Performance evaluation of machine learning-based classification with rock-physics analysis of geological lithofacies in Tarakan Basin, Indonesia

Antariksa, Gian; Muammar, Radhi; Lee, Jihwan

doi:10.1016/j.petrol.2021.109250

Cited by 38 publications

(17 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Cai et al, 2014;Avseth et al, 2014;Dutta et al, 2012) proposed a rock physical modeling method for medium-low-permeability tight rocks by analyzing the lithofacies type and burial history, that is, the CCT contact model is used to calculate the low porosity section (35%), while the HS upper limit is used to calculate the medium-porosity section (10%-35%) (He, 2017;Tang, 2011;Pan et al, 2019). In this study, considering the pore type and structure in the middlelow porosity and middle-low-permeability section, the DEM model and Gassmann equation, which are suitable for rock physical modeling of relatively high porosity, are used to calculate the equivalent rock physical model (Yin et al, 2017;Antariksa et al, 2022;Fawad and Mondol, 2022;Guo et al, 2016). Tight sandstone rock physical modeling is mainly composed of a boundary average model, inclusion model, fluid replacement model, and so on (Figure 5).…”

Section: Rock Physical Model Of Heterogeneous Tight Sandstonesmentioning

confidence: 99%

Rock Physical Modeling of Tight Sandstones Based on Digital Rocks and Reservoir Porosity Prediction From Seismic Data

et al. 2022

View full text Add to dashboard Cite

Digital rock physics (DRP) has become an important tool to analyze the characteristics of pore structures and minerals and reveal the relationships between microscopic structures and the physical properties of reservoirs. However, it is greatly difficult to upscale the rock physical parameters, such as P-wave velocity, S-wave velocity, and elastic moduli, from DRP to large-scale boreholes and reservoirs. On the other hand, theoretical rock physical modeling can establish the internal relationship between the elastic properties and physical parameters of tight sandstones, which provides a theoretical basis for seismic inversion and seismic forward modeling. Therefore, the combination of digital rock physics and rock physical modeling can guide the identification and evaluation of the gas reservoir’s “sweet spot.” In this study, the CT images are used to analyze the mineral and pore characteristics. After that, the V-R-H model is used to calculate the equivalent elastic moduli of rocks containing only the mineral matrix, and then, the differential equivalent medium (DEM) model is used to obtain the elastic moduli of dry rocks containing minerals and pores. Subsequently, the homogeneous saturation model is used to fill the fluids in the pores and the Gassmann equation is used to calculate the equivalent elastic moduli of the saturated rock of tight sandstones. Rock physical modeling is calibrated, and the reliability of the rock physical model is verified by comparing those with the logging data. Afterward, the empirical relationship of rock porosity established from CT images and rock elastic moduli is obtained, and then, the elastic parameters obtained by seismic data inversion are converted into porosity parameters by using this empirical relationship. Finally, the porosity prediction of large-scale reservoirs in the study area is realized to figure out the distribution of gas reservoirs with high porosity. The results show that the H3b and H3c sections of the study area exhibit higher porosity than H3a. For the H3b reservoir, the northeast and middle areas of the gas field are potential targets since their porosity is larger than that of others, from 10% to 20%. Because of the effects of the provenance from the east direction, the southeast region of the H3c reservoir exhibits higher porosity than others.

show abstract

Section: Rock Physical Model Of Heterogeneous Tight Sandstonesmentioning

confidence: 99%

Rock Physical Modeling of Tight Sandstones Based on Digital Rocks and Reservoir Porosity Prediction From Seismic Data

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Antariksa et al. (2022) launched a performance evaluation of some ML‐based classification based on a lithofacies prediction, and after a thorough analysis confirmed the effectiveness of RF. Nonetheless, for the pattern recognition, the most principal performance measure is prediction accuracy rather than robustness.…”

Section: Introductionmentioning

confidence: 98%

“…Dwivedi (2019, 2020) testified some sophisticated classifiers in the geological predictions, and according to a review of experimental results clarified that the application of RF for lithofacies is feasible. Antariksa et al (2022) launched a performance evaluation of some ML-based classification based on a lithofacies prediction, and after a thorough analysis confirmed the effectiveness of RF. Nonetheless, for the pattern recognition, the most principal performance measure is prediction accuracy rather than robustness.…”

Section: Introductionmentioning

confidence: 99%

Lithofacies prediction driven by logging‐based Bayesian‐optimized ensemble learning: A case study of lacustrine carbonate reservoirs

Zhang

Wang³

et al. 2022

Geophysical Prospecting

View full text Add to dashboard Cite

Although lithofacies routinely is featured by distinct logging responses from each other, many types of lithofacies in practical cases show similar measuring characteristics on logs, and then to achieve a desirable solution from logging‐based lithofacies prediction actually is challengeable. Since the mathematical essence of lithofacies prediction can be explained as an issue of pattern recognition, a light gradient boosting machine, a state‐of‐the‐art ensemble learning, specifically developed to address supervised classification, could be a potential solver. Nonetheless, due to an incompatibility of inherent exclusive feature bundling algorithm for logs and usage of a great deal of hyper‐parameters, a raw light gradient boosting machine might not be suitable or functional to predict lithofacies. Thus, continuous restricted Boltzmann machine and Bayesian optimization, respectively, employed to process original logging data and optimize hyper‐parameters, are adopted as technical assistants for the light gradient boosting machine, and accordingly a new ensemble learning‐based predictor called continuous restricted Boltzmann machine – Bayesian optimization – the light gradient boosting machine, is proposed for lithofacies. To validate classifying capability and robust nature of new predictor, three experiments are designed purposefully based on the application of a dataset collected from the wells located within pre‐salt lacustrine carbonate reservoirs of the Santos Basin. Simultaneously, to highlight validating effect, other three sophisticated classifiers are introduced as competitors in all experiments, including supper vector machine, random forest and extreme gradient boosting. According to the analysis and comparison of all experimental results, overall four points are verified: (1) the integration of continuous restricted Boltzmann machine and Bayesian optimization indeed is beneficial for the light gradient boosting machine in data preprocess and modelling stage; (2) the light gradient boosting machine cored predictor shows more capability of producing reliable predicted lithofacies information compared to other three competitors; (3) training more learning samples is a simple and effective approach to enhance computing capability of any validated predictor, and under this circumstance the light gradient boosting machine cored predictor still performs relatively better; (4) the light gradient boosting machine cored predictor is characterized with a better robustness as its predicting outcomes, even derived from a sparse‐condition dataset, are also proved more qualified. Consequently, the new proposed predictor is demonstrated as a high‐efficient and robust solver for the prediction of lithofacies and deserves a widespread application in the geological, geophysical and petrophysical research.

show abstract

“…Supervised learning methods are more concerned with the correlations between geological properties and logging responses. These include Bayesian inversion (Qin et al, 2018;Feng, 2021), decision trees (Ren et al, 2022), support vector machines (SU et al, 2020), neural networks (Gu et al, 2019), gradient boosting algorithms (Gu et al, 2021;Al-Mudhafar et al, 2022;Zheng et al, 2022), random forests (Antariksa et al, 2022), and emerging deep learning methods (Song et al, 2020;Liu and Liu, 2022). Among these methods, Bayesian inversion can apply different prior frameworks and likelihood models to avoid inappropriate transitions among different lithofacies in geology and petrophysics (Hammer et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

Lithofacies logging identification for strongly heterogeneous deep-buried reservoirs based on improved Bayesian inversion: The Lower Jurassic sandstone, Central Junggar Basin, China

Zheng

Zhang²,

Cheng³

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

The strong heterogeneity characteristics of deep-buried clastic low-permeability reservoirs may lead to great risks in hydrocarbon exploration and development, which makes the accurate identification of reservoir lithofacies crucial for improving the obtained exploration results. Due to the very limited core data acquired from deep drilling, lithofacies logging identification has become the most important method for comprehensively obtaining the rock information of deep-buried reservoirs and is a fundamental task for carrying out reservoir characterization and geological modeling. In this study, a machine learning method is introduced to lithofacies logging identification, to explore an accurate lithofacies identification method for deep fluvial-delta sandstone reservoirs with frequent lithofacies changes. Here Sangonghe Formation in the Central Junggar Basin of China is taken as an example. The K-means-based synthetic minority oversampling technique (K-means SMOTE) is employed to solve the problem regarding the imbalanced lithofacies data categories used to calibrate logging data, and a probabilistic calibration method is introduced to correct the likelihood function. To address the situation in which traditional machine learning methods ignore the geological deposition process, we introduce a depositional prior for controlling the vertical spreading process based on a Markov chain and propose an improved Bayesian inversion process for training on the log data to identify lithofacies. The results of a series of experiments show that, compared with the traditional machine learning method, the new method improves the recognition accuracy by 20%, and the predicted petrographic vertical distribution results are consistent with geological constraints. In addition, SMOTE and probabilistic calibration can effectively handle data imbalance problems so that different categories can be adequately learned. Also the introduction of geological prior has a positive impact on the overall distribution, which significantly improves the accuracy and recall rate of the method. According to this comprehensive analysis, the proposed method greatly enhanced the identification of the lithofacies distributions in the Sangonghe Formation. Therefore, this method can provide a tool for logging lithofacies interpretation of deep and strongly heterogeneous clastic reservoirs in fluvial-delta and other depositional environments.

show abstract

Performance evaluation of machine learning-based classification with rock-physics analysis of geological lithofacies in Tarakan Basin, Indonesia

Cited by 38 publications

References 31 publications

Rock Physical Modeling of Tight Sandstones Based on Digital Rocks and Reservoir Porosity Prediction From Seismic Data

Rock Physical Modeling of Tight Sandstones Based on Digital Rocks and Reservoir Porosity Prediction From Seismic Data

Lithofacies prediction driven by logging‐based Bayesian‐optimized ensemble learning: A case study of lacustrine carbonate reservoirs

Lithofacies logging identification for strongly heterogeneous deep-buried reservoirs based on improved Bayesian inversion: The Lower Jurassic sandstone, Central Junggar Basin, China

Contact Info

Product

Resources

About