Diagenetic Facies Classification in the Arbuckle Formation Using Deep Neural Networks

Deng, Tianqi; Xu, Chicheng; Lang, Xiaozheng; Doveton, John H.

doi:10.1007/s11004-021-09918-0

Cited by 13 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The models deployed in this paper are implemented in TensorFlow Keras banked (Chollet, 2015). We mainly focus on one‐dimensional convolutional neural network (1D CNN) architecture due to their high success in tackling similar tasks (Brazell et al ., 2019; Imamverdiyev and Sukhostat, 2019, and Wang et al ., 2020; Deng et al ., 2021), as well as in several multi‐sensor problems that use time‐series data (e.g., Abdoli et al . (2019), Gadzicki et al .…”

Section: Methodsmentioning

confidence: 99%

“…The models deployed in this paper are implemented in Ten-sorFlow Keras banked (Chollet, 2015). We mainly focus on one-dimensional convolutional neural network (1D CNN) architecture due to their high success in tackling similar tasks (Brazell et al, 2019;Imamverdiyev andSukhostat, 2019, andWang et al, 2020;Deng et al, 2021), as well as in several multi-sensor problems that use time-series data (e.g., Abdoli et al (2019), Gadzicki et al (2020), and Münzner et al (2017)). Additionally, CNN's versatility and avoidance of complex feature engineering and extensive preprocessing of the input data is an important advantage that contributed to this choice.…”

Section: Deep Learning Implementationmentioning

confidence: 99%

See 1 more Smart Citation

Automated well log depth matching: Late fusion multimodal deep learning

Caceres

Duffaut

Yazidi

et al. 2022

Geophysical Prospecting

View full text Add to dashboard Cite

Petrophysical interpretation and optimal correlation extraction of different measurements require accurate well log depth matching. We have developed a supervised multimodal machine learning alternative for the task of simultaneously matching raw logging while drilling and electrical wireline logging logs. Seven one‐dimensional convolutional neural networks are trained using different log measurements: gamma‐ray, resistivity, P‐ and S‐wave sonic, density, neutron and photoelectric factors, and their depth shift estimates are aggregated using different multimodal late fusion strategies. We test the late fusion average, late fusion weighted average, late fusion with linear and nonlinear learners and model‐level fusion. Depth matching results using the different fusion strategies applied to two unseen wells are compared using visual inspection and the mean Pearson correlation. All models perform well, increasing the correlation after depth matching. Late fusion weighted average achieves the highest scores for all log types. The late fusion weighted average results are compared to a cross‐correlation user‐assisted workflow and manual depth matching for validation. In general, the convolutional neural network fused method exhibits a lower performance than the traditional methods. For one of the wells, the cross‐correlation shows higher correlation values than the other methods but for the second well the manual depth match performs best. However, the differences in Pearson correlation values are small ranging from 0.01 to 0.1. The manual depth match performs very well for the sonic logs, which tend to require slightly larger depth shifts than the other measurements, thus a common depth shift might not always be suitable. Although our convolutional neural network fused approach is limited to estimating bulk shifts and uses constant fusion weights, its performance is similar to that of more time‐consuming methods. Our approach might be substantially improved by including dynamic shifts (stretch/squeeze) and depth‐dependent fusion weights via long‐short‐term memory recurrent neural networks.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Deep Learning Implementationmentioning

confidence: 99%

Automated well log depth matching: Late fusion multimodal deep learning

Caceres

Duffaut

Yazidi

et al. 2022

Geophysical Prospecting

View full text Add to dashboard Cite

show abstract

“…Many studies have focused on establishing diagenetic facies interpretation models using logging curves, but it is still difficult to predict. The methods for establishing these models include the discriminant analysis method, such as the cross plot method (Fan et al, 2018); linear discriminant analysis (LDA) (Trevor et al, 2014); hierarchical cluster analysis (HCA) (Wang and Lu, 2021); K-Nearest Neighbor (KNN) (Cui et al, 2017); machine learning methods, such as back propagation neural networks (BPNN) and support vector machine (SVM) (Wang and Lu, 2021); and deep learning methods, such as convolutional neural networks (CNN) and recurrent neural networks (RNN) (Zhou et al, 2018;Xu et al, 2019;Deng et al, 2021). These algorithms have been successfully applied in other fields; however, the predicted results are biased to types with large sample numbers under real geological conditions, such as limited and unbalanced sample data (Cuddy and Glover, 2002;Richa et al, 2006;Dubois et al, 2007;Chauhan et al, 2015;Bhattacharya et al, 2019;Khalifah et al, 2020;Vikara et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Diagenetic facies characteristics and quantitative prediction via wireline logs based on machine learning: A case of Lianggaoshan tight sandstone, fuling area, Southeastern Sichuan Basin, Southwest China

Zhang

Wang

et al. 2022

Front. Earth Sci.

View full text Add to dashboard Cite

Tight sandstone has low porosity and permeability, a complex pore structure, and strong heterogeneity due to strong diagenetic modifications. Limited intervals of Lianggaoshan Formation in the Fuling area are cored due to high costs, thus, a model for predicting diagenetic facies based on logging curves was established based on few core, thin section, X-ray diffraction (XRD), scanning electron microscopy (SEM), cathodoluminescence, routine core analysis, and mercury injection capillary pressure tests. The results show that tight sandstone in the Lianggaoshan Formation has primary and secondary intergranular pores, secondary intragranular pores, and intergranular micropores in the clay minerals. The compaction experienced by sandstone is medium to strong, and the main diagenetic minerals are carbonates (calcite, dolomite, and ferric dolomite) and clay minerals (chlorite, illite, and mixed illite/montmorillonite). Four types of diagenetic facies are recognized: carbonate cemented (CCF), tightly compacted (TCF), chlorite coating and clay mineral filling (CCCMFF), and dissolution facies (DF). Primary pores develop in the CCCMFF, and secondary pores develop in the DF; The porosities and permeabilities of CCCMFF and DF are better than that of CCF and TCF. The diagenetic facies were converted to logging data, and a diagenetic facies prediction model using four machine learning methods was established. The prediction results show that the random forest model has the highest prediction accuracy of 97.5%, followed by back propagation neural networks (BPNN), decision trees, and K-Nearest Neighbor (KNN). In addition, the random forest model had the smallest accuracy difference between the different diagenetic facies (2.86%). Compared with the other three machine learning models, the random forest model can balance unbalanced sample data and improve the prediction accuracy for the tight sandstone of the Lianggaoshan Formation in the Fuling area, which has a wide application range. It is worth noting that the BPNN may be more advantageous in diagenetic facies prediction when there are more sample data and diagenetic facies types.

show abstract

Supervised Mineral Prospectivity Mapping via Class-Balanced Focal Loss Function on Imbalanced Geoscience Datasets

Zhang

Wang

et al. 2023

Math Geosci

View full text Add to dashboard Cite

Diagenetic Facies Classification in the Arbuckle Formation Using Deep Neural Networks

Cited by 13 publications

References 25 publications

Automated well log depth matching: Late fusion multimodal deep learning

Automated well log depth matching: Late fusion multimodal deep learning

Diagenetic facies characteristics and quantitative prediction via wireline logs based on machine learning: A case of Lianggaoshan tight sandstone, fuling area, Southeastern Sichuan Basin, Southwest China

Supervised Mineral Prospectivity Mapping via Class-Balanced Focal Loss Function on Imbalanced Geoscience Datasets

Contact Info

Product

Resources

About