Machine learning for carbonate formation drilling: Mud loss prediction using seismic attributes and mud loss records

Due to the complexity and variability of carbonate formation leakage zones, lost circulation prediction and control is one of the major challenges of carbonate drilling. It raises well-control risks and production expenses. This research utilizes the H oilfield as an example, employs seismic features to analyze mud loss prediction, and produces a complete set of pre-drilling mud loss prediction solutions. Firstly, 16seismic attributes are calculated based on the post-stack seismic data, and the mud loss rate per unit footage is specified. The sample set is constructed by extracting each attribute from the seismic trace surrounding 15 typical wells, with a ratio of 8:2 between the training set and the test set. With the calibration results for mud loss rate per unit footage, the nonlinear mapping relationship between seismic attributes and mud loss rate per unit size is established using the mixed density network model.Then, the influence of the number of sub-Gausses and the uncertainty coefficient on the model's prediction is evaluated. Finally, the model is used in conjunction with downhole drilling conditions to assess the risk of mud loss in various layers and along the wellbore trajectory. The study demonstrates that the mean relative errors of the model for training data and test data are 6.9% and 7.5%, respectively, and that R2is 90% and 88%, respectively, for training data and test data. The accuracy and efficacy of mud loss prediction may be greatly enhanced by combining 16 seismic attributes with the mud loss rate per unit footage and applying machine learning methods. The mud loss prediction model based on the MDN model can not only predict the mud loss rate but also objectively evaluate the prediction based on the quality of the data and the model.

Seismic attributes optimization and application in reservoir prediction

Petroleum geophysicists recognize that many parameters related to oil and gas reservoirs are predicted using seismic attribute data. However, how best to optimize the seismic attributes, predict the character of thin sandstone reservoirs, and enhance the reservoir description accuracy is an important goal for geologists and geophysicists. Based on the theory of main component analysis, we present a new optimization method, called constrained main component analysis. Modeling estimates and real application in an oilfield show that it can enhance reservoir prediction accuracy and has better applicability.

Ordovician limestone aquosity prediction using nonlinear seismic attributes:Case from the Xutuan coal mine

Ordovician limestone water is coal mines. In this paper, we analyze the the main source of water inrush in North China characteristic of three kinds of nonlinear seismic attributes, such as the largest lyapunov exponent,fractal dimension and entropy and introduce their calculation methods. Taking the 81st and 82nd coal districts in the Xutuan coal mine as examples, we extract the three seismic attributes based on the 3D prestack migration seismic data of this area, which can display the Ordovician limestone fracture distribution in the mine. We comprehensively analyzed the three nonlinear seismic attributes and compared the results with transient electromagnetic exploration results and determined the possible Ordovician limestone aquosity distribution. This demonstrated that the nonlinear seismic attributes technology is an effective approach to predict the aquosity of Ordovician limestone.

Estimation of reservoir porosity using probabilistic neural network and seismic attributes

Porosity is one of the most important properties of oil and gas reservoirs. The porosity data that come from well log are only available at well points. It is necessary to use other method to estimate reservoir porosity.Seismic data contain abundant lithological information. Because there are inherent correlations between reservoir property and seismic data,it is possible to estimate reservoir porosity by using seismic data and attributes.Probabilistic neural network is a powerful tool to extract mathematical relation between two data sets. It has been used to extract the mathematical relation between porosity and seismic attributes. Firstly,a seismic impedance volume is calculated by seismic inversion. Secondly,several appropriate seismic attributes are extracted by using multi-regression analysis. Then a probabilistic neural network model is trained to obtain a mathematical relation between porosity and seismic attributes. Finally,this trained probabilistic neural network model is implemented to calculate a porosity data volume. This methodology could be utilized to find advantageous areas at the early stage of exploration. It is also helpful for the establishment of a reservoir model at the stage of reservoir development.

Application of AVO and Seismic Attributes Techniques for Characterizing Pliocene Sand Reservoirs in Darfeel Field, Eastern Mediterranean, Egypt

Mediterranean Sea considered as a main hydrocarbon province in Egypt as a huge reservoirs have been discovered till now. Port Fouad marine is a gas and condensate field located in Eastern Mediterranean Sea about 30 KM off Egyptian coast, in a water depth of about 30 m. The Concession is operated by PETROBEL on behalf of Petrosaid (Port Said Petroleum Company). The field was put on production on April 1996, from the Miocene turbidities sands of Wakar Formation plus Pilocene Kafr EL Sheikh Formation. Darfeel field is located within Port Fouad Concession, seven wells have been drilled till now and producing from Pliocene section (Kafr El Sheikh Formation). Pliocene is the main reservoir in Darfeel field which characterized by turbidities sand stone. The aim of this work is to identify the distribution of turbidities sand and characterize sand reservoirs using AVO (amplitude verses offset) and seismic attributes techniques. The workflow is starting from conventional seismic interpretation, maps (time, depth, and amplitude), depositional environments, and finally structure setting. In addition to use some of unconventional seismic interpretation such as seismic attributes. AVO analysis and attributes had been applied in a temp of differentiate between gas sand reservoirs and non-gas reservoirs. The final result aid to identify the reservoir distribution and characterization of sand reservoirs through the field. So, the use of different seismic techniques is powerful techniques in identifying reservoir distribution.

Integrating the geology, seismic attributes, and production of reservoirs to adjust interwell areas: A case from the Mangyshlak Basin of West Kazakhstan

Dynamic models of the seismic,geological,and flow characteristics of a reservoir are the main tool used to evaluate the potential of drilling new infill wells.Static geological models are mainly based on borehole data combined with dynamic analyses of production dynamics.They are used to determine the redevelopment of and adjustments to new drilling locations;however,such models rarely incorporate seismic data.Consequently,it is difficult to control the changes in geological models between wells,which results in the configuration of well positions and predicted results being less than ideal.To improve the development of adjusted areas in terms of their remaining oil contents,we developed a new integrated analysis that combines static sediment modelling,including microfacies analysis(among other reservoir and seismic properties),with production behaviours.Here,we illustrate this new process by(1)establishing favourable areas for static geological analysis;(2)studying well recompletion potential and the condition of non-producing wells;(3)conducting interwell analyses with seismic and sedimentary data;(4)identifying potential sites constrained by seismic and geological studies,as well as initial oilfield production;(5)providing suggestions in a new well development plan.

Modeling of the Shale Volume in the Hendijan Oil Field Using Seismic Attributes and Artificial Neural Networks

Petrophysical properties have played an important and definitive role in the study of oil and gas reservoirs,necessitating that diverse kinds of information are used to infer these properties.In this study,the seismic data related to the Hendijan oil field were utilised,along with the available logs of 7 wells of this field,in order to use the extracted relationships between seismic attributes and the values of the shale volume in the wells to estimate the shale volume in wells intervals.After the overall survey of data,a seismic line was selected and seismic inversion methods(model-based,band limited and sparse spike inversion)were applied to it.Amongst all of these techniques,the model-based method presented the better results.By using seismic attributes and artificial neural networks,the shale volume was then estimated using three types of neural networks,namely the probabilistic neural network(PNN),multi-layer feed-forward network(MLFN)and radial basic function network(RBFN).

Analysis of Information of Oil-bearing Reservoir Using Seismic Attributes Technique——A Case Study of HD4 Oilfield, Tarim Basin

The theoretical and practical analysis of reservoir thickness and oil-bearing information of thin reservoirs is performed by using seismic attributes and forward modelling. The results show that thin reservoir can be recognized using seismic attributes technique when its thickness is less than 1/4 of wavelength. Through analyzing the influence of tuning effect, the relationship between thin layer thickness and tuning amplitude is well revealed. A precise structure interpretation is conducted using relative amplitude preserved high-resolution seismic data. By taking the geologic condition and well data into account, the distribution of oil and gas of HD4 oilfield is analyzed and predicted. based on seismic attributes. The result is helpful to promote the exploration and development in this oilfield.

Applications of Amplitude versus Offset and Seismic Attributes for Perceiving Messinian Reservoirs in Nidoco Field, Nile Delta, Egypt

Nile Delta which covers approximately 60,000 square kilometers represents the most important gas province in Egypt whereas its fields provide two-thirds of the gas production in Egypt. The Nile Delta province begins to display its hydrocarbon potentiality in the early 1960s. Nidoco field is located in the shallow water offshore Nile delta. Abu Madi formation (Messinian age) is the most important formation through all the section where it represents the main gas producing reservoirs in the Field. The production of the field is coming from two sand reservoir levels;Abu Madi level 2&3 which are characterized by fluvial-deltaic sandstones. The purpose of this paper is to perceive the Messinian gas bearing reservoirs and channelized sand distribution inside Abu Madi formation using seismic attributes and amplitude versus offset (AVO) technique. The results indicated that the seismic attributes and AVO aided to give a complete picture about the Messinian reservoirs distribution and characterization in the field. Also the results show that there are still promising locations of prospective Abu Madi Level 2&3 which are proposed to be drilled in the field.

Seismic attributes and integrated prediction of fractured and caved carbonate reservoirs in the Tarim Basin,China

The carbonate reservoirs in the Tarim Basin are characterized by anisotropy and strong heterogeneity.Combined with an integrated analysis of data from seismic,geology,and drilling results,a series of attributes which are suitable for fractured and caved carbonate reservoir prediction is discussed,including amplitude,coherence analysis,spectra decomposition,seismic absorption attenuation analysis and impedance inversion.Moreover,3-D optimization of these attributes is achieved by integration of multivariate discriminant analysis and principle component analysis,where the logging data are taken as training samples.Using the optimized results,the spatial distribution and configuration features of the caved reservoirs can be characterized in detail.This technique not only improves the understanding of the spatial distribution of current reservoirs but also provides a significant basis for the discovery and production of carbonate reservoirs in the Tarim Basin.

Reservoir prediction using multi-wave seismic attributes

The main problems in seismic attribute technology are the redundancy of data and the uncertainty of attributes, and these problems become much more serious in multi-wave seismic exploration. Data redundancy will increase the burden on interpreters, occupy large computer memory, take much more computing time, conceal the effective information, and especially cause the ＂curse of dimension＂. Uncertainty of attributes will reduce the accuracy of rebuilding the relationship between attributes and geological significance. In order to solve these problems, we study methods of principal component analysis （PCA）, independent component analysis （ICA） for attribute optimization and support vector machine （SVM） for reservoir prediction. We propose a flow chart of multi-wave seismic attribute process and further apply it to multi-wave seismic reservoir prediction. The processing results of real seismic data demonstrate that reservoir prediction based on combination of PP- and PS-wave attributes, compared with that based on traditional PP-wave attributes, can improve the prediction accuracy.

Reservoir heterogeneity analysis using multi-directional textural attributes from deep learning-based enhanced acoustic impedance inversion:A study from Poseidon,NW shelf Australia

Reservoir heterogeneities play a crucial role in governing reservoir performance and management.Traditionally,detailed and inter-well heterogeneity analyses are commonly performed by mapping seismic facies change in the seismic data,which is a time-intensive task.Many researchers have utilized a robust Grey-level co-occurrence matrix(GLCM)-based texture attributes to map reservoir heterogeneity.However,these attributes take seismic data as input and might not be sensitive to lateral lithology variation.To incorporate the lithology information,we have developed an innovative impedance-based texture approach using GLCM workflow by integrating 3D acoustic impedance volume(a rock propertybased attribute)obtained from a deep convolution network-based impedance inversion.Our proposed workflow is anticipated to be more sensitive toward mapping lateral changes than the conventional amplitude-based texture approach,wherein seismic data is used as input.To evaluate the improvement,we applied the proposed workflow to the full-stack 3D seismic data from the Poseidon field,NW-shelf,Australia.This study demonstrates that a better demarcation of reservoir gas sands with improved lateral continuity is achievable with the presented approach compared to the conventional approach.In addition,we assess the implication of multi-stage faulting on facies distribution for effective reservoir characterization.This study also suggests a well-bounded potential reservoir facies distribution along the parallel fault lines.Thus,the proposed approach provides an efficient strategy by integrating the impedance information with texture attributes to improve the inference on reservoir heterogeneity,which can serve as a promising tool for identifying potential reservoir zones for both production benefits and fluid storage.

Quantitative prediction of channel sand bodies based on seismic peak attributes in the frequency domain and its application

The boundary identification and quantitative thickness prediction of channel sand bodies are always difficult in seismic exploration.We present a new method for boundary identification and quantitative thickness prediction of channel sand bodies based on seismic peak attributes in the frequency domain.Using seismic forward modeling of a typical thin channel sand body,a new seismic attribute-the ratio of peak frequency to amplitude was constructed.Theoretical study demonstrated that seismic peak frequency is sensitive to the thickness of the channel sand bodies,while the amplitude attribute is sensitive to the strata lithology.The ratio of the two attributes can highlight the boundaries of the channel sand body.Moreover,the thickness of the thin channel sand bodies can be determined using the relationship between seismic peak frequency and thin layer thickness.Practical applications have demonstrated that the seismic peak frequency attribute can depict the horizontal distribution characteristics of channels very well.The ratio of peak frequency to amplitude attribute can improve the identification ability of channel sand body boundaries.Quantitative prediction and boundary identification of channel sand bodies with seismic peak attributes in the frequency domain are feasible.

Integration of Core Data, Well Logs and Seismic Attributes for Identification of the Low Reservoir Quality Units with Unswept Gas in the Carbonate Rocks of the World's Largest Gas Field

Tight zones of the gas bearing Kangan and Dalan formations of the South Pars gas field contain a considerable amount of unswept gas due to their low porosity, low permeability and isolated pore types. The current study, integrates core data, rock elastic properties and 3D seismic attributes to delineate fight and low-reservoir-quality zones of the South Pars gas field. In the first step, the dynamic reservoir geomechanical parameters were calculated based on empirical relationships from well log data. The log-derived elastic moduli were validated with the available laboratory measurements of core data. Cross plots between estimated porosity and elastic parameters based on Young＇s modulus indicate that low porosity zone coincide with high values of Young＇s module. The results were validated with petro- graphic studies of the available thin sections. The core samples with low porosity and permeability are correlated with strong rocks with tight matrix frameworks and high elastic values. Subsequently, rock elastic properties including Young＇s modulus and Poisson＇s ratio along with porosity were estimated by using neural networks from a collection of 3D post-stack seismic attributes, such as acoustic impedance （ALl）, instantaneous phase of AI and apparent polarity. Distinguishing low reservoir quality areas in pay zones with unswept gas is then facilitated by locating low porosity and high elastic modulus values. An- hydrite zones are identified and eliminated as non-pay zones due to their characterization of zero porosi- ty and high Young modulus values. The methodology described has applications for unconventional re- servoirs more generally, because it is able to distinguish low porosity and permeability zones that are po- tentially productive from those unprospective zones with negligible reservoir quality.

Identification of gas zones and chimneys using seismic attributes analysis at the Scarab field,offshore,Nile Delta,Egypt

Seismic attributes supported by composite logs are the best way that can enable the interpreter to understand seismic data very well and generate a new view of the output results.Detection of the reservoir zone can be enhanced by analyzing wells log data based on Gamma-ray,Resistivity,and Vp sonic logs respectively.Composite logs of Scarab-1,Scarab-De,Scarab-Da,Scarab-Dd,and Scarab-2 wells indicate the lateral and vertical variation of the gas reservoir in ElWastani Formation.However,there are several seismic attributes that can be used to support reservoirs identification.For enhancement the detection of the hydrocarbon reservoirs,it is important to carefully analyze the 2D seismic data,which in this study will be primarily prepared to enhance seismic attributes results for the identification of gas chimneys,gas zones as channels,enhance stratigraphic and structural interpretations.In this article,we have performed data conditioning,quality control and seismic well ties including the preliminary wavelet extractions to get accurate output.Then,we have extracted of several classes of physical,geometrical and complex attributes as a direct hydrocarbon indicator to identify the gas zones,channels and chimneys and to identify the faults and discontinuities.The main contribution of this work is to provide a more detailed seismic reflection image supported by several seismic attributes classes and well logs to show a visual and quantitative evidence to identify the gas channels and gas chimneys with improving the detection of the faults and discontinuities.

3D Seismic Attributes for Structural Analysis in Compressional Context: A Case Study from Western Sichuan Basin

Compressional region usually forms complex thrust faults system, which is difficult to identify using traditional migration profiles. The successful application of three-dimensional（3D） seismic attributes analysis greatly reduces the difficulty, and improves the accuracy and efficiency of seismic interpretation and structural analysis. In this paper, we took Qiongxi area in the compressional region of western Sichuan as an example, using two 3D seismic attributes, coherence and instantaneous phase, to identify fault assemblages and variations both vertically and laterally. The results show that the study area mainly consists of NS-, NE- and NEE-trending faults. The NS-trending faults are the largest and have a component of sinistral slip controlling the formation of NEE-trending faults, while the NE-trending faults are intermediate in scale, formed earlier and were cut by the NS-trending faults. Our results demonstrate that using seismic attributes for structural analysis have the following advantages：（1） more details of major fault zones,（2） highlighting minor faults which are hardly traced in seismic migration cube, and（3） easier acquisition of accurate fault systems. The application of seismic attributes provides a new idea for deciphering fine and complicated structures, and will significantly contribute to the development of objective and precise geological interpretation in the future.

Quantitative estimation of bubble volume fraction of submarine seep plumes by modeling seismic oceanography data

Submarine seep plumes are a natural phenomenon in which different types of gases migrate through deep or shallow subsurface sediments and leak into seawater in pressure gradient.When detected using acoustic data,the leaked gases frequently exhibit a flame-like structure.We numerically modelled the relationship between the seismic response characteristic and bubble volume fraction to establish the bubble volume fraction in the submarine seep plume.Results show that our models are able to invert and predict the bubble volume fraction from field seismic oceanography data,by which synthetic seismic sections in different dominant frequencies could be numerically simulated,seismic attribute sections(e.g.,instantaneous amplitude,instantaneous frequency,and instantaneous phase)extracted,and the correlation between the seismic attributes and bubble volume fraction be quantitatively determined with functional equations.The instantaneous amplitude is positively correlated with bubble volume fraction,while the instantaneous frequency and bubble volume fraction are negatively correlated.In addition,information entropy is introduced as a proxy to quantify the relationship between the instantaneous phase and bubble volume fraction.As the bubble volume fraction increases,the information entropy of the instantaneous phase increases rapidly at the beginning,followed by a slight upward trend,and finally stabilizes.Therefore,under optimal noise conditions,the bubble volume fraction of submarine seep plumes can be inverted and predicted based on seismic response characteristics in terms of seismic attributes.

Seismic attribute extraction based on HHT and its application in a marine carbonate area

The Hilbert-Huang transform（HHT） is a new analysis method suitable for nonlinear and non-stationary signals.It is very appropriate to seismic signals because they show both non-stationary and nonlinear characteristics.We first introduce the realization of HHT empirical mode decomposition（EMD） and then comparatively analyze three instantaneous frequency algorithms based on intrinsic mode functions（IMF） resulting from EMD,of which one uses the average instantaneous frequency of two sample intervals having higher resolution which can determine that the signal frequency components change with time.The method is used with 3-D poststack migrated seismic data of marine carbonate strata in southern China to effectively extract the three instantaneous attributes.The instantaneous phase attributes of the second intrinsic mode functions（IMF2） better describe the reef facies of the platform margin and the IMF2 instantaneous frequency attribute has better zoning.Combining analysis of the three IMF2 instantaneous seismic attributes and drilling data can identify the distribution of sedimentary facies well.

Application of seismic multi-attribute fusion method based on D-S evidence theory in prediction of CBM-enriched area

D-S evidence theory provides a good approach to fuse uncertain inlbrmation. In this article, we introduce seismic multi-attribute fusion based on D-S evidence theory to predict the coalbed methane （CBM） concentrated areas. First, we choose seismic attributes that are most sensitive to CBM content changes with the guidance of CBM content measured at well sites. Then the selected seismic attributes are fused using D-S evidence theory and the fusion results are used to predict CBM-enriched area. The application shows that the predicted CBM content and the measured values are basically consistent. The results indicate that using D-S evidence theory in seismic multi-attribute fusion to predict CBM-enriched areas is feasible.

Geometry and formation mechanism of tension gashes and their implication on the hydrocarbon accumulation in the deep-seated strata of sedimentary basin:A case from Shunnan area of Tarim Basin

With the theoretical and technological developments related to cratonic strike-slip faults,the Shuntuoguole Low Uplift in the Tarim Basin has attracted considerable attention recently.Affected by multi-stage tectonic movements,the strike-slip faults have controlled the distribution of hydrocarbon resources owing to the special fault characteristics and fault-related structures.In contrast,the kinematics and formation mechanism of strike-slip faults in buried sedimentary basins are difficult to investigate,limiting the discussion of these faults and hydrocarbon accumulation.In this study,we identified the characteristics of massive sigmoidal tension gashes(STGs)that formed in the Shunnan area of the Tarim Basin.High-resolution three-dimensional seismic data and attribute analyses were used to investigate their geometric and kinematic characteristics.Then,the stress state of each point of the STGs was calculated using seismic curvature attributes.Finally,the formation mechanism of the STGs and their roles in controlling hydrocarbon migration and accumulation were discussed.The results suggest that:(1)the STGs developed in the Shunnan area have a wide distribution,with a tensile fault arranged in an enéchelon pattern,showing an S-shaped bending.These STGs formed in multiple stages,and differential rotation occurred along the direction of strike-slip stress during formation.(2)Near the principal displacement zone of the strike-slip faults,the stress value of the STGs was higher,gradually decreasing at both ends.The shallow layer deformation was greater than the deep layer deformation.(3)STGs are critical for connecting source rocks,migrating oil and gas,sealing horizontally,and developing efficient reservoirs.This study not only provides seismic evidence for the formation and evolution of super large STGs,but also provides certain guidance for oil and gas exploration in this area.