Integrated Reservoir Prediction and Oil-Gas Evaluation in the Maoshan Area

The Maoshan area is an area with well-developed igneous rocks and complex structures. The thickness of the reservoirs is generally small. The study of the reservoirs is based on seismic data, logging data and geological data. Using techniques and software such as Voxelgeo, BCI, RM, DFM and AP, the authors have made a comprehensive analysis of the lateral variation of reservoir parameters in the Upper Shazu bed of the third member of the Palaeogene Funing Formation, and compiled the thickness map of the Shazu bed. Also, with the data from ANN, BCI and the abstracting method for seismic characteristic parameters in combination with the structural factors, the authors have tried the multi-parameter and multi-method prediction of petroleum, delineated the potential oil and gas areas and proposed two well sites. The prediction of oil and gas for Well JB2 turns out to be quite successful.

Time series prediction of reservoir bank landslide failure probability considering the spatial variability of soil properties

Historically,landslides have been the primary type of geological disaster worldwide.Generally,the stability of reservoir banks is primarily affected by rainfall and reservoir water level fluctuations.Moreover,the stability of reservoir banks changes with the long-term dynamics of external disastercausing factors.Thus,assessing the time-varying reliability of reservoir landslides remains a challenge.In this paper,a machine learning(ML)based approach is proposed to analyze the long-term reliability of reservoir bank landslides in spatially variable soils through time series prediction.This study systematically investigated the prediction performances of three ML algorithms,i.e.multilayer perceptron(MLP),convolutional neural network(CNN),and long short-term memory(LSTM).Additionally,the effects of the data quantity and data ratio on the predictive power of deep learning models are considered.The results show that all three ML models can accurately depict the changes in the time-varying failure probability of reservoir landslides.The CNN model outperforms both the MLP and LSTM models in predicting the failure probability.Furthermore,selecting the right data ratio can improve the prediction accuracy of the failure probability obtained by ML models.

Complementary testing and machine learning techniques for the characterization and prediction of middle Permian tight gas sandstone reservoir quality in the northeastern Ordos Basin, China

In this study, an integrated approach for diagenetic facies classification, reservoir quality analysis and quantitative wireline log prediction of tight gas sandstones(TGSs) is introduced utilizing a combination of fit-for-purpose complementary testing and machine learning techniques. The integrated approach is specialized for the middle Permian Shihezi Formation TGSs in the northeastern Ordos Basin, where operators often face significant drilling uncertainty and increased exploration risks due to low porosities and micro-Darcy range permeabilities. In this study, detrital compositions and diagenetic minerals and their pore type assemblages were analyzed using optical light microscopy, cathodoluminescence, standard scanning electron microscopy, and X-ray diffraction. Different types of diagenetic facies were delineated on this basis to capture the characteristic rock properties of the TGSs in the target formation.A combination of He porosity and permeability measurements, mercury intrusion capillary pressure and nuclear magnetic resonance data was used to analyze the mechanism of heterogeneous TGS reservoirs.We found that the type, size and proportion of pores considerably varied between diagenetic facies due to differences in the initial depositional attributes and subsequent diagenetic alterations;these differences affected the size, distribution and connectivity of the pore network and varied the reservoir quality. Five types of diagenetic facies were classified:(i) grain-coating facies, which have minimal ductile grains, chlorite coatings that inhibit quartz overgrowths, large intergranular pores that dominate the pore network, the best pore structure and the greatest reservoir quality;(ii) quartz-cemented facies,which exhibit strong quartz overgrowths, intergranular porosity and a pore size decrease, resulting in the deterioration of the pore structure and reservoir quality;(iii) mixed-cemented facies, in which the cementation of various authigenic minerals increases the micropores, resulting in a poor pore structure and reservoir quality;(iv) carbonate-cemented facies and(v) tightly compacted facies, in which the intergranular pores are filled with carbonate cement and ductile grains;thus, the pore network mainly consists of micropores with small pore throat sizes, and the pore structure and reservoir quality are the worst. The grain-coating facies with the best reservoir properties are more likely to have high gas productivity and are the primary targets for exploration and development. The diagenetic facies were then translated into wireline log expressions(conventional and NMR logging). Finally, a wireline log quantitative prediction model of TGSs using convolutional neural network machine learning algorithms was established to successfully classify the different diagenetic facies.

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.

The application study on the multi-scales integrated prediction method to fractured reservoir description

In this paper,we implement three scales of fracture integrated prediction study by classifying it to macro-（ 1/4/λ）,meso-（ 1/100λ and 1/4λ） and micro-（ 1/100λ） scales.Based on the multi-scales rock physics modelling technique,the seismic azimuthal anisotropy characteristic is analyzed for distinguishing the fractures of meso-scale.Furthermore,by integrating geological core fracture description,image well-logging fracture interpretation,seismic attributes macro-scale fracture prediction and core slice micro-scale fracture characterization,an comprehensive multi-scale fracture prediction methodology and technique workflow are proposed by using geology,well-logging and seismic multi-attributes.Firstly,utilizing the geology core slice observation（Fractures description） and image well-logging data interpretation results,the main governing factors of fracture development are obtained,and then the control factors of the development of regional macro-scale fractures are carried out via modelling of the tectonic stress field.For the meso-scale fracture description,the poststack geometric attributes are used to describe the macro-scale fracture as well,the prestack attenuation seismic attribute is used to predict the meso-scale fracture.Finally,by combining lithological statistic inversion with superposed results of faults,the relationship of the meso-scale fractures,lithology and faults can be reasonably interpreted and the cause of meso-scale fractures can be verified.The micro-scale fracture description is mainly implemented by using the electron microscope scanning of cores.Therefore,the development of fractures in reservoirs is assessed by valuating three classes of fracture prediction results.An integrated fracture prediction application to a real field in Sichuan basin,where limestone reservoir fractures developed,is implemented.The application results in the study area indicates that the proposed multi-scales integrated fracture prediction method and the technique procedureare able to deal with the strong heterogeneity and multi-scales problems in fracture prediction.Moreover,the multi-scale fracture prediction technique integrated with geology,well-logging and seismic multi-information can help improve the reservoir characterization and sweet-spots prediction for the fractured hydrocarbon reservoirs.

Application of Prediction Techniques in Carbonate Karst Reservoir in Tarim Basin

Carbonate karst reservoir is the emphases of Tarim＇s carbonate exploration. However, it is buried at a large depth, which results in Weak seismic reflection signal and low S/N ratio. In addition, the karst reservoir contains great heterogeneity, so reservoir prediction is very difficult. Through many years of research and exploration, we have established a suite of comprehensive evaluation technology for carbonate karst reservoir using geophysical characteristics and a geological concept model, including a technique for reconstructing the paleogeomorphology of buried hills based on a sequence framework, seismic description of the karst reservoir, and strain variant analysis for fracture estimation. The evaluation technology has been successfully applied in the Tabei and Tazhong areas, and commercial production of oil and gas has been achieved. We show the application of this technology in the Lunguxi area in North Tarim in this paper.

Reservoir prediction using pre-stack inverted elastic parameters

This is a case study of the application of pre-stack inverted elastic parameters to tight-sand reservoir prediction. With the development of oil and gas exploration, pre-stack data and inversion results are increasingly used for production objectives. The pre-stack seismic property studies include not only amplitude verse offset （AVO） but also the characteristics of other elastic property changes. In this paper, we analyze the elastic property parameters characteristics of gas- and wet-sands using data from four gas-sand core types. We found that some special elastic property parameters or combinations can be used to identify gas sands from water saturated sand. Thus, we can do reservoir interpretation and description using different elastic property data from the pre-stack seismic inversion processing. The pre- stack inversion method is based on the simplified Aki-Richard linear equation. The initial model can be generated from well log data and seismic and geologic interpreted horizons in the study area. The input seismic data is angle gathers generated from the common reflection gathers used in pre-stack time or depth migration. The inversion results are elastic property parameters or their combinations. We use a field data example to examine which elastic property parameters or combinations of parameters can most easily discriminate gas sands from background geology and which are most sensitive to pore-fluid content. Comparing the inversion results to well data, we found that it is useful to predict gas reservoirs using λ, λρ, λ/μ, and K/μ properties, which indicate the gas characteristics in the study reservoir.

Seismic Prediction of Prolific Oil Zones in Carbonate Reservoirs with Extremely Low Porosity and Permeability under Salt

The Carboniferous reservoir in KJ oilfield is a carbonate reservoir with extremely low porosity and permeability and high-pressure. The reservoir has severe heterogeneity, is deeply buried, has complex master control factors, is covered with thick salt, all of which result in the serious distortion of reflection time and amplitudes under the salt, the poor seismic imaging, and the low S/N ratio and resolution. The key to developing this kind of reservoir is to correctly predict the distribution of highly profitable oil zones. In this paper we start by analyzing the master control factors, perform seismic-log calibration, optimize the seismic attributes indicating the lithofacies, karst, petrophysical properties, and fractures, and combine these results with the seismic, geology, log, oil reservoir engineering, and well data. We decompose the seismic prediction into six key areas： structural interpretation, prediction of lithofacies, karst, petrophysical properties, fractures, and then perform an integrated assessment. First, based on building the models of faults and fractures, sedimentary facies, and karst, we predict the distribution of the most favorable reservoir zones qualitatively. Then, using multi-parameter inversion and integrated multi-attribute analysis, we predict the favorable reservoir distribution quantitatively and semi-quantitatively to clarify the distribution of high-yield zones. We finally have a reliable basis for optimal selection of exploration and development targets.

Data-augmented landslide displacement prediction using generative adversarial network

Landslides are destructive natural disasters that cause catastrophic damage and loss of life worldwide.Accurately predicting landslide displacement enables effective early warning and risk management.However,the limited availability of on-site measurement data has been a substantial obstacle in developing data-driven models,such as state-of-the-art machine learning(ML)models.To address these challenges,this study proposes a data augmentation framework that uses generative adversarial networks(GANs),a recent advance in generative artificial intelligence(AI),to improve the accuracy of landslide displacement prediction.The framework provides effective data augmentation to enhance limited datasets.A recurrent GAN model,RGAN-LS,is proposed,specifically designed to generate realistic synthetic multivariate time series that mimics the characteristics of real landslide on-site measurement data.A customized moment-matching loss is incorporated in addition to the adversarial loss in GAN during the training of RGAN-LS to capture the temporal dynamics and correlations in real time series data.Then,the synthetic data generated by RGAN-LS is used to enhance the training of long short-term memory(LSTM)networks and particle swarm optimization-support vector machine(PSO-SVM)models for landslide displacement prediction tasks.Results on two landslides in the Three Gorges Reservoir(TGR)region show a significant improvement in LSTM model prediction performance when trained on augmented data.For instance,in the case of the Baishuihe landslide,the average root mean square error(RMSE)increases by 16.11%,and the mean absolute error(MAE)by 17.59%.More importantly,the model’s responsiveness during mutational stages is enhanced for early warning purposes.However,the results have shown that the static PSO-SVM model only sees marginal gains compared to recurrent models such as LSTM.Further analysis indicates that an optimal synthetic-to-real data ratio(50%on the illustration cases)maximizes the improvements.This also demonstrates the robustness and effectiveness of supplementing training data for dynamic models to obtain better results.By using the powerful generative AI approach,RGAN-LS can generate high-fidelity synthetic landslide data.This is critical for improving the performance of advanced ML models in predicting landslide displacement,particularly when there are limited training data.Additionally,this approach has the potential to expand the use of generative AI in geohazard risk management and other research areas.

Prediction of Fracture-Cavity System in Carbonate Reservoir： A Case Study in the Tahe Oilfield

The carbonate rocks in Tahe oilfield, which suffered from multi-period polycycle karstification and structure deformation, are heterogeneous reservoirs that are rich in pores, cavities,and fractures. The reservoirs are diversified in scale, space configuration, and complex in filling. For this kind of reservoir, a suite of seismic prestack or poststack prediction techniques has been developed based on the separation of seismic wave fields. Through cross-verification of the estimated results,a detailed description of palaeogeomorphology and structural features such as pores, cavities, and fractures in unaka has been achieved, the understanding of the spatial distribution of reservoir improved.

Pre-stack inversion for caved carbonate reservoir prediction:A case study from Tarim Basin,China

The major storage space types in the carbonate reservoir in the Ordovician in the TZ45 area are secondary dissolution caves.For the prediction of caved carbonate reservoir,post-stack methods are commonly used in the oilfield at present since pre-stack inversion is always limited by poor seismic data quality and insufficient logging data.In this paper,based on amplitude preserved seismic data processing and rock-physics analysis,pre-stack inversion is employed to predict the caved carbonate reservoir in TZ45 area by seriously controlling the quality of inversion procedures.These procedures mainly include angle-gather conversion,partial stack,wavelet estimation,low-frequency model building and inversion residual analysis.The amplitude-preserved data processing method can achieve high quality data based on the principle that they are very consistent with the synthetics.Besides,the foundation of pre-stack inversion and reservoir prediction criterion can be established by the connection between reservoir property and seismic reflection through rock-physics analysis.Finally,the inversion result is consistent with drilling wells in most cases.It is concluded that integrated with amplitude-preserved processing and rock-physics,pre-stack inversion can be effectively applied in the caved carbonate reservoir prediction.

Displacement characteristics and prediction of Baishuihe landslide in the Three Gorges Reservoir

In order to reach the designated final water level of 175 m, there were three impoundment stages in the Three Gorges Reservoir, with water levels of 135 m, 156 m and 175 m. Baishuihe landslide in the Reservoir was chosen to analyze its displacement characteristics and displacement variability at the different stages. Based on monitoring data, the landslide displacement was mainly influenced by rainfall and drawdown of the reservoir water level. However, the magnitude of the rise and drawdown of the water level after the reservoir water level reached 175 m did not accelerate landslide displacement. The prediction of landslide displacement for active landslides is very important for landslide risk management. The time series of cumulative displacement was divided into a trend term and a periodic term using the Hodrick-Prescott(HP) filter method. The polynomial model was used to predict the trend term. The extreme learning machine(ELM) and least squares support vector machine(LS-SVM) were chosen to predict theperiodic term. In the prediction model for the periodic term, input variables based on the effects of rainfall and reservoir water level in landslide displacement were selected using grey relational analysis. Based on the results, the prediction precision of ELM is better than that of LS-SVM for predicting landslide displacement. The method for predicting landslide displacement could be applied by relevant authorities in making landslide emergency plans in the future.

Multiple-Element Matching Reservoir Formation and Quantitative Prediction of Favorable Areas in Superimposed Basins

Superimposed basins in West China have experienced multi-stage tectonic events and multicycle hydrocarbon reservoir formation, and complex hydrocarbon reservoirs have been discovered widely in basins of this kind. Most of the complex hydrocarbon reservoirs are characterized by relocation, scale re-construction, component variation and phase state transformation, and their distributions are very difficult to predict. Research shows that regional caprock （C）, high-quality sedimentary facies （Deposits, D）, paleohighs （Mountain, M） and source rock （S） are four geologic elements contributing to complex hydrocarbon reservoir formation and distribution of western superimposed basins. Longitudinal sequential combinations of the four elements control the strata of hydrocarbon reservoir formation, and planar superimpositions and combinations control the range of hydrocarbon reservoir and their simultaneous joint effects in geohistory determine the time of hydrocarbon reservoir formation. Multiple-element matching reservoir formation presents a basic mode of reservoir formation in superimposed basins, and we recommend it is expressed as T-CDMS. Based on the multiple-element matching reservoir formation mode, a comprehensive reservoir formation index （Tcdms） is developed in this paper to characterize reservoir formation conditions, and a method is presented to predict reservoir formation range and probability of occurrence in superimposed basins. Through application of new theory, methods and technology, the favorable reservoir formation range and probability of occurrence in the Ordovician target zone in Tarim Basin in four different reservoir formation periods are predicted. Results show that central Tarim, Yinmaili and Lunnan are the three most favorable regions where Ordovician oil and gas fields may have formed. The coincidence of prediction results with currently discovered hydrocarbon reservoirs reaches 97 %. This reflects the effectiveness and reliability of the new theory, methods and technology.

Prediction of chlorophyll a concentration using HJ-1 satellite imagery for Xiangxi Bay in Three Gorges Reservoir

Since the impoundment of the Three Gorges Reservoir in 2003, algal blooms have frequently been observed in it. The chlorophyll a concentration is an important parameter for evaluating algal blooms. In this study, the chlorophyll a concentration in Xiangxi Bay, in the Three Gorges Reservoir, was predicted using HJ-1 satellite imagery. Several models were established based on a correlation analysis between in situ measurements of the chlorophyll a concentration and the values obtained from satellite images of the study area from January 2010 to December 2011. Chlorophyll a concentrations in Xiangxi Bay were predicted based on the established models. The results show that the maximum correlation is between the reflectance of the band combination of B4/（B2＋B3） and in situ measurements of chlorophyll a concentration. The root mean square errors of the predicted values using the linear and quadratic models are 18.49 mg/m3 and 18.52 mg/m3, respectively, and the average relative errors are 37.79% and 36.79%, respectively. The results provide a reference for water bloom prediction in typical tributaries of the Three Gorges Reservoir and contribute to large-scale remote sensing monitoring and water quality management.

Mesozoic Reservoir Predictionin the Longdong Loess Plateau

This paper summarizes a set of interpretation technologies for Mesozoic sandstone reservoir prediction in the Longdong loess plateau, such as seismic sequence processing and interpretation based on generalized S transform, the eroded paleo-geomorphology interpretation of the top of the Triassic and a variety of lateral reservoir predictions. The effects of employing these technologies are compared and analyzed, as well. The research results show that seismic sequence processing interpretation technology based on generalized S transform can distinguish 3ms (about the thickness of 6 m)sequence interface. Consequently the technology can ascertain the distribution of a sand body of the formation Ch 8 and expand the exploration area of the Xifeng oil field in the Longdong area.

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.

Machine learning seismic reservoir prediction method based on virtual sample generation

Seismic reservoir prediction plays an important role in oil exploration and development.With the progress of artificial intelligence,many achievements have been made in machine learning seismic reservoir prediction.However,due to the factors such as economic cost,exploration maturity,and technical limitations,it is often difficult to obtain a large number of training samples for machine learning.In this case,the prediction accuracy cannot meet the requirements.To overcome this shortcoming,we develop a new machine learning reservoir prediction method based on virtual sample generation.In this method,the virtual samples,which are generated in a high-dimensional hypersphere space,are more consistent with the original data characteristics.Furthermore,at the stage of model building after virtual sample generation,virtual samples screening and model iterative optimization are used to eliminate noise samples and ensure the rationality of virtual samples.The proposed method has been applied to standard function data and real seismic data.The results show that this method can improve the prediction accuracy of machine learning significantly.

Pre-Drilling Prediction Techniques on the High-Temperature High-Pressure Hydrocarbon Reservoirs Offshore Hainan Island,China

Decreasing the risks and geohazards associated with drilling engineering in high-temperature high-pressure(HTHP) geologic settings begins with the implementation of pre-drilling prediction techniques(PPTs). To improve the accuracy of geopressure prediction in HTHP hydrocarbon reservoirs offshore Hainan Island, we made a comprehensive summary of current PPTs to identify existing problems and challenges by analyzing the global distribution of HTHP hydrocarbon reservoirs, the research status of PPTs, and the geologic setting and its HTHP formation mechanism. Our research results indicate that the HTHP formation mechanism in the study area is caused by multiple factors, including rapid loading, diapir intrusions, hydrocarbon generation, and the thermal expansion of pore fluids. Due to this multi-factor interaction, a cloud of HTHP hydrocarbon reservoirs has developed in the Ying-Qiong Basin, but only traditional PPTs have been implemented, based on the assumption of conditions that do not conform to the actual geologic environment, e.g., Bellotti's law and Eaton's law. In this paper, we focus on these issues, identify some challenges and solutions, and call for further PPT research to address the drawbacks of previous works and meet the challenges associated with the deepwater technology gap. In this way, we hope to contribute to the improved accuracy of geopressure prediction prior to drilling and provide support for future HTHP drilling offshore Hainan Island.

Geochronological Records of Oil-Gas Accumulations in the Permian Reservoirs of the Northeastern Ordos Basin

Geochronology of oil-gas accumulation （OGA） is a challenging subject of petroleum geology in multi-cycle superimposed basins.By K-Ar dating of authigenic illite （AI） and fluid inclusion （FI） analysis combined with apatite fission track （AFT） thermal modeling,a case study of constraining the OGA times of the Permian reservoirs in northeast Ordos basin （NOB） has been conducted in this paper.AI dating of the Permian oil-gas-bearing sandstone core-samples shows a wide time domain of 178-108 Ma.The distribution of the AI ages presents 2-stage primary OGA processes in the Permian reservoirs,which developed in the time domains of 175-155 Ma and 145-115 Ma with 2-peak ages of 165 Ma and 130 Ma,respectively.The FI temperature peaks of the samples and their projected ages on the AFT thermal path not only present two groups with a low and a high peak temperatures in ranges of 90-78℃ and 125-118℃,respectively corresponding to 2-stage primary OGA processes of 162-153 Ma and 140-128 Ma in the Permian reservoirs,but also appear a medium temperature group with the peak of 98℃ in agreement with a secondary OGA process of c.～30 Ma in the Upper Permian reservoirs.The integrated analysis of the AI and FI ages and the tectono-thermal evolution reveals that the Permian reservoirs in the NOB experienced at least 2-stage primary OGA processes of 165-153 Ma and 140-128 Ma in agreement with the subsidence thermal process of the Mid-Early Jurassic and the tectono-thermal event of the Early Cretaceous.Then,the Upper Permian reservoirs further experienced at least 1-stage secondary OGA process of c.～30 Ma in coincidence with a critical tectonic conversion between the slow and the rapid uplift processes from the Late Cretaceous to Neogene.

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.