An adaptive physics-informed deep learning method for pore pressure prediction using seismic data

Accurate prediction of formation pore pressure is essential to predict fluid flow and manage hydrocarbon production in petroleum engineering.Recent deep learning technique has been receiving more interest due to the great potential to deal with pore pressure prediction.However,most of the traditional deep learning models are less efficient to address generalization problems.To fill this technical gap,in this work,we developed a new adaptive physics-informed deep learning model with high generalization capability to predict pore pressure values directly from seismic data.Specifically,the new model,named CGP-NN,consists of a novel parametric features extraction approach(1DCPP),a stacked multilayer gated recurrent model(multilayer GRU),and an adaptive physics-informed loss function.Through machine training,the developed model can automatically select the optimal physical model to constrain the results for each pore pressure prediction.The CGP-NN model has the best generalization when the physicsrelated metricλ=0.5.A hybrid approach combining Eaton and Bowers methods is also proposed to build machine-learnable labels for solving the problem of few labels.To validate the developed model and methodology,a case study on a complex reservoir in Tarim Basin was further performed to demonstrate the high accuracy on the pore pressure prediction of new wells along with the strong generalization ability.The adaptive physics-informed deep learning approach presented here has potential application in the prediction of pore pressures coupled with multiple genesis mechanisms using seismic data.

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.

Geophysical prediction of organic matter abundance in source rocks based on geochemical analysis:A case study of southwestern Bozhong Sag,Bohai Sea,China

The Bozhong Sag is the largest petroliferous sag in the Bohai Bay Basin,and the source rocks of Paleogene Dongying and Shahejie Formations were buried deeply.Most of the drillings were located at the structural high,and there were few wells that met good quality source rocks,so it is difficult to evaluate the source rocks in the study area precisely by geochemical analysis only.Based on the Rock-Eval pyrolysis,total organic carbon(TOC)testing,the organic matter(OM)abundance of Paleogene source rocks in the southwestern Bozhong Sag were evaluated,including the lower of second member of Dongying Formation(E_(3)d2L),the third member of Dongying Formation(E_(3)d_(3)),the first and second members of Shahejie Formation(E_(2)s_(1+2)),the third member of Shahejie Formation(E_(2)s_(3)).The results indicate that the E_(2)s_(1+2)and E_(2)s_(3)have better hydrocarbon generative potentials with the highest OM abundance,the E_(3)d_(3)are of the second good quality,and the E_(3)d2L have poor to fair hydrocarbon generative potential.Furthermore,the well logs were applied to predict TOC and residual hydrocarbon generation potential(S_(2))based on the sedimentary facies classification,usingΔlogR,generalizedΔlogR,logging multiple linear regression and BP neural network methods.The various methods were compared,and the BP neural network method have relatively better prediction accuracy.Based on the pre-stack simultaneous inversion(P-wave impedance,P-wave velocity and density inversion results)and the post-stack seismic attributes,the three-dimensional(3D)seismic prediction of TOC and S_(2)was carried out.The results show that the seismic near well prediction results of TOC and S_(2)based on seismic multi-attributes analysis correspond well with the results of well logging methods,and the plane prediction results are identical with the sedimentary facies map in the study area.The TOC and S_(2)values of E_(2)s_(1+2)and E_(2)s_(3)are higher than those in E_(3)d_(3)and E_(3)d_(2)L,basically consistent with the geochemical analysis results.This method makes up the deficiency of geochemical methods,establishing the connection between geophysical information and geochemical data,and it is helpful to the 3D quantitative prediction and the evaluation of high-quality source rocks in the areas where the drillings are limited.

Facies-controlled prediction of dolomite reservoirs in the Middle Permian Qixia Formation in Shuangyushi,northwestern Sichuan Basin

The Middle Permian Qixia Formation in the Shuangyushi area,northwestern Sichuan Basin,develops shoal-facies dolomite reservoirs.To pinpoint promising reservoirs in the Qixia Formation,deep thin shoal-facies dolomite reservoirs were predicted using the techniques of pre-stack Kirchhoff-Q compensation for absorption,inverse Q filtering,low-to high-frequency compensation,forward modeling,and facies-controlled seismic meme inversion.The results are obtained in six aspects.First,the dolomite reservoirs mainly exist in the middle and lower parts of the second member of Qixia Formation(Qi2 Member),which coincide with the zones shoal cores are developed.Second,the forward modeling shows that the trough energy at the top and bottom of shoal core increases with increasing shoal-core thickness,and weak peak reflections are associated in the middle of shoal core.Third,five types of seismic waveform are identified through waveform analysis of seismic facies.Type-Ⅰ and Type-Ⅱ waveforms correspond to promising facies(shoal core microfacies).Fourth,vertically,two packages of thin dolomite reservoirs turn up in the sedimentary cycle of intraplatform shoal in the Qi2 Member,and the lower package is superior to the upper package in dolomite thickness,scale and lateral connectivity.Fifth,in plane,significantly controlled by sedimentary facies,dolomite reservoirs laterally distribute with consistent thickness in shoal cores at topographical highs and extend toward the break.Sixth,the promising prospects are the zones with thick dolomite reservoirs and superimposition of horstegraben structural traps.

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.

Research on Fracture Prediction Method Based on Multi-Source Information Fusion

Machine learning is a good method for predicting fracture by integrating multi-source information. Post-stack seismic attributes are commonly used to predict medium to large fractures, while pre-stack seismic attributes are proven to be more sensitive to small and micro sized fractures through forward modeling. Using machine learning algorithm to fuse information from different scales to predict fracture can greatly improve the accuracy of fracture prediction. On the basis of In-Situ stress prediction, the paper conducted post-stack seismic attribute analysis and pre-stack seismic attribute analysis, further studied on the sensitivity of seismic attributes to fracture and selected sensitive attributes, used the sensitivity log of well-bore fractures as the target log for learning, ultimately obtained a comprehensive body of fracture. Through blind well verification, the prediction results match well with the we1l data and the prediction results is highly consistent with the production data. The results of fracture prediction are reliable, and the research method has certain reference significance for fracture prediction.

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.

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.

SEISMIC DAMAGE PREDICTION ON MULTI-STORYBRIOK BUILDINGS WITH TWO FRAME-SHEAR-WALL-SUPPORTED STORIES

This paper presents a method for searching the weak story by using the ultimate shear force coefficient on the multi-story brick buildings with two frame-shear-wall-supported stories. The method of seismic damage prediction is discussed according to different weak stories. When the first story is t theweak one,the damage state of the building can be determined by the displacement ratio. The prediction method is also used in a practical engineering project.

Prediction of column failure modes based on artificial neural network

To implement the performance-based seismic design of engineered structures,the failure modes of members must be classified.The classification method of column failure modes is analyzed using data from the Pacific Earthquake Engineering Research Center(PEER).The main factors affecting failure modes of columns include the hoop ratios,longitudinal reinforcement ratios,ratios of transverse reinforcement spacing to section depth,aspect ratios,axial compression ratios,and flexure-shear ratios.This study proposes a data-driven prediction model based on an artificial neural network(ANN)to identify the column failure modes.In this study,111 groups of data are used,out of which 89 are used as training data and 22 are used as test data,and the ANN prediction model of failure modes is developed.The results show that the proposed method based on ANN is superior to traditional methods in identifying the column failure modes.

Seismological method for prediction of areal rockbursts in deep mine with seismic source mechanism and unstable failure theory

The research on the rock burst prediction was made on the basis of seismology,rock mechanics and the data from Dongguashan Copper Mine(DCM) ,the deepest metal mine in China.The seismic responses to mining in DCM were investigated through the analyses of the spatio-temporal distribution of hypocenters,apparent stress and displacement of seismic events,and the process of the generation of hazardous seismicity in DCM was studied in the framework of the theory of asperity in the seismic source mechanism.A method of locating areas with hazardous seismicity and a conceptual model of hazardous seismic nucleation in DCM were proposed.A criterion of rockburst prediction was analyzed theoretically in the framework of unstable failure theories,and consequently,the rate of change in the ratio of the seismic stiffness of rock in a seismic nucleation area to that in surrounding area,dS/dt,is defined as an index of the rockburst prediction.The possibility of a rockburst will increase if dS/dt>0,and the possibility of rock burst will decrease if dS/dt<0.The correctness of these methods is demonstrated by analyses of rock failure cases in DCM.

The Analysis of Seismic Data Structure and Oil and Gas Prediction

In this paper, a new concept called numerical structure of seismic data is introduced and the difference between numerical structure and numerical value of seismic data is explained. Our study shows that the numerical seismic structure is closely related to oil and gas-bearing reservoir, so it is very useful for a geologist or a geophysicist to precisely interpret the oil-bearing layers from the seismic data. This technology can be applied to any exploration or production stage. The new method has been tested on a series of exploratory or development wells and proved to be reliable in China. Hydrocarbon-detection with this new method for 39 exploration wells on 25 structures indi- cates a success ratio of over 80 percent. The new method of hydrocarbon prediction can be applied for: (1) depositional environment of reservoirs with marine fades, delta, or non-marine fades (including fluvial facies, lacustrine fades); (2) sedimentary rocks of reservoirs that are non-marine clastic rocks and carbonate rock; and (3) burial depths range from 300 m to 7000 m, and the minimum thickness of these reservoirs is over 8 m (main frequency is about 50 Hz).

Tunnel seismic tomography method for geological prediction and its application

Typical existing methods of tunnel geological prediction include negative apparent velocity, horizontal seismic profile, and the Tunnel Seismic Prediction （TSP） method as this technology is under development at home and abroad. Considering simpler observational methods and data processing, it is hard to accurately determine the seismic velocity of the wall rock in the front of the tunnel face. Therefore, applying these defective methods may result in inaccurate geological inferences which will not provide sufficient evidence for classifying the wall rock characteristics. This paper proposes the Tunnel Seismic Tomography （TST） method using a spatial observation arrangement and migration and travel time inversion image processing to solve the problem of analyzing the velocity structure of wall rock in the front of the tunnel face and realize accurate imaging of the geological framework of the tunnel wall rock. This method is very appropriate for geological prediction under complex geological conditions.

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.

Performance assessment of genetic programming(GP)and minimax probability machine regression(MPMR)for prediction of seismic ultrasonic attenuation

The determination of seismic attenuation （s） （dB/cm） is a challenging task in earthquake science. This article employs genetic programming （GP） and minimax probability machine regression （MPMR） for prediction of s. GP is developed based on genetic algo- rithm. MPMR maximizes the minimum probability of future predictions being within some bound of the true regression function. Porosity （n） （%）, permeability （k） （millidarcy）, grain size （d） （μm）, and clay content （c） （%） have been considered as inputs of GP and MPMR. The output of GP and MPMR is s. The developed GP gives an equation for prediction of s. The results of GP and MPMR have been compared with the artificial neural net- work. This article gives robust models based on GP and MPMR for prediction of s.

Comparative Study of Global Seismicity on the Hot Engine Belt and the Cooling Seismic Belt—Improvement on Research Ideas of Earthquake Prediction

The study in this paper analyzes and compares the distribution on the global engine active seismic zone and cooling seismic belt basing on the ANSS earthquake catalog from Northern California Earthquake Data Center. An idea of the seismogenesis and earthquake prediction research is achieved by showing the stratigraphic structure in the hot engine belt. The results show that the main engine and its seismic cones are the global seismic activity area, as well as the subject of global geological disaster. Based on the conjecture of other stratum structure, the energy of crustal strong earthquake and volcano activities probably originates from the deep upper mantle. It is suggested that the research on earthquake and volcano prediction should focus on the monitor and analysis on the sub-crustal earthquake activities.

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.

NEURAL NETWORKS PREDICTION FOR SEISMIC RESPONSE OF STRUCTURE UNDER THE LEVENBERG-MARQUARDT ALGORITHM

Objective To investigate the prediction effect of neural networks for seismic response of structure under the Levenberg Marquardt(LM) algorithm. Results Based on identification and prediction ability of neural networks for nonlinear systems, and combined with LM algorithm, a multi layer forward networks is adopted to predict the seismic responses of structure. The networks is trained in batch by the shaking table test data of three floor reinforced concrete structure firstly, then the seismic responses of structure are predicted under the unused excitation data, and the predict responses are compared with the experiment responses. The error curves between the prediction and the experimental results show the efficiency of the method. Conclusion LM algorithm has very good convergence rate, and the neural networks can predict the seismic response of the structure well.

Prediction of Shale Gas Pressure based on Multi-channel Seismic Inversion in Fuling

The accurate prediction of formation pressure is important in oil/gas exploration and development.However,the achievement of this goal remains challenging,due to insufficient logging data and the low predictive data accuracy from seismic data.In this work,a case study was carried out in the Baima area of Wulong,in order to develop a workflow for accurately predicting shale gas formation pressure.The multi-channel stack method was first used,as well as the inversion of single-channel seismic data,to construct velocity and density models of the formation.Combined with the existing welllogging data,the velocity and density models of the whole well section were established.The shale gas formation pressure was then estimated using the Eaton method.The results show that the multi-channel seismic stacking method has a higher accuracy than the inversion of the formation velocity obtained by the single-channel seismic method.The discrepancies between our predicted formation pressure and the actual formation pressure measurement are within an acceptable range,indicating that our workflow is effective.

Seismic hazard prediction using multispectral amplification maps in a complex topographic area: A case study of Qiaozhuang town, Sichuan Province, Southwest China

Earthquakes can cause widely distributed slope failures and damage in mountainous areas.The accurate prediction of ground motions in mountainous areas is essential for managing the seismic risk of urban cities near mountains but is restricted primarily by complex seismic site amplification effects in areas of uneven terrain.This study selected Qiaozhuang town located in the Qingchuan–Pingwu fault zone,Southwest China,as a case study.A simulator for mapped seismic responses using a hybrid model(Si Se RHMap)was applied to compute the multispectral seismic topographic amplification maps at the three slope units surrounding Qiaozhuang town(Weigan hill,Mt.Dong,and Mt.Shizi).Post-earthquake damage survey maps,1 D seismic site response spectral ratios,and H/V spectral ratios of earthquake data were used to validate the computed seismic site amplification factors and resonance frequencies.The results suggest that strong topographic amplification effects usually occur at distinct slope locations,such as hilltops,convex slope positions,upslope,and narrow ridges.The computed topographic amplification factors in the study area reached up to 2.4 at upslope or hilltops,and the resonance frequencies were between 3 and 10 Hz.Topographic effects can be as important as stratigraphic effects when assessing seismic amplification effects in the study area.We conclude that both topographic and stratigraphic effects should be considered in the comprehensive seismic hazard assessment of the study area or other similar mountain towns.