Qaidam Basin.Due to the complex genesis mechanisms and special geological characteristics,the logging curves of low gas-saturation reservoirs are characterized by ambiguity and diversity,namely without significant log response characteristics. Therefore,it is particularly difficult to identify the low gas-saturation reservoirs in the study area.In addition,the traditional methods such as using the relations among lithology,electrical property,physical property and gas bearing property,as well as their threshold values,can not effectively identify low gas-saturation reservoirs.To solve this problem,we adopt the decision tree,support vector machine and rough set methods to establish a predictive model of low gas-saturation reservoirs,which is capable of classifying a mass of multi-dimensional and fuzzy data.According to the transparency of learning processes and the understandability of learning results,the predictive model was also revised by absorbing the actual reservoir characteristics.Practical applications indicate that the predictive model is effective in identifying low gas-saturation reservoirs in the study area.

Controlling factors of high-quality volcanic reservoirs of Yingcheng Formation in the Songnan gas field

Predicting high-quality volcanic reservoirs is one of the key issues for oil and gas exploration in the Songnan gas field.Core,seismic,and measurement data were used to study the lithologies,facies,reservoir porosity,and reservoir types of the volcanic rocks in the Songnan gas field.The primary controlling factors and characteristics of the high-quality volcanic reservoirs of the Yingcheng Formation in the Songnan gas field were investigated,including the volcanic eruptive stage,edifice,edifice facies,cooling unit,lithology,facies,and diagenesis.Stages with more volatile content can form more high-quality reservoirs.The effusive rhyolite,explosive tuff,and tuff lava that formed in the crater,near-crater,and proximal facies and in the high-volatility cooling units of large acidic-lava volcanic edifices are the most favorable locations for the development of the high-quality reservoirs in the Songnan gas field.Diagenesis dissolution,which is controlled by tectonic action,can increase the size of secondary pores in reservoirs.Studying the controlling factors of the high-quality reservoirs can provide a theoretical basis for the prediction and analysis of high-quality volcanic reservoirs.

Division and identification of vertical reservoir units in Archaeozoic metamorphic buried hill of Bozhong Sag,Bohai Bay Basin,East China

Based on the data associated with cores,sidewall cores,casting thin sections,reservoir physical properties,conventional logging and imaging logging,the classification schemes of vertical reservoir units are proposed for the two types of Archaeozoic buried hills(exposed and covered ones)in the Bozhong Sag,Bohai Bay Basin.The geological characteristics and storage spaces of these reservoir units are described,and their identification markers in conventional and imaging log curves are established.The Archaeozoic metamorphic buried hills can be vertically classified into two primary reservoir units:weathering crust and inner buried hill.The weathering crust contains four secondary units,i.e.,the clay zone,weathered glutenite zone,leached zone,disaggregation zone;and the interiors contain two secondary units,i.e.,interior fracture zone and tight zone.In particular,the inner fracture zone was further divided into cataclasite belts and dense-fracture belts.It is proposed that the favorable reservoirs of exposed Archaeozoic metamorphic buried hills are mainly developed in four parts including weathered glutenite zone,leached zone,disintegration zone superposed with the cataclasite belt and the cataclasite belt of inner fracture zone,and are controlled by both weathering and tectonic actions.Favorable reservoirs in covered Archaeozoic metamorphic buried hills are mainly developed in the weathering crust superposed with the cataclasite belts and the cataclasite belts of inner fracture zone,and are mainly controlled by tectonic actions.

A new method for reservoir fluid identification

The wavelet transform （WT） method has been employed to decompose an original geophysical signal into a series of components containing different information about reservoir features such as pore fluids, lithology, and pore structure. We have developed a new method based on WT energy spectra analysis, by which the signal component reflecting the reservoir fluid property is extracted. We have successfully processed real log data from an oil field in central China using this method. The results of the reservoir fluid identification agree with the results of well tests.

Log identification method in complex sand reservoirs

In order to obtain effective parameters for complex sand reservoirs,a log evaluation method for relevant reservoir parameters is established based on an analysis in the gas-bearing sandstone with high porosity and low permeability,low porosity and permeability and on various characteristics of log responses to reservoir lithologies and physical properties in the Neopleozoic sand reservoir of the Ordos basin.This log evaluation method covers the Cook method that is used to evaluate the porosity and oiliness in high porosity and low permeability reservoirs and another method in which the mineral content,derived from geochemical logs,is used to identify formation lithologies.Some areas have high calcium and low silt content,not uniformly distributed,the results of which show up in the complex formation lithologies and conventional log responses with great deviation.The reliability of the method is verified by comparison with conventional log data and core analyses.The calculation results coincide with the core analytical data and gas tests,which indicate that this log evaluation method is available,provides novel ideas for study of similar complex reservoir lithologies and has some reference value.

Large-scale toppling slope under water level fluctuation of reservoir:A case of Yunnan Province,China

Landslides induced by reservoir inundation are common in Southwest China,negatively influencing hydropower stations.TheWunonglong hydropower station dam was constructed in the upper reaches of the Lancang River,accordingly causing the water level at the Lajinshengu slope to increase by 30 m.A tension crack with a visible depth of 8 m was observed in the upper sector of the Lajinshengu slope after reservoir impoundment for 170 d.In the following days,numerous cracks appeared on the surface of the slope,and the maximum displacement of the slope reached 3.22 m.Then,a large-scale active deformation body within the Lajinshengu slope formed with an area of 2.62×10^(5)m^(2)and a volume of 1.65×10^(7)m^(3).Detailed field investigations,on-site monitoring,and centrifugal model tests were carried out to analyze the surface features,deformation characteristics,and failure mechanism of the Lajinshengu slope.The results show that the slope is an ancient landslide,divided into two parts(i.e.zone A and zone B)by the gully.Zone B is a traction landslide caused by the displacement of zone A.The longterm inundation weakens the soft rock at the slope foot,intensifying the toppling of bedrock and consequently triggering the sliding of the overburden in zone A.The failure mode of the Lajinshengu slope is a typical case of toppling-sliding failure,and the underlying rock toppling drives the overlying sliding.In addition,early identification methods for toppling deformation covered by overburdened soil were proposed based on monitoring data and deformation signs.

Application of fluid modulus inversion to complex lithology reservoirs in deep-water areas

It has been a challenge to distinguish between seismic anomalies caused by complex lithology and hydrocarbon reservoirs using conventional fluid identification techniques,leading to difficulties in accurately predicting hydrocarbon-bearing properties and determining oil-water contacts in reservoirs.In this study,we built a petrophysical model tailored to the deep-water area of the Baiyun Sag in the eastern South China Sea based on seismic data and explored the feasibility of the tri-parameter direct inversion method in the fluid identification of complex lithology reservoirs,offering a more precise alternative to conventional techniques.Our research found that the fluid modulus can successfully eliminate seismic amplitude anomalies caused by lithological variations.Furthermore,the seismic databased direct inversion for fluid modulus can remove the cumulative errors caused by indirect inversion and the influence of porosity.We discovered that traditional methods using seismic amplitude anomalies were ineffective in detecting fluids,determining gas-water contacts,or delineating high-quality reservoirs.However,the fluid factor Kf,derived from solid-liquid decoupling,proved to be sensitive to the identification of hydrocarbon-bearing properties,distinguishing between high-quality and poor-quality gas zones.Our findings confirm the value of the fluid modulus in fluid identification and demonstrate that the tri-parameter direct inversion method can significantly enhance hydrocarbon exploration in deep-water areas,reducing associated risks.

The Fluid Identification Forward Modeling Study of Carbonate Cave Reservoir

The fluid identification of carbonate reservoir is a key factor to hydrocarbon exploration and reservoir development. In order to simulate the seismic response characteristics of the cave in the carbonate reservoir, three sets of models were designed, including the caves varied in width, the caves filled with different solids, and the oil-gas-water model. The numerical simulation technique was used to carry out the forward modeling and the AVO (Amplitude varies with offset) response characteristics of the three groups of models were analyzed. The results show that the AVO characteristics can be observed when the cave reaches a certain extent in the horizontal direction. When the surrounding rock is constant, the absolute value of the intercept of the AVO curve increases with the Vp/Vs decrease. The AVO technology can effectively identify the gas cave. The effect is not obvious to water or oil cave.

An Integrated Method of Data Mining and Flow Unit Identification for Typical Low Permeability Reservoir Prediction

With the development of oilfield exploration and mining, the research on continental oil and gas reservoirs has been gradually refined, and the exploration target of offshore reservoir has also entered the hot studystage of small sand bodies, small fault blocks, complex structures, low permeability and various heterogeneous geological bodies. Thus, the marine oil and gas development will inevitably enter thecomplicated reservoir stage;meanwhile the corresponding assessment technologies, engineering measures andexploration method should be designed delicately. Studying on hydraulic flow unit of low permeability reservoir of offshore oilfield has practical significance for connectivity degree and remaining oil distribution. An integrated method which contains the data mining and flow unit identification part was used on the flow unit prediction of low permeability reservoir;the predicted results?were compared with mature commercial system results for verifying its application. This strategy is successfully applied to increase the accuracy by choosing the outstanding prediction result. Excellent computing system could provide more accurate geological information for reservoir characterization.