Deep carbonate reservoir characterisation using multi-seismic attributes via machine learning with physical constraints

Chen, Yuanyuan; Zhao, Luanxiao; Pan, Jianguo; Li, Chuang; Xu, Minghui; Li, Kejian; Zhang, Fengshou; Geng, Jianhua

doi:10.1093/jge/gxab049

Cited by 35 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, integrating machine learning, digital twin, and data analysis approaches can enhance reservoir modeling and simulation, improving the accuracy of predictions and reducing uncertainty [16]. In addition, by incorporating physical constraints into machine learning models and digital twins, these approaches can provide more realistic representations of reservoir behavior and enable better estimation of reservoir properties [37].…”

Section: Opportunities Of Integrating Data-driven Approaches Into Res...mentioning

confidence: 99%

Reservoir Geomechanics: A Data-driven Approach

Korie,

Ogochukwu,

Innocent

2023

JENRR

View full text Add to dashboard Cite

Reservoir geomechanics is a crucial aspect of optimising and developing oil and gas activities, especially in maximising production. Recent technological advancements have revolutionised reservoir geomechanics studies, including integrating data-driven approaches. This review examines and integrates machine learning, data science, and data twin in reservoir studies. The primary aim is to identify the benefits, limitations, significant advancements, potential challenges, opportunities, and research gaps of data-driven approaches to reservoir geomechanics. Additionally, this study aims to create opportunities for further research to address these challenges. The review identifies cost-effectiveness, improved reservoir characterisation, and reduced operational risks as the benefits of integrating data-driven approaches in reservoir geomechanics. However, the review also highlights the significant challenges of data-driven approaches, such as insufficient datasets, limited interpretability, and limited transferability of models. By shedding light on these issues, this review provides a foundation for future research toward finding solutions to these challenges.

show abstract

Section: Opportunities Of Integrating Data-driven Approaches Into Res...mentioning

confidence: 99%

Reservoir Geomechanics: A Data-driven Approach

Korie,

Ogochukwu,

Innocent

2023

JENRR

View full text Add to dashboard Cite

show abstract

“…At present, the buried depth of the reservoir on the South Bank of Tahe River generally exceeds 7500 m, the formation temperature exceeds 160℃, the porosity is 0.4%-4.6%, and the permeability heterogeneity is strong. Deep carbonate reservoir has complex geological conditions and strong heterogeneity [1][2][3]. Based on the existing materials and previous research results, in this paper, through the fitting of fracture static pressure and fracture conductivity curve, the reservoir seepage characteristics are analyzed, the reservoir seepage characteristics were analyzed by using fracture static pressure fitting and fracture conductivity curve [4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Acid Fracturing Technology and Effect Evaluation of Carbonate Horizontal Well in Fuman Oilfield

Li,

Chen,

Wang

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Since the deep and ultra-deep carbonate rocks in the Fuman oilfield have made continuous breakthroughs, the acidification and fracturing of the reservoir on the south bank of Tarim River have been faced with problems such as faster acidification and shorter effective acidification fracture length with the increased burial depth and formation temperature, which seriously restrict the effect of acidification and fracturing. At present, the Fuman oilfield has achieved remarkable results after acid fracturing construction. In this paper, the acid fracturing construction effects of multiple reservoir reconstruction Wells in Tahe Yueman, Fuyuan, Guole, and Manshen blocks are evaluated and classified by analyzing acid fracturing construction curves, using fracture static pressure fitting and fracture conductivity curve analysis. The characteristics and distribution law of carbonate reservoirs corresponding to different construction curves are studied, and various situations of artificial fractures communicating with natural fracture-cavity systems are analyzed. The research results can accurately guide the design optimization and development of acid pressure.

show abstract

“…With the rapid development of deep learning algorithms, these algorithms are widely applied to the field of exploration geophysics and play an important role in fault detection Wu, Geng, et al, 2020), cave detection (Wu, Yan, et al, 2020;S. Wei et al, 2022;Yan et al, 2022) and reservoir characterization (Chen et al, 2021;Xu et al, 2022;Zhao et al, 2021). However, in the Shunbei area, the cave formation is controlled by faults, and the major caves are located around the fault zone (as shown in Figure 1).…”

Section: Introductionmentioning

confidence: 99%

“…Through the above studies, we find that the characterization of fault–karst reservoir is commonly implemented by detecting faults and caves, respectively, due to the distinctly different reflection characteristics of faults and caves on seismic data. With the rapid development of deep learning algorithms, these algorithms are widely applied to the field of exploration geophysics and play an important role in fault detection (Wu, Liang, Shi, & Fomel, 2019; Wu, Geng, et al., 2020), cave detection (Wu, Yan, et al., 2020; S. Wei et al., 2022; Yan et al., 2022) and reservoir characterization (Chen et al., 2021; Xu et al., 2022; Zhao et al., 2021). However, in the Shunbei area, the cave formation is controlled by faults, and the major caves are located around the fault zone (as shown in Figure 1).…”

Section: Introductionmentioning

confidence: 99%

Deep carbonate fault–karst reservoir characterization by multi‐task learning

Zhang,

Li,

Yan

et al. 2023

Geophysical Prospecting

View full text Add to dashboard Cite

The carbonate fault–karst reservoir is a special and significant reservoir in the Shunbei area, and the development of the cave has been controlled by strike‐slip faults. Due to the complex subsurface structures, fault–karst reservoir characterization is generally divided into fault and cave detection tasks. The potential spatial relationships between faults and caves might be neglected by using the separate detection scheme. The multi‐task learning network can perform multiple tasks simultaneously and exploit the potential features of training data by using a deep neural network. In this study, we built fault–karst models based on the geological background of the Shunbei area and synthesized fault–karst training data using three‐dimensional point spread function convolution. Then, we developed a multi‐task learning network to learn fault–karst features and detect faults and caves simultaneously. The test result demonstrates that the multi‐task learning network trained by synthetic fault–karst data can effectively identify the faults and caves in field seismic data. The comparisons of the multi‐task learning network, single‐task learning networks and conventional methods demonstrate the importance of spatial relationships between faults and caves and show the superiority of the multi‐task learning network. This technique could significantly assist in the exploration, development and well deployment for an ultra‐deep carbonate reservoir.

show abstract

Deep carbonate reservoir characterisation using multi-seismic attributes via machine learning with physical constraints

Cited by 35 publications

References 33 publications

Reservoir Geomechanics: A Data-driven Approach

Reservoir Geomechanics: A Data-driven Approach

Acid Fracturing Technology and Effect Evaluation of Carbonate Horizontal Well in Fuman Oilfield

Deep carbonate fault–karst reservoir characterization by multi‐task learning

Contact Info

Product

Resources

About