Seismic Attributes Research Articles

Fracture Modeling of Deep Tight Sandstone Fault-Fracture Reservoir Based on Geological Model and Seismic Attributes: A Case Study on Xu 2 Member in Western Sichuan Depression, Sichuan Basin

With significant geological reserves and high resource abundance, the Xujiahe Formation in the Western Sichuan Depression is considered a key target for natural gas exploration and development in continental clastic rocks within the Sichuan Basin. However, this formation remains underdeveloped. Critical to forming “sweet spots” of tight reservoir is the presence of fractures. Based on available data sources, including core samples, well logs, and outcrop data, we utilized a combination of geophysical and geological modeling techniques to clarify the characteristics of effective fractures in tight gas reservoirs. This allowed us to construct a geological model of a tight sandstone fault-fracture gas reservoir in the Xu 2 Member of the Xujiahe Formation located in the Xinchang area, which represents a fault-fracture reservoir formed by high-angle faulting-derived fractures and controlled by the S-N trending fault. With this model, a variety of seismic attributes, including likelihood and entropy, was used to predict the fault-fracture reservoir. Furthermore, geological information, well logs, and seismic attributes were integrated for characterizing the fractures of different scales. The cutoff on various attributes for characterizing the fault-fracture reservoir was defined, and the distribution of the fault-fracture reservoir was delineated. By using the geological modeling technique, the fracture model of the fault-fracture reservoir comprising natural fractures at different scales was built. This model provides further guidance for the exploration and development of the Xu 2 Member tight gas reservoirs in the Xinchang area and, as demonstrated by drilling results, has achieved remarkable effects in practice. This approach has shown good performance in characterizing fracture models. However, due to the complexity of fractures and the discrepancy between the scale of fractures and the scale that can be predicted by geophysical methods, there may still be some uncertainties associated with this method.

A modified method of multiple point geostatistics for spatial simulation of sedimentary facies for carbonate reservoirs

Sedimentary facies information plays an important role in elastic parameter modeling, seismic inversion, and other aspects of marine oil and gas exploration. Multiple-point geostatistics is an important method used to obtain accurate and reliable simulation sedimentary facies data; the filtersim algorithm. However, it is difficult to use the filtersim algorithm to extract the features in a training image by scanning indirect data, such as multiple seismic attributes, as several filters are required. Therefore, we constructed a new method by applying filters to directly scan the training image for a target, such as sedimentary facies, from which two types of prototypes of sedimentary facies and seismic attributes could be obtained. In addition, we modified the method of dividing the filter score and added the score range for the sedimentary facies boundary, which increased the accuracy of the pattern classification. We reduced the number of prototypes with multiple filters by dividing each sedimentary facies prototype by its boundary prototype. Subsequently, we eliminated some empty bins, and improved the efficiency of the simulation. We verified the accuracy of this simulation by comparing the distribution of sedimentary facies in well logs. The results showed that this simulation algorithm can effectively construct 2D or 3D spatial distributions of sedimentary facies in carbonate reservoir by adding the constraints of sedimentary facies and seismic attributes to the filtersim algorithm. The simulation results have valuable implications for situations in which marine oil and gas exploration is being conducted with limited information.

The Application of Seismic Attributes in Fault Detection and Direct Hydrocarbon Indicator in Tomboy Field, Western-Offshore Niger Delta Basin

Seismic attribute analysis is important in subsurface data interpretation, such as seismic interpretation, which could involve seismic stratigraphic and structural interpretation. This interpretation is often hampered by seismic resolution and, sometimes, human inability to identify a subtle feature on the seismic. These factors have frequently led to the poor seismic interpretation of geologic features. Thus, an integral approach to studying structural patterns and hydrocarbon bearing zones using seismic attributes was carried out on the Tomboy field using 3D seismic data covering approximately 56 km2 of the western belt of the Niger Delta. The seismic volume underwent post-stack processing, which enhanced seismic discontinuities. A deep steering volume was first created, and several dip filters were applied to enhance faults in the study area. After that, curvature and similarity attributes were calculated on the dip-steered and fault-enhanced volume. These calculations show detailed geometry of the faults and zones of subtle lineaments. Six faults (F1, F2, F3, F4, F5 and F6) were identified and mapped. These faults range from antithetic to crest growth faults. Two major growth faults (F5 and F6) were revealed to dip in the northeast to southwest directions. A near-extensive crest fault (F4) appeared beneath the major faults. Although several minor fractures were displayed in the southern and central portions of the crest fault of the dipping seismic data, the southwest (F4) and growth fault, F6, are responsible for holding the hydrocarbon found within the identified closures. Using attributes on the seismic data increased confidence in mapping and interpreting structural features. Furthermore, energy attributes were used as Direct Hydrocarbon Indicators (DHI) to visualize viable areas within the study, which allows a more robust interpretation. Time slices were taken in regions of flat and bright spots. The spectral decomposition attribute was run on these slices to display areas of high amplitude reflection typical of hydrocarbon-bearing regions trapped mainly by regional to sub-regional growth faults. The surface attribute calculated on the generated surface shows that the field is predominantly controlled by faults serving as traps for hydrocarbon.

Seismic prediction of porosity in tight reservoirs based on transformer

Porosity is a crucial index in reservoir evaluation. In tight reservoirs, the porosity is low, resulting in weak seismic responses to changes in porosity. Moreover, the relationship between porosity and seismic response is complex, making accurate porosity inversion prediction challenging. This paper proposes a Transformer-based seismic multi-attribute inversion prediction method for tight reservoir porosity to address this issue. The proposed method takes multiple seismic attributes as input data and porosity as output data. The Transformer mapping transformation network consists of an encoder, a multi-head attention layer, and a decoder and is optimized for training with a gating mechanism and a variable selection module. Applying this method to actual data from a tight sandstone gas exploration area in the Sichuan Basin yielded a porosity prediction coincidence rate of 95% with the well data.

On the applicability of seismic attributes in the description and interpretation of mass-transport deposits

Mass transport deposits (MTDs) have gained economic importance in the last years because of their significance as seals or stratigraphic trapping mechanisms in deep water turbidite prospects. The analysis of MTDs in 3D seismic data provides a better understanding of their characteristics when compared to outcrop or 2D seismic data, as it is possible to capture both internal and external features over large areas in 3D. Moreover, this analysis can be further improved by applying seismic attributes, which have been employed only to describe specific aspects of these deposits. In this study, we applied several seismic attributes systematically in the characterization of an MTD, located in the northern Santos Basin (offshore southeastern Brazil), aiming to identify their applicability in the description and interpretation of 33 characteristics of this kind of deposit. As a result, it was possible to identify which features of the MTD the application of seismic attributes is indispensable, helpful, or redundant.

Gas channel delineation utilizing a neural network and 3D seismic attributes: Simian Field, offshore Nile Delta, Egypt

Depositional architecture and hydrocarbon-bearing reservoir detection are considered the main challenges in the Nile Delta Basin, predominantly in the slope area. Channel fill deposits are very complicated because they are vertically stacked and pass through different depositional stages, forming complex depositional patterns. In the current study, an artificial neural network was used to detect gas and water-bearing reservoirs inside the complex depositional pattern and their spatial dimensions. Modern seismic reservoir characterization attribute analysis provides a good outcome in detecting reservoir fluids by mixing fluid-sensitive attributes with the well outcomes. Artificial Neural Network (ANN) algorithms for rock property prediction are considered to be a new emerging trend. The ANN algorithm has an advantage over other seismic reservoir delineation techniques because it has a good capability for building a nonlinear relationship between seismic data and petrophysical logs.Hence, it can be utilized to spatially anticipate reservoir fluids with a rational degree of accuracy. A back-error propagation algorithm, a supervised neural network method, was implemented on the Simian Field to anticipate the fluid-bearing reservoirs from the seismic-derived amplitudes. The ANN method showed unique results in the case study area by discriminating the gas-bearing intervals from the water-bearing intervals, although combining the assembly of the seismic attributes to supervise fluid classification. The method will help in the development plans of the field and track the volume of water and gas.

Geologic Causatives and Seismic Attributes Heterogeneities for Structural and Stratigraphic Interplays, Sitra Area, North Western Desert, Egypt

Sand-lithofacies distributions are a vital component of reservoir characterisation and the generation of successful reservoir models, particularly in thin reservoirs thickness. The integration between seismic attributes and conceptual geologic models is important to identify the sand distributions and reservoir geometries. The aim of this work is illustrating the uses of seismic data in revealing the structural and stratigraphic elements of two main reservoir units. It is important to identify and list the attributes, which can be involved in analysing the reservoirs and their degree of involvement in the characterisation of the hydrocarbon accumulation zones. The study was carried out for the reservoirs: Abu Roash C and Abu Roach E in Sitra oil and gas concession, which is located in the northern part of the Egyptian Western Desert. Four seismic attributes are used: 1- Coherence (Variance) 2- 3D Curvature attributes were used for resolving mainly the structural features and also the stratigraphic features 3- Instantaneous phase 4- Instantaneous frequency attributes were used mainly for resolving the stratigraphic features. Through the integration of selected seismic attributes with post-stack seismic data, reservoir distributions and architectures are accurately delineated for the Upper Cretaceous reservoir (Abu Roash ‘C’ and ‘E’). Five wells were used to match the results of the seismic attributes and establish the regional trends of reservoir parameters. The integration of wells data, conventional seismic interpretation and extracted the relevant seismic attributes help in reaching a robust geologic model for the reservoirs of interest. Stratigraphic and structural interpretation objectives based on extracting the seismic attributes for reservoir characterisation become more dominant, as they go deeper in seismic data, to derive more subsurface geologic data than traditional interpretation. 3D structure model of the concern area was established by interpreting the available seismic data as both reservoirs implicated by two fault trends: NW-SE and ENE-WSW. By the end a 3D geological model was defined based on the results of the conventional interpretation of the seismic and seismic attributes to reflect all structural and stratigraphic elements of the two reservoir units.

Seismic attribute assisted analysis of the interpretational variations in the time and depth migrated datasets: An example from Taranaki Basin, New Zealand

In the regions with complex geology together with the apparent stratigraphic and seismic sequence events, time migration algorithms do not provide high-quality imaging for seismic interpretation due to strong lateral velocity contrasts, usage of average velocities in the vertical and horizontal directions, and without defining the ray-bending at interfaces. Therefore, the depth migration method using interval velocities and bended ray-traces at interfaces, provides more accurate results. There are also interpretational differences between the time and depth-migrated seismic data. The objective of this research is to compare these differences using several seismic attributes. In this context, we used the Toro 3-D pre-stack time and pre-stack depth migrated datasets from the Taranaki Basin, offshore New Zealand, because the Giant Foresets Formation presents suitable examples for the different types of channels like distributary, sinuous and meandering channels. Comparisons indicate that dip angles of the faults increased, channel walls become steeper and indicate more curvature, and structures get narrower in the depth-migrated data. There are also amplitude and phase variations in and around the channels. Most of the seismic data in the world are in the time domain and there is no sufficient borehole and velocity data. This situation may affect the attribute calculations in both migration data sets. The main goal of this investigation is to provide an understanding about the possible seismic differences in the time and depth migrations, the reasons behind them and, relationship between the lithology and probable seismic responses by using geometrical and physical attributes used in the seismic industry. These steps allow an accurate interpretation and more reliable evaluation of the subsurface structures. This study will also provide a toolkit and guidance for the interpreters in the time and depth migrations.

Seismic Analysis of RMS Amplitude Attributes to Identify Hydrocarbon Potential in Field "X" of Jambi Province Indonesia

Indonesia has many potential oil and gas basins. Seismic attribute analysis of RMS Amplitude (Root Mean Square) was conducted in the Betung area, Jambi sub-basin, South Sumatra Basin. The reservoir characterisation technique used in this study is rms attribute analysis which can show changes in the lithology of the study layer. Seismic attributes were extracted from 2D pre-stack time migration (PSTM) seismic data. This study also takes BTJ-210 log data as interpretation and determines the reservoir thickness at the target. Based on the seismic attribute analysis with rms, it is verified that the reservoir is indeed detected within the analysis window of 10 ms, 20 ms, 30 ms, 40 ms and the possible distribution of the reservoir is in horizon 3 and horizon 4 which has a high range of amplitude values and is in a high range zone or higher area than the surrounding area. The results of this seismic attribute analysis can show the hydrocarbon prospect zone and the potential for new well development in the study area, which is located in Horizon 3 and Horizon 4 at a depth of 227 to 250 metres south of the study area.

A novel method for seismic-attribute optimization driven by forward modeling and machine learning in prediction of fluvial reservoirs

The use of seismic attributes for hydrocarbon exploration is well established, and the integration of multiple attributes by supervised machine learning is increasingly being applied as an effective method for attribute optimization. However, this method relies upon a dense array of wells to be employed as a training dataset, which limits its application to fields with sparse boreholes, especially offshore. To address this limitation, this study proposes a novel method of seismic attribute integration driven by forward seismic modeling, enabling the integration of multiple attributes by supervised learning in fields with a limited number of wells. This proposed method consists of two main tasks: (i) establishing a forward geological (lithological) model on a well-correlation section by forward seismic modeling, based on seismic data and wells from the study area; (ii) fusing multiple seismic attributes by supervised machine learning, employing the forward geological model and its synthetic seismic reflection as the training dataset. This method is applied and tested on a real-world case study from the East China Sea region. In this case study, seismic surface attributes of root-mean-square amplitude, max peak amplitude and sweetness are selected and then integrated using the proposed method. The integrated seismic attribute shows significant advantages for the detection of channel belts. Notably, it results in markedly improved correlation between seismic attribute and sand thickness, with the correlation coefficient increasing from 0.586 to 0.849, compared to the original seismic attribute.

Innovative 3D modeling of an old oil field for sustainable production: Case study of Katin-Barbes oil field (KBOF), SE Anatolia- Turkey

The goal of this study is to establish a workflow for the re-interpretation of almost depleted fields targeting the long-term sustainable oil production; in particular, for the oil fields in Turkey and the neighboring Middle Eastern countries located on the fold and thrust belts of the Zagros Mountains. It also fills some of the gaps in our understanding of the northern part of the Arabian Platform by describing the seismic characteristics of the Cretaceous reservoirs that were deposited during the Aptian to Turonian. The Katin-Barbes oil field (KBOF) in SE-Turkey was used as a case study. In this area, 3D seismic data were used for structural interpretation and re-modeling of Cretaceous carbonates sedimented in the complex tectonic region. The well logs from 55 wells in the field were used to create a compilation of formation tops and were used as reference points for two separate sets of 3-D seismic data, acquired in 1991 and 2017. The quality of seismic data was improved with interpretation filters. The structural model was obtained by using various qualifiers from the seismic cubes and seismic facies changes were identified by analyzing a number of seismic attributes. Therefore, seismic data and velocities from the borehole measurements were combined to form a velocity model in building a structural model. Seismic attributes and well logs were used to create a porosity model. Consequently, top and base of two reservoir units; the Derdere and Sabunsuyu Formations have been clarified and re-defined, and potential new well locations were identified. Depending on the results of this investigation, 9 new wells were drilled in the potential areas in the KBOF, recently. Except the last one drilled on the NE boundary of the northern block, all wells have been completed as the “oil producing wells” and top of the reservoir units were encountered at almost the same depths in our depth model. Therefore, results and proposed methods in this research are confirmed by the real, borehole data. This research will be an examplary study for the re-evaluation of older and/or almost depleted oil fields, either in Turkey or in the other Middle Eastern countries.

Delineation of oil–water contact within Tipam reservoir: A study from Upper Assam Basin, North‐East India

Fluid contacts within a reservoir can vary either because of compartmentalization by faults, lithological variations, hydrocarbon fill history or changes in the hydrodynamic activity of fluids. Their detailed interpretation is significant for estimating potential reserves and developing an explored hydrocarbon field. This study uses high‐quality three‐dimensional (3D) seismic reflection data to decipher the fluid contact zones and their types from the well‐known Tipam reservoir in the petroliferous Upper Assam foreland basin. Different seismic attributes are used to understand the seismic response of fluids and associated structures that structurally control the reservoir geometry. Fluid contact analysis is performed by amalgamating these responses within the target interval. The analysis indicates that the south‐west part of the reservoir is a promising hydrocarbon‐bearing zone and consists of oil–water contacts. These contacts possess a dominant trend of NE–SW within the reservoir. Further, a decreasing trend in the density, velocity and an increasing trend in the resistivity and porosity logs of the wellbore SC‐2 calibrates these inferences and confirms the presence of oil‐bearing zones underlain by water in the SW part of the Tipam reservoir. Thus, the Upper Assam foreland basin is a promising area for hydrocarbon exploration, in which Mid‐Miocene sequences are the potential leads that can be unlocked. The analysis presented through this research could be efficiently and similarly carried out in onshore basins worldwide.

Prediction of Permian karst reservoirs in the Yuanba gas field, northern Sichuan Basin, China

Karst reservoir has great hydrocarbon potential, however karst reservoir prediction is inhibited by the strong lateral and vertical heterogeneity of karstification which in turn results in recognition difficulty when geological and geophysical methods are used in isolation. Combined geological and geophysical methods, including core observation, thin section analysis, well log interpretation, seismic attributes and seismic inversion are applied to understand the depositional environment, types of karstification, the geophysical response and distribution of karst reservoir and the controls over and evolution model of karst reservoir in Permian Yuanba gas field, northern Sichuan Basin. The results show that there are four types of major seismic facies recognized in the study area, which correspond to platform margin reef, carbonate platform, platform margin inter-bay and platform margin slope. Karstification can be divided into three zones: the supergene karst zone, the vertical seepage zone and the horizontal underflow zone, among which the supergene karst zone have the strongest karstification. Karstification is highlighted with low seismic impedance, low Poisson's ratio, and high seismic attenuation on seismic inversion as well as micro scale paleo geomorphology recognized by trend surface analysis. By comparing the distribution of karstification with paleo geomorphology, fault distribution and gas contents, it can be observed that the karstification have a good matching relationship with these factors. The dominant type of karstification is epigenic karst, which is strongly influenced by depositional facies and paleo geomorphology. Fracture networks have contributed to karstification but are not the dominant factor of karst formation. The integration of geological and geophysical methods can predict karst reservoir with high accuracy within large area and can be applied to karst reservoir hydrocarbon exploration of similar geological setting.

Distribution pattern of natural fractures in lacustrine shales: a case study of the Fengcheng formation in the Mahu Sag of the Junggar Basin, China

The Lower Permian Fengcheng Formation in the Mahu Sag develops a set of organic-rich alkaline lacustrine shale strata, which is a key area for shale oil exploration and development. As an important storage space and seepage channel for shale reservoirs, natural fractures have an impact on shale oil enrichment, production and development effect. In this study, the types and characteristics of natural fractures were first analyzed using core, thin section and imaging logging data. On this basis, combined with the distribution of fractures in single wells, the vertical distribution law of fractures is discussed. Finally, the planar distribution of fractures is evaluated using different seismic attributes such as coherence, curvature, likelihood, and AVAz. The results showed that three types of fractures are existed, including transformational shear fractures, intraformational open fractures and bed-parallel shear fractures, with intraformational open fractures being the most developed. The development degree of fractures in different layers has obvious differences, mainly controlled by lithology and brittle mineral content. The basalt and tuff are developed in the Feng 1 Member, with low carbonate mineral content, resulting in a relatively low degree of fracture development. The dolomite and argillaceous dolomite are developed in the Feng 2 Member and the Feng 3 Member, with high carbonate mineral content and brittleness, resulting in a high degree of fracture development. Additionally, the closer to the fault, the higher the degree of fracture development. On the plane, the fracture zone develops near the main and secondary faults, with the trend mainly oriented in the E-W direction and approximately parallel to the direction of the faults. The width of the fracture zone is largest in the central and southern part of the study area. These fractures are fault-related and are caused by regional stress fields resulting from the activity of the main-secondary faults.

Seismic characterization of geologically complex geothermal reservoirs by combining structure-oriented filtering and attributes analysis

In geothermal systems, the geologic structure is a decisive factor in controlling fluid flow. Several geothermal systems around the world are located in complex geological structures, such as closely spaced and intersecting faults and fractures, folds, and dykes. Seismic data provides high-resolution images of complex structures that can be used to explore geothermal reservoirs. In fact, faults and fractures have subtle geologic edges that produce significant lateral variations in seismic data. Volumetric seismic attributes are quite effective for detecting these discontinuities in seismic data but are sensitive to noise and velocity accuracy. In North China, a deeply buried carbonate structure presents a geologically complex system with fault-controlled geothermal circulation. However, due to the deep burial depth and structural complexity, seismic reflection beneath the buried-hill has a low-quality, making it difficult to detect the characteristics of the fault edges. In this study, we first develop a structural architecture of the buried-hill carbonate reservoirs to show the development characteristics in vertical and plane directions. Next, we propose an intelligent workflow based on structure-oriented filtering and sensitive seismic attributes to investigate structural complexity (faults and fractures) in the basin for geothermal reservoir exploration. The results show that by combining the proposed structure-oriented filtering and sensitive volumetric seismic attributes, we can generate high-resolution seismic images to characterize fault edges, geometries, and fracture anomalies in structurally complex settings in order to identify upflow locations along the faults and fractures in geothermal systems. We further validated the fracture networks distribution by superimposing the extracted attributes with seismic fault networks and fracture density map using multilayer feedforward neural network. This workflow provides a reliable basis for the characterization of geothermal reservoirs in deep-buried and structurally controlled geothermal fields.

Low-order fault identification method of Putaohua oil layer of X block in Songliao Basin

With the exploration and development of oil fields to the later stage, the distribution of remaining oil is highly scattered, and the oil control area becomes smaller. It is necessary to carry out fine identification and description of small geological interfaces, so as to improve the accuracy of reservoir description. Therefore, low-level fault identification has become an extremely important link. However, due to the influence of seismic data resolution, it is often difficult to directly interpret small faults on conventional seismic profiles. In conventional seismic data, fault interpretation is often based on seismic attribute analysis. At present, there are many kinds of seismic attributes used for fault interpretation, such as coherence class, curvature body attribute, ant attribute body and so on. By comprehensively utilizing the time slices and seismic profiles of these seismic attributes, small faults can be identified more effectively. In the process of studying the three-dimensional work area of Putaohua oil layer of X block in Songliao Basin, the above methods are used in combination with various information such as seismic profiles to identify small faults that are difficult to identify on conventional seismic data volume and coherence volume, and good application results have been achieved.

Timanian Fold-and-Thrust Belt and Caledonian Overprint in the Selis Ridge Imaged by New 3D Seismic Attributes and Spectral Decomposition

The present study is a detailed structural analysis of 3D seismic data in the Selis Ridge in the western Loppa High in the Norwegian Barents Sea, to which new seismic attributes and spectral decomposition were applied. The analysis reveals that pre-Devonian basement rocks are crosscut by a 40–50 kilometers wide, several kilometers thick, E–W- to WNW–ESE-striking fold-and-thrust belt, including a steep, kilometer-thick, top-SSW shear zone. The folds display dome- and trough-shaped geometries, the thrusts appear to have been reactivated dominantly as top-west structures, and the main shear zone warps over the top of the Selis Ridge. The fold-and-thrust belt is interpreted as part of the latest Neoproterozoic (ca. 650–550 Ma) Timanian Orogeny, which potentially reworked preexisting Neoproterozoic rift basins and highs, and was reworked during E–W Caledonian contraction in the Ordovician–Silurian. The results are analogous to recent findings in the northern Norwegian Barents Sea and Svalbard. The presented interpretation provides the basis for discussing Neoproterozoic–Paleozoic plate tectonics reconstructions, the influence of Precambrian–early Paleozoic structures on post-Caledonian fault complexes, the location of the Timanian and Caledonian suture zones, Neoproterozoic rifting, and the origin of the Seiland Igneous Province.

Seismic Facies Recognition of Ultra-Deep Carbonate Rocks Based on Convolutional Neural Network

Seismic facies is a seismic reflection unit defined by specific seismic reflection characteristics, that is, the seismic responses of sedimentary facies or geological bodies, whose accuracy will directly affect the reliability of oil and gas exploration results. Currently, seismic facies is generally recognized depending upon the differences between certain single trace seismic attributes (waveform, frequency spectrum, and amplitude, etc.) and adjacent units to conduct cluster analysis. Such methods, however, have ambiguity in identifying special reflective structures with continuous waveforms (e.g. massive carbonate deposits). In order to solve this problem, this paper incorporates artificial intelligence (AI) technology into automatic recognition of seismic facies with special reflection structures. Firstly, a 2D seismic facies classification sample label set is designed and formed. Then, a seismic facies prediction model is designed and constructed using a multi-layer convolutional neural network (CNN). Finally, the trained model is used to automatically track the seismic facies in the study area. This method was applied to seismic facies recognition for the Sinian Dengying Formation in an area of the Sichuan Basin, and the seismic facies recognized were compared with artificially interpreted ones. It is confirmed that the proposed method provides a better effect than artificial interpretation, with greatly improved accuracy and efficiency.

Classification, identification, and reservoir characteristics of intermediate mafic lava flows: a case study in Dongling area, Songliao Basin

Intermediate mafic lava is a special oil and gas reservoir. While its internal structure is an important factor affecting the reservoir properties, the identification of facies and understanding of the relationship between facies architecture and reservoir are limited. This study evaluated the intermediate mafic lava flows of the Yingcheng Formation in the Dongling area of Songliao Basin by analyzing drilling cores, corresponding thin sections, and scanning electron microscope (SEM) images, as well as well-logging and seismic attributes. We also performed helium gas experiments and high-pressure mercury intrusion (HPMI) analysis to assess the physical properties and pore structure of the reservoir, respectively. The results showed that intermediate mafic lava flows develop tabular lava flow, compound lava flow, and hyaloclastite. Three facies showed present diverse well-logging and seismic responses. The intermediate mafic lava facies architecture was divided into crater-proximal facies (CF-PF), medial facies (MF), and distal facies (DF), which were characterized by their vesicles and joints and could be identified through their seismic attributes. The reservoir spaces including vesicles, amygdale inner pores, joint fissures, and dissolution pores predominantly showed oil and gas accumulation. The results of the tests of the reservoir’s physical properties showed that the reservoir quality was best in the CF-PF, which is the main target of oil and gas exploration.

Accuracy assessment of various supervised machine learning algorithms in litho-facies classification from seismic data in the Penobscot field, Scotian Basin

Litho-facies classification is an essential task in characterizing the complex reservoirs in petroleum exploration and subsequent field development. The lithofacies classification at borehole locations is detailed but lacks in providing larger coverage areas. The acquired 3D seismic data provides global coverage for studying the reservoir facies heterogeneities in the study area. This study applies six supervised machine learning techniques (Random Forest, Support Vector Machine, Artificial Neural Network, Adaptive Boosting, Xtreme Gradient Boosting, and Multilayer Perceptron) to 3D post-stack seismic data to accurately estimate different litho-facies in inter-well regions and compares their performance. Initially, the efficacy of the said models was critically examined via the confusion matrix (accuracy and misclass) and evaluation matrix (precision, recall, F1-score) on the test data. It was found that all the machine learning models performed best in classifying the shale facies (87%–94%) followed by the sand (65%–79%) and carbonate facies (60%–78%) in the Penobscot field, Scotian Basin. On an overall accuracy scale, we found the multilayer perceptron method the best-performing tool, whereas the adaptive boosting method was the least-performing tool in classifying all three litho-facies in the current analysis. While other methods also performed moderately good for the classification of all three litho-facies. The predicted litho-facies using seismic attributes matched well with the log data interpreted facies on the borehole locations. It indicates that the facies estimated in inter-well regions are accurate and reliable. Furthermore, we validated the estimated results with the other seismic attributes to ascertain the accuracy and reliability of the predicted litho-facies between the borehole locations. This study recommends machine learning applications for litho-facies classification to reduce the risk associated with reservoir characterization.