An improved deep dilated convolutional neural network for seismic facies interpretation

With the successful application and breakthrough of deep learning technology in image segmentation,there has been continuous development in the field of seismic facies interpretation using convolutional neural networks.These intelligent and automated methods significantly reduce manual labor,particularly in the laborious task of manually labeling seismic facies.However,the extensive demand for training data imposes limitations on their wider application.To overcome this challenge,we adopt the UNet architecture as the foundational network structure for seismic facies classification,which has demonstrated effective segmentation results even with small-sample training data.Additionally,we integrate spatial pyramid pooling and dilated convolution modules into the network architecture to enhance the perception of spatial information across a broader range.The seismic facies classification test on the public data from the F3 block verifies the superior performance of our proposed improved network structure in delineating seismic facies boundaries.Comparative analysis against the traditional UNet model reveals that our method achieves more accurate predictive classification results,as evidenced by various evaluation metrics for image segmentation.Obviously,the classification accuracy reaches an impressive 96%.Furthermore,the results of seismic facies classification in the seismic slice dimension provide further confirmation of the superior performance of our proposed method,which accurately defines the range of different seismic facies.This approach holds significant potential for analyzing geological patterns and extracting valuable depositional information.

Seismic facies response of tectonics and direction of block movement in the northeastern South China Sea

The close relationship between the structure,evolution,and resources environment of the South China Sea is a current research focus and also a focal point of our study.In this paper,we use regional seismic sections to analyze the relationship between seismic facies and the structure and tectonic evolution of the northeastern South China Sea and propose new points about the structure and the direction of block（land mass） motion.First,the tectonic features are clear and can be divided into five different structural units which are both linked and independent of each other.Second,it doesn＇t matter if the South China Sea basin pattern is extensional,weakly compressive,or strongly compressive,the regional tectonic stress field is unified.For the first time we find that two shallow subduction zones are recognized in the seismic profiles.All the tectonic blocks have accordion-fold-style structures,converging in the east,and the South China Sea exhibits different stages of basin development：growth, maturity,end,and termination.The block subduction and regional block dip directions are all aligned with the regional stress field.

Pre-stack-texture-based reservoir characteristics and seismic facies analysis

Seismic texture attributes are closely related to seismic facies and reservoir characteristics and are thus widely used in seismic data interpretation.However,information is mislaid in the stacking process when traditional texture attributes are extracted from poststack data,which is detrimental to complex reservoir description.In this study,pre-stack texture attributes are introduced,these attributes can not only capable of precisely depicting the lateral continuity of waveforms between different reflection points but also reflect amplitude versus offset,anisotropy,and heterogeneity in the medium.Due to its strong ability to represent stratigraphies,a pre-stack-data-based seismic facies analysis method is proposed using the selforganizing map algorithm.This method is tested on wide azimuth seismic data from China,and the advantages of pre-stack texture attributes in the description of stratum lateral changes are verified,in addition to the method＇s ability to reveal anisotropy and heterogeneity characteristics.The pre-stack texture classification results effectively distinguish different seismic reflection patterns,thereby providing reliable evidence for use in seismic facies analysis.

Seismic Facies in a Deepwater Area of a Marine Faulted Basin:Deepwater Area of the Paleogene Lingshui Formation in the Qiongdongnan Basin

In recent years, deep water areas have become popular exploration fields because of their abundant hydrocarbon resource potential. There are only relatively poor planar seismic profiles and no wells for deepwater areas of the Lingshui Formation in the Qiongdongnan Basin. A lot of faults developed and strata are fragmented due to high temperatures and high pressure, and this has resulted in dim sequence boundaries. Based on seismic data of the deepwater area and well data of bordering shallow water areas, Lingshui Formation was divided into four third class sequences; namely SI, SII, SIII and SIV, and the three-dimensional isochronous stratigraphic framework of the Lingshui Formation in the studied area was shaped. Based mainly on seismic attributes such as amplitude, continuity, internal structure and external shape, six typical seismic facies were identified, including mat-shaped, filling, wedge-shaped, foreset, moundy-shaped and lenticular-shaped, and a seismic facies distribution map was subsequently drawn. With studies on wells of bordering shallow water areas, regional sedimentary characteristics, and isopach map as references, sedimentary planar distribution features were analyzed. The deepwater area of the Lingshui Formation has mainly developed littoral and shallow sea. Sandstone bodies of fan delta, braided river delta, slope fan, basin floor fan, and turbidite fan are at an interdigitate junction to marine hydrocarbon source rocks and thus are favorable prospecting targets.

Unsupervised seismic facies analysis using sparse representation spectral clustering

Traditional unsupervised seismic facies analysis techniques need to assume that seismic data obey mixed Gaussian distribution.However,fi eld seismic data may not meet this condition,thereby leading to wrong classifi cation in the application of this technology.This paper introduces a spectral clustering technique for unsupervised seismic facies analysis.This algorithm is based on on the idea of a graph to cluster the data.Its kem is that seismic data are regarded as points in space,points can be connected with the edge and construct to graphs.When the graphs are divided,the weights of the edges between the different subgraphs are as low as possible,whereas the weights of the inner edges of the subgraph should be as high as possible.That has high computational complexity and entails large memory consumption for spectral clustering algorithm.To solve the problem this paper introduces the idea of sparse representation into spectral clustering.Through the selection of a small number of local sparse representation points,the spectral clustering matrix of all sample points is approximately represented to reduce the cost of spectral clustering operation.Verifi cation of physical model and fi eld data shows that the proposed approach can obtain more accurate seismic facies classification results without considering the data meet any hypothesis.The computing efficiency of this new method is better than that of the conventional spectral clustering method,thereby meeting the application needs of fi eld seismic data.

Incremental semi-supervised learning for intelligent seismic facies identification

Intelligent seismic facies identification based on deep learning can alleviate the time-consuming and labor-intensive problem of manual interpretation,which has been widely applied.Supervised learning can realize facies identification with high efficiency and accuracy;however,it depends on the usage of a large amount of well-labeled data.To solve this issue,we propose herein an incremental semi-supervised method for intelligent facies identification.Our method considers the continuity of the lateral variation of strata and uses cosine similarity to quantify the similarity of the seismic data feature domain.The maximum-diff erence sample in the neighborhood of the currently used training data is then found to reasonably expand the training sets.This process continuously increases the amount of training data and learns its distribution.We integrate old knowledge while absorbing new ones to realize incremental semi-supervised learning and achieve the purpose of evolving the network models.In this work,accuracy and confusion matrix are employed to jointly control the predicted results of the model from both overall and partial aspects.The obtained values are then applied to a three-dimensional(3D)real dataset and used to quantitatively evaluate the results.Using unlabeled data,our proposed method acquires more accurate and stable testing results compared to conventional supervised learning algorithms that only use well-labeled data.A considerable improvement for small-sample categories is also observed.Using less than 1%of the training data,the proposed method can achieve an average accuracy of over 95%on the 3D dataset.In contrast,the conventional supervised learning algorithm achieved only approximately 85%.

Study on the Igneous Rock Seismic Facies in Yingmai 32 Blocks

The western part of north Tarim Uplift underwent multi-stage tectonic movement and multiple stages of magmatism. Igneous rocks are associated with carbonate and buried deep. The seismic response characteristics of igneous rocks are similar in many respects to the seismic response characteristics of karst, making the identification and prediction of igneous rocks more difficult. This study compares the seismic reflection characteristics of igneous rocks. Set up three types of igneous rock seismic facies model penetration type, fracture type and central type. And it concluded that a time-slice, coherence analysis, analysis of the seismic properties of the layers and the method of three-dimensional engraving to identify the igneous rocks. This method has been applied to the identification and prediction of carbonate rock buried and hill igneous rocks in the north Tarim basin YingMaiLi region and has achieved good results.

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.

Sedimentary microfacies of Member 5 of Xujiahe Formation in the Dongfengchang area, Sichuan Basin

Member 5 of the Upper Triassic Xujiahe Formation(T_(3)X_(5))in central Sichuan Basin has made a breakthrough in exploration recently.However,this new stratum has not been investigated sufficiently with respect to basic geology,making its types and distribution of sedimentary facies unclear,which severely restricts its subsequent exploration evaluation.In this study,types of sedimentary microfacies in the first sand group of T_(3)X_(5)(T_(3)X_(5)^(1))are clarified through core observation and logging interpretation using core,log and seismic data,and then distribution of sedimentary microfacies in T_(3)X_(5)^(1) is determined according to seismic waveform features and seismic prediction.The results show that T_(3)X_(5)^(1) in the Dongfengchang area is mainly composed of deltaic deposits of several microfacies,such as delta front underwater distributary channel,sheet sand,and interdistributary bay.On seismic sections,different microfacies are significantly different in waveform features,the underwater distributary channel is characterized by one trough between two peaks,while diversion bay exhibits chaotic reflections between T6 and T51.The sedimentary microfacies varied greatly during the depositional period of T_(3)X_(5)^(1) in the Dongfengchang area,this is because that the sediment supply was mainly controlled by the southwest and southeast provenance regions.Three superimposed underwater distributary channels are developed in the Dongfengchang area.The phase-1 superimposed underwater distributary channel in the northwest transition to sheet sand in the northeast,the phase-2 superimposed underwater distributary channel in the south extends shortly,the phase-3 superimposed underwater distributary channel in the northeast has a large development scale.These research findings are helpful to guide the subsequent exploration of T_(3)X_(5) gas reservoir and also theoretically significant for investigating the depositional evolution of the Xujiahe Formation in central Sichuan Basin.

Study on the Fine Configuration of Reservoir in River Facies Oilfield in Bohai Sea Area

The geological conditions of offshore shallow water delta oil reservoirs were complex, with limited well data and large well spacing. Taking A Oilfield in the Bohai Sea Area, China as an example, the target sand body was formed in a shallow water delta sedimentary environment, with well-developed underwater distributary channels and frequent branching and diversion. The reservoir was strong non-uniformity and uneven plane water cut pressure. To this end, based on the existing work of predecessors, combined with seismic, logging, and production dynamics data, and based on the genesis mechanism of shallow water delta reservoirs, the boundary of composite river channels was identified through seismic facies, and logging facies were used to subdivide them into single river levels within the composite river channels. Then, seismic waveform characteristics were applied to track and characterize the plane distribution of single river channels, guiding the efficient development of offshore shallow water delta oil fields and achieving increased storage and production in Bohai Oilfield, China.

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).

Integrative method in lithofacies characteristics and 3D velocity volume of the Permian igneous rocks in H area, Tarim Basin

This paper introduces horizon control, seismic control, logging control and facies control methods through the application of the least squares fitting of logging curves, seismic inversion and facies-controlled techniques. Based on the microgeology and thin section analyses, the lithology, lithofacies and periods of the Permian igneous rocks are described in detail. The seismic inversion and facies-controlled techniques were used to find the distribution characteristics of the igneous rocks and the 3D velocity volume. The least squares fitting of the logging curves overcome the problem that the work area is short of density logging data. Through analysis of thin sections, the lithofacies can be classified into eruption airfall subfacies, eruption pyroclastic flow subfacies and eruption facies.

Seismic Reflection,Distribution,and Potential Trap of Permian Volcanic Rocks in the Tahe Field

Permian Kaipaileicike （开派雷兹克） volcanic rocks approximately 0-200 m thick are drilled in the Tahe （塔河） field. The distribution of volcanic rocks and their potential to form hydrocarbon reservoirs are discussed based on the integrated interpretation of log and 3D seismic data. The volcanic rocks, mainly consisting of dacites and basalts, are sandwiched between the Lower Triassic and Lower Carboniferous and bounded by top and bottom unconformities. The dacites accumulated in a mound shape around volcanic craters, whereas the basalts are deposited in tabular or trough-fill ge- ometries. Permian volcanic craters mainly located at the northwest corner of the Tahe field are identi- fied from volcanic rock thickening, occurrence of volcanic breccias, structural arch of the top Permian, seismic attribute anomalies, and fault （piercing conduit） reflections. Along the northwest wing of a Carboniferous salt dome, a stratigraphic trap is formed by a northeast updip pinch-out of Permian volcanic rock. Oil indications within the trap are found in numerous wells. The reservoir volcanic rocks are mainly of the fracture-pore pattern and covered by the caprock of a Lower Triassic mudstone. The hydrocarbon reservoir, which can potentially be a medium-sized oil pool, is connected to Camhrian-Ordovician source rocks through normal faults along the salt dome boundary.

Morphology, sedimentary characteristics, and origin of the Dongsha submarine canyon in the northeastern continental slope of the South China Sea

The Dongsha submarine canyon is a large canyon belonging to a group of canyons on the northeastern South China Sea margin Investigation of the Dongsha canyon is important for understanding the origin of this canyon group as well as the transport mechanism of sediments on the margin, and the evolution of the Taixinan foreland basin and the associated Taiwan orogenic belt. In this study, the morphology, sedimentary characteristics, and origin of the Dongsha canyon were investigated by inte- grating high-resolution multi-channel seismic reflection profiles and high-precision multibeam bathymetric data. This is a slope-confined canyon that originates in the upper slope east of the Dongsha Islands, extends downslope in the SEE direction, and finally merges with the South Taiwan Shoal canyon at a water depth of 3000 m. The total length and average width of the canyon are around 190 and 10 km, respectively. Eleven seismic sequence boundaries within the canyon fills were identified and interpreted as incision surfaces of the canyon. In the canyon fills, four types of seismic facies were defined： parallel onlap fill, chaotic fill, mounded divergent facies, and migrated wavy facies. The parallel onlap fill facies is interpreted as altemating coarser turbidites or other gravity-flow deposits and fine hemipelagic sediments filling the canyon valley. The chaotic fill faci- es is presumed to be debrites and/or basal lag deposits filling the thalwegs. The mounded divergent and migrated wavy seismic facies can be explained as canyon levees consisting mainly of overspilled fine turbidites and sediment waves on the levees or on the canyon-mouth submarine fans. Age correlation between the sequence boundaries and the ODP Site 1144 data suggests that the Dongsha canyon was initiated at approximately 0.9 Ma in the middle Pleistocene. Mapping of the canyon indicates that the canyon originated at the upstream portion of the middle reach of the modem canyon, and has been continuously expanding both upstream and downstream by retrogressive erosion, incision, and deposition of turbidity currents and other gravity transport processes. The ages of the sequence boundaries representing major canyon incision events are in good agreement with those of global sea-level lowstands, indicating that sea-level changes may have played an important role in the canyon＇s development. The Dongsha canyon developed in a region with an active tectonic background characterized by the Taiwan up- lifting and the development of the Taixinan foreland basin. However, no evidence suggests that the canyon formation is directly associated with local or regional faulting and magmatic activities. Turbidity currents and other gravity transport processes （includ- ing submarine slides and slumps） may have had an important influence on the formation and evolution of the canyon.

Study on sedimentation distribution based on cooperative analysis of geologic-geophysical in less well area: A case study of Suweiyi sandstone in the DB area, Kuqa Depression in Tarim Basin

The Kuqa Depression in Tarim Basin develops fan deltaic,braided river deltaic,and lacustrine sedi-mentation,espeially extensive braided river deltaic sedimentation,in the Cretaceous-Paleogene Sys-tems.However,fine sedimentary pattern of the Kuqa Depression and North Tarim Uplift belt since the Middle Cenozoic still needs to be studied.As a combination zone of the Kuqa Depression and North Tarim Uplift,the sedimentary characteristics of the DB area in the southern margin of the east of the Kuqa depression have been paid more attention.To better understand the sedimentary framework in the Kuqa Depression and North Tarim Uplift in the Mesozoic and Cenozoic,through joint geologic-geophysical study,sedime ntation of sandstone at the bottom of the Paleogene Suweiyi Formation in the DB area and its peripheral area is investigated.Sedimentary facies and sandstone distribution in the area are identified through core observation,component analysis,logging interpretation and seismic inversion.Based on seismic facies analysis,sedimentary facies distribution in the area is delineated.Results show that sandstone at the bottom of the Paleogene Suweiyi Fommation in the DB area and its peripheral area is developed in shore shallow lacustrine beach-bar facies.The beach-bar arenaceous sediments are mainly distnibuted in the southern DB area and the shallow lacustrine mudstone is developed in northern DB area,showing obvious north south di ferentiation charactenistics.