Lithology Identification Research Articles

A New Strategy to Fuse Remote Sensing Data and Geochemical Data with Different Machine Learning Methods

Geochemical data can reflect geological features, making it one of the basic types of geodata that have been widely used in mineral exploration, environmental assessment, resource potential analysis and other research. However, final decisions regarding activities are often limited by the spatial accuracy of geochemical data. Geochemical sampling is sometimes difficult to conduct because of harsh natural and geographic conditions (e.g., mountainous areas with high altitude and complex terrain), meaning that only medium/low-precision survey data could be obtained, which may not be adequate for regional geochemical mapping and exploration. Modern techniques such as remote sensing could be used to address this issue. In recent decades, the development of remote sensing technology has provided a huge amount of earth observation data with high spatial, temporal and spectral resolutions. The advantage of rapid acquisition of spatial and spectral information of large areas has promoted the broad use of remote sensing data in geoscientific research. Remote sensing data can help to differentiate various ground features by recording the electromagnetic response of the surface to solar radiation. Many problems that occur during the process of fusing remote sensing and geochemical data have been reported, such as the feasibility of existing fusion methods and low fusion accuracies that are less useful in practice. In this paper, a new strategy for integrating geochemical data and remote sensing data (referred to as ASTER data) is proposed; this strategy is achieved through linear regression as well as random forest and support vector regression algorithms. The results show that support vector regression can obtain better results for the available data sets and prove that the strategy currently proposed can effectively support the fusion of high-spatial-resolution remote sensing data (15 m) and low-spatial-resolution geochemical data (2000 m) in wide-range accurate geochemical applications (e.g., lithological identification and geochemical exploration).

Channel attention-based static-dynamic graph convolutional network for lithology identification with scarce labels

Accurately identifying the complicated lithology distribution of unconventional reservoirs has become an urgent need for oil and gas exploitation. However, the expensive and rare lithology labels limit the precision of current machine learning-based lithology identification methods. Meanwhile, those methods neglect the associated information implicit in adjacent logging samples and underutilize the abundant unlabeled data. In this paper, a channel attention-based static-dynamic graph convolutional network for lithology identification is proposed to solve the problem of scarce labels. To utilize the unlabeled logging data adequately, logging graphs are modeled based on geographic distance and feature similarity to characterize associated information as well as logging features. On the basis, the dynamic similarity graph is introduced to magnify distinctions and reduce connections between samples with different lithologies, improving the quality of logging graphs. Aiming at enhancing the model performance of eliminating redundant and noisy information in logging graphs, the channel attention mechanism is taken into account to realize the fusion and complementation between different associated information. Verification experiments are conducted by utilizing the logging datasets from a shale formation. Results show that the proposed approach has general applicability and achieves high identification accuracy for various strata. Moreover, the proposed approach reduces the cost of drilling coring for lithology identification immensely and can serve as a reference for applying graph theory to solve future reservoir-related issues in petroleum exploitation.

Lithology identification using graph neural network in continental shale oil reservoirs: A case study in Mahu Sag, Junggar Basin, Western China

The continental shale oil reservoir of Fengcheng Formation in the northern slope area of Mahu Sag, Junggar Basin, Western China is very heterogeneous in lithology. Thus, the complex response characteristics of conventional logging and limited core availability in the study area has led to major challenges in lithology identification. Therefore, to resolve lithology identification by well logs in continental shale oil reservoirs, a graph neural network (GNN) method named GraphSAGE is used to train the lithology identification model based on a constructed graph, which connects the samples with adjacent depth and similar log response features on operator intention. The identification process is divided into two parts: first, based on the formation depth sequence and affinity propagation clustering method, the vertical distribution of the stratum and nodes logging curve similarity information are integrated into the graph structure, which structurally represents the conventional logging curves as graph instead of well logs as input data; Second, the nodes of the constructed graph are classified by GraphSAGE, which naturally supports combination generalization and improves sample complexity accompanied by strong relational inductive bias. To examine the effectiveness of GraphSAGE for lithology identification, a conventional log dataset labelled by direct core observations from two separate wells in Muhu Sag are used. The identification results showed that the accuracy of GraphSAGE for the lithologies exceeds 90% of the testing data, especially for transitional lithology such as dolomitic mudstone, silty mudstone and tuffaceous fine sandstone. Compared with the commonly used machine learning methods such as SVM, RF and XGBoost, GraphSAGE was more accurate in lithology identification, matching core observations. Collectively, this reflects the superiority of graph neural network in conventional logging lithology identification and effective means provided for lithology identification of continental shale oil reservoir in the Mahu Sag.

Reservoir Lithology Identification Based on Multicore Ensemble Learning and Multiclassification Algorithm Based on Noise Detection Function.

Reservoir lithology identification is an important part of well logging interpretation. The accuracy of identification affects the subsequent exploration and development work, such as reservoir division and reserve prediction. Correct reservoir lithology identification has important geological significance. In this paper, the wavelet threshold method will be used to preliminarily reduce the noise of the curve, and then the MKBoost-MC model will be used to identify the reservoir lithology. It is found that the prediction accuracy of MKBoost-MC is higher than that of the traditional SVM algorithm, and though the operation of MKBoost-MC takes a long time, the speed of MKBoost-MC reservoir lithology identification is much higher than that of manual processing. The accuracy of MKBoost-MC for reservoir lithology recognition can reach the application standard. For the unbalanced distribution of lithology types, the MKBoost-MC algorithm can be effectively suppressed. Finally, the MKBoost-MC reservoir lithology identification method has good applicability and practicality to the lithology identification problem.

Cross-Well Lithology Identification Based on Wavelet Transform and Adversarial Learning

For geological analysis tasks such as reservoir characterization and petroleum exploration, lithology identification is a crucial and foundational task. The logging lithology identification tasks at this stage generally build a lithology identification model, assuming that the logging data share an independent and identical distribution. This assumption, however, does not hold among various wells due to the variations in depositional conditions, logging apparatus, etc. In addition, the current lithology identification model does not fully integrate the geological knowledge, meaning that the model is not geologically reliable and easy to interpret. Therefore, we propose a cross-domain lithology identification method that incorporates geological information and domain adaptation. This method consists of designing a named UAFN structure to better extract the semantic (depth) features of logging curves, introducing geological information via wavelet transform to improve the model’s interpretability, and using dynamic adversarial domain adaptation to solve the data-drift issue cross-wells. The experimental results show that, by combining the geological information in wavelet coefficients with semantic information, more lithological features can be extracted in the logging curve. Moreover, the model performance is further improved by dynamic domain adaptation and wavelet transform. The addition of wavelet transform improved the model performance by an average of 6.25%, indicating the value of the stratigraphic information contained in the wavelet coefficients for lithology prediction.

The Influence of Continental Mixosedimentite Sedimentation on Shale Oil Sweet Spot: A Case Study on the Permian Lucaogou Formation in the Jimsar Sag of the Junggar Basin, NW China

Over the years, shale oil has been at the leading edge of oil exploration and also become the hotspot of reserve increases for various oil fields. The Permian Lucaogou Formation in the Jimsar Sag has been less extensively researched in terms of, among others, lithologic interpretation of fine-grained mixosedimentite, identification and classification of sedimentary microfacies, and sweet spot evaluation. The present study identifies the classification of sedimentary microfacies, characteristic distribution of sedimentary reservoir, and spatial configuration distribution of facies-controlled sweet spot body based on core logging, cutting logging, and data while drilling, combined with logging information, experimental analysis data, and production data with respect to formation test and production test and through the lithology identification based on element logging. This study indicated the following: 1) Microfacies of the reservoir body include a shallow lacustrine sand bar, mixing beach, and dolomitic flat. Different microfacies are adapted to different lithologies or lithological associations. 2) The lower sweet spots P2l12−3, P2l12−2, and P2l12−1 evolved into the dolomitic flat from mixing beach from NE to W. Also, the dolomitic flat is mostly developed in the west of the work area, and the mixing beach is better developed in the east. The shallow lacustrine sand bar is highly developed in the middle location, and the mixing beach and shallow lacustrine sand bar are highly developed on the northern and southern sides. 3) Sedimentary microfacies have evident controls over sweet spots. The upper sweet spots P2l22−3 and P2l22−2 are dominated by Class I sweet spots followed by Class II and IV sweet spots, which are major sweet spot reservoirs. The upper sweet spot P2l22−1 is mainly suffused with Class IV sweet spots, and the Class I reservoir is feldspathic litharenite (shallow lacustrine sand bar microfacies accordingly).

LITHOFACIES DISTRIBUTION AND DEPOSITIONAL ARCHITECTURAL STUDIES OF THE MIOCENE DEPOSITS OF THE “THOR” FIELD, COASTAL SWAMP DEPOBELT, NIGER DELTA BASIN, NIGERIA

The study accesses the petrophysical data from the Eocene deposit of the “Thor” field, Coastal swamp depobelt, Niger Delta and process it to decipher the different lithological makeup, the reservoir units, the depositional architecture and how these factors influenced reservoir distribution within the field. The study made use of well logs consisting of gamma ray, resistivity, neutron and density logs. Gamma ray log aided lithological identification, resistivity logs help to isolate reservoir rocks from non-reservoir rocks while neutron and density logs was used to differentiate oil or gas zones. Three hydrocarbon reservoirs designated as R-1, R-2 and R-3 were interpreted from the logs and the sand bodies show a lateral continuity within the field in the north-eastern direction. Log sequences analysis of the field made use of a combination of gamma ray and restively logs via electro-sequence identification and mapping of key stratigraphic surfaces and the identification of para-sequences including retrogadational, aggradational and progradational stacking pattern leading to the delineation of the environment of deposition. The three stratigraphic surfaces enable the classification of the field into two depositional sequences and further subdivision into three system tracts. The first depositional sequence is interpreted as the oldest and lies at the base which is about 1201ft thick while the second depositional sequence overlies the first sequence with about 1605ft in thickness and is interpreted to be younger. Sediments within the two sequences are thought to be deposited in deltaic environment within the marginal to shallow marine settings.

Application of improved support vector machine in geochemical lithology identification

Application of improved support vector machine in geochemical lithology identification

Analysis and selection of measurement indexes of MWD in rock lithology identification

Based on the measurement indexes monitored by the roof bolter while drilling, the rock properties, fractures and other rock stratum characteristics can be obtained, which provide important basics for risk assessment of underground engineering, design of safety measures and determination of parameters. In this study, the measurement indexes include distance, thrust, torque and vibration in three directions s are measured by various types of sensors in laboratory when drilling two different bricks and their combined sample under fixed rotational speed. Through the research and analysis of the measurement data, the data of different drilling stages are also analyzed, more importantly, the test parameter difference and the obvious degree of the parameters in distinguishing the two types of bricks are obtained. The study results are of great significance for the selection of monitoring measurement indexes of roof bolter while drilling.

Unsupervised Machine Learning Techniques for Improving Reservoir Interpretation Using Walkaway VSP and Sonic Log Data

In this paper, we present a detailed analysis of the possibility of using unsupervised machine learning techniques for reservoir interpretation based on the parameters obtained from geophysical measurements that are related to the elastic properties of rocks. Four different clustering algorithms were compared, including balanced iterative reducing and clustering using hierarchies, the Gaussian mixture model, k-means, and spectral clustering. Measurements with different vertical resolutions were used. The first set of input parameters was obtained from the walkaway VSP survey. The second one was acquired in the well using a full-wave sonic tool. Apart from the study of algorithms used for clustering, two data pre-processing paths were analyzed in the context of matching the vertical resolution of both methods. The validation of the final results was carried out using a lithological identification of the medium based on an analysis of the drill core. The measurements were performed in Silurian rocks (claystone, mudstone, marly claystone) lying under an overburdened Zechstein formation (salt and anhydrite). This formation is known for high attenuating seismic signal properties. The presented study shows results from the first and only multilevel walkaway VSP acquisition in Poland.

Reservoir Lithology Identification Based on Improved Adversarial Learning

Reservoir lithology identification is critical to reservoir characterization, reserves calculation, and geological modeling. The deep learning lithology identification method is a data-driven algorithm for establishing the relationship between lithology-sensitive properties and litho-types from a large amount of observed data. The lithology label is inadequate for high drilling and core recovery costs. Consequently, we propose a reservoir lithology identification method based on improved adversarial learning to relieve the overfitting problem and the multi-solution problem caused by inadequate labeled data and massive learnable parameters in training. Firstly, a probabilistic lithology classification neural network (PLCNN) is constructed to predict lithology from density, P-velocity, and S-velocity. In addition, we design an improved adversarial learning (IAL) lithology identification workflow to train the PLCNN with limited labeled data and large-scale unlabeled data. In the workflow, a lightweight discrimination network is established to ensure that the prediction result of the PLCNN is consistent with the data distribution characteristics of real underground lithology. Finally, the proposed method is successfully applied to the Book cliffs model. Compared with the conventional supervised learning workflow, the misclassification of sand and sandy shale can be relieved efficiently with the IAL workflow, and the classification accuracy can be improved to 92.71%.

Logging identification of complex lithology of the Lower Jurassic Da'anzhai Member in the eastern slope of the western Sichuan Depression

In recent years, with the in-depth development of oil and gas exploration in the eastern slope of the western Sichuan Depression, breakthroughs have been made in the research on high-quality gas reservoirs in the Da'anzhai Member of the Ziliujing Formation in this area. Fine logging identification of lithology in the Da'anzhai Member in the eastern slope of the western Sichuan Depression is the core subject of reservoir sweet spot prediction. In this paper, taking the Da'anzhai Member in the western Sichuan Basin as an example, the work flow and comparisons of multi-lithology logging models have been systematically conducted, using a large number of cores, geological data and logging interpretation models. The research shows that there are four main lithologies developed in the Da'anzhai Member, namely shale, marl-bearing limestone, shell limestone and sandstone. Intersection and spider diagram methods can effectively screen out the logging parameters that are sensitive to lithology, including natural gamma (GR), neutron (CNL), deep lateral resistivity (RD), and acoustic wave time difference (AC). The lithology of the Da'anzhai Member in the study area can be identified with high precision via the "lithology probability factor", "BP neural network" and cluster analysis methods. Among them, the "lithologic probability factor" and "BP neural network" methods have a prediction accuracy of lithology exceeds 80%. Therefore, these two methods are optimized as the most effective methods for logging identification of lithology in the Da'anzhai Member. This study has certain reference value for the lithology identification of similar gas reservoirs worldwide. • The calculation and comparison of multi-lithology logging models have been systematically conducted, using a large number of cores, geological data and logging interpretation models. • The lithology of the Da'anzhai Member in the study area can be identified with high precision by the "lithology probability factor" method, the "BP neural network" method and the cluster analysis method. • A complex lithology identification model is established.

Time-Domain Elastic Full Waveform Inversion With Frequency Normalization

Time-domain elastic full waveform inversion (FWI) uses seismic data to recover the high-resolution subsurface medium properties for structural imaging and lithologic identification. The approximate pulse generated by the explosion source in seismic exploration evolves into a limited bandwidth seismic wavelet through the propagation of the seismic wave in the underground medium, exhibiting strong energy near the dominant frequency and weak energy far away. Therefore, time-domain FWI using the band-limited seismic wavelet can only match the energy of the dominant frequencies present in a dataset to a large extent, resulting in insufficient low-wavenumber updates of model parameters because of the weak energy of low frequencies. To remove the effect of finite-frequency-band wavelet spectra from the time-domain FWI, we propose a time-domain elastic FWI without wavelet spectral limitation. In our method, a newly refined seismic wavelet with a normalized amplitude and accurate phase is used to propagate seismic waves in the time domain. Data residual measurement is performed based on the summation of single-frequency residuals between the normalized synthetic and observed frequencies. The adjoint-state method is used to approximate the gradients of the model parameters, and the decoupled wavefields obtained by the phase-sensitive detection method were involved in the gradient calculation. Overall, the proposed method helps FWI avoid falling into local minima by enhancing the low wavenumber reconstruction of the velocity models. The elastic FWI numerical tests and field data FWI application demonstrate that our approach can reliably recover high-precision inversion results.

Integrating Aster Images Processing and Fieldwork for Identification of Hydrothermal Alteration Zones at the Oumjrane-Boukerzia District, Moroccan Anti-Atlas

Mapping from remote sensing has become more effective in the field of geology, mainly in lithological discrimination and identification of hydrothermal alteration zones. The use of this technique consists in obtaining information about the rock mass and the main ones existing in the inaccessible areas. Satellite data from the ASTER (Advanced Spaceborne Thermal Emission and Reflection Radiometer) sensor represent a favorable potential for detecting the spectral signatures of mineral zones and identifying their nature. These data are more reliable in places where the climate is arid with less abundant vegetation, as at the Oumjrane-Boukerzia mining district. This region which is part of the Eastern Anti-Atlas, is composed of several mineralized veins which still require detailed studies and exploration by the technique of remote sensing. In this work we applied several processing techniques on ASTER imagery such as Colored Composition, Principal Component Analysis and Ratio Bands. The use of the reports of the specialized Bands makes it possible to identify some hydrothermal alteration minerals within the mining district of Oumjrane Boukerzia. These minerals are represented mainly by iron oxides and hydroxides (Hematite, jarosite, limonite and goethite), carbonate minerals (dolomite, calcite), clay minerals (Illite, kaolinite and chlorite) and quartz minerals. This work allows us to produce a map of hydrothermal alteration zones which can be used as a valuable reference in the strategy of mining exploration for the base metals (Cu, Pb, Zn and Ba), in the mining district of Oumjrane-Boukerzia and in the entire Eastern Anti-Atlas.

Joint elastic reverse time migration of towed streamer and sparse ocean-bottom seismic node hybrid data

Compared to 1C towed-streamer (TS) seismic exploration, 4C ocean-bottom seismic (OBS) node exploration has great advantages in complex structure imaging, lithology, and fluid identification using elastic waves. However, sparse spatial sampling of OBS node surveys highlights the problems of the imaging acquisition footprint, poor phase continuity, and low signal-to-noise ratio (S/N) with conventional elastic reverse time migration (ERTM) methods. Therefore, a solution of joint ERTM (J-ERTM) is proposed by combining sparse OBS node data with dense TS data. In the J-ERTM of the hybrid data, a novel weighted boundary condition combined with acoustic-elastic coupling equations and a vector-based crosscorrelation imaging condition are presented to perform PP and PS imaging by receiver-side tensorial extrapolation of TS and OBS node hybrid data. A synthetic example demonstrates that our method can effectively process TS and OBS node hybrid data and improve elastic imaging problems caused by OBS node sparse acquisition. J-ERTM techniques also are applied to an active-source OBS data set from the South China Sea. To improve the imaging quality with limited data, some preprocessing procedures for field TS and OBS node hybrid data sets are necessary, such as denoising, OBS node relocation, OBS node orientation correction, OBS node calibration, and others. After preprocessing, the pressure component and velocity components have a more physical energy relationship, more consistent frequency range and wavelet, and a higher S/N. Finally, the preprocessed hybrid data can be used for J-ERTM. The imaging results demonstrate that our method works well with field data.

Lithology identification technology based on the stacking fusion model

Lithology identification technology based on the stacking fusion model

RESERVOIR CHARACTERIZATION OF THE ‘SHULA FIELD’, OFFSHORE NIGER DELTA BASIN, NIGERIA: AN INTEGRATED APPROACH

This study analyzed “Shula field” offshore Niger Delta basin for it hydrocarbon bearing capacity. Well logs and seismic data were used for the analysis. Well logs consisting of gamma ray, resistivity, neutron and density logs for five different wells were used. Gamma ray logs aided lithological identification, resistivity logs were used to delineate hydrocarbon bearing zones while a combination of neutron and density logs aided in distinguishing oil and gas zones. Three hydrocarbon bearing sands (reservoirs) of varying thickness designated as RES-AA, RES-BB and RES-CC were identified. Well log correlation of the five wells revealed lateral continuity of the sand units thinning out in northwestern direction of the study field. The range values of gross thickness (GT), net-to-gross (NTG), volume of shale (VSH), effective porosity (ΦEff), permeability (K), hydrocarbon saturation (Sh) and water saturation (SW) for RES-AA reservoir are 51-74ft, 0.88-98%, 0.10-11%, 24-28%, 174-734mD, 8-80%, and 20-92% respectively. RES-BB reservoir range values of (GT), (NTG), (VSH), (ΦEff), (K), (Sh) and (SW) are 47-65ft, 83-98%, 8-14%, 24-32%, 234-1880mD, 4-78%, and 22-96% respectively while the RES-CC reservoir range values of (GT), (NTG), (VSH), (ΦEff), (K), (Sh) and (SW) are 121-191ft, 82-96%, 8-11%, 23-31%, 125-1352mD, 9-88% and 12-91% respectively. Sixteen faults were identified and interpreted comprising of nine synthetic and seven antithetic faults. The time and depth structural maps show the subsurface structural geometry and possible hydrocarbon migration and trapping potential. The probable structure trapping hydrocarbon in the study field is anticlinal structure and four-way closure. The volumetric calculation revealed that reservoir RES-AA has 951 × 106 bbl, reservoir RES-BB has 1058 × 106 bbl and reservoir RES-CC has 1688 × 106 bbl of oil originally in place (OIIP). Generally, the petrophysical results and the volumetric calculation for the field confirm an economically viable investment potential except for reservoir RES-AA, wellbore ZY-005 with 8% Sh, reservoir RES-BB, wellbore ZY-003 and ZY-005 with 4% Sh, and 7% Sh respectively and reservoir RES-CC, wellbore ZY-005 with 9% Sh. Therefore, these four reservoir units may be screen out during production to reduce the rate of water cut thereby increasing the producing life of the field.

A Lithology Identification Approach Using Well Logs Data and Convolutional Long Short-Term Memory Networks

A Lithology Identification Approach Using Well Logs Data and Convolutional Long Short-Term Memory Networks

Lithology identification technology based on the stacking fusion model

Lithology identification technology based on the stacking fusion model

Igneous rocks lithology identification with deep forest: Case study from eastern sag, Liaohe basin

At present, volcanic reservoir exploration has been carried out widely in the world. In the eastern sag of Liaohe Basin, different volcanic eruption periods lead to complex facies and lithology of igneous rocks, which brings difficulties to logging interpretation. Therefore, a method to accurately identify igneous rock lithology is urgently needed. In this paper, the scheme for identifying igneous rock lithology uses multiple deep forest classifiers. To select a practical training set, 944 conventional logs (AC, DEN, GR, RLLD, and CNL) with lithologic labels were randomly selected from the target area. Compared with the test sets selected from other formations, the accuracy of the scheme reached 99.96%. The scheme was applied to three wells in the same area, and excellent results were achieved when the predicted lithology was compared with the lithology profile and thin section data.