Stacking ensemble learning based inversion for three-dimensional distribution region of hydraulic fractures in shale

Luo, Yang; Kang, Bo; Wang, Hehua; Guo, Jianchun; Jiang, Liping; Cheng, Yi; Xiao, Yong; Zhao, Xing; Sun, Bao; Zhang, Ran; Lu, Cong

doi:10.1016/j.geoen.2024.212712

Cited by 2 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fundamental purpose of evaluating fracturing effects is to enhance the success rate of fracturing operations, optimize fracturing design technology, enhance post-fracturing production, and guide production management post-fracturing (Zhang et al, 2020;Wang et al, 2022;Guo et al, 2023;Luo et al, 2024). The evaluation of the stimulated reservoir volume (SRV) fracturing effect entails a comprehensive assessment of the overall quality of fracturing construction.…”

Section: Introductionmentioning

confidence: 99%

Quantitative characterization of stimulated reservoir volume (SRV) fracturing effects in naturally fractured unconventional hydrocarbon reservoirs

Ren,

Dou,

Dong

et al. 2024

Front. Earth Sci.

View full text Add to dashboard Cite

Stimulated reservoir volume (SRV) fracturing has become the most efficient technology in the treatment of unconventional hydrocarbon reservoir formations. This process aims to optimize well productivity by establishing an intricate network of fractures that integrate hydraulic and natural fractures, distal to the wellbore, thereby amplifying the contact area with the subterranean formations and fracture systems. This study introduces a quantitative framework designed to characterize the fracturing effects within naturally fractured unconventional hydrocarbon reservoirs. Leveraging existing fracturing treatment designs and production performance data, the study formulates a mathematical model of the complex fracture network, predicated on the principle of material balance. The model comprehensively accounts for the development degree of natural fractures, the morphological impact of stress differentials on the fracture network, and the imbibition displacement effects of the fracturing fluids. The model’s accuracy is verified through an integration with microseismic monitoring data and an enhanced understanding of reservoir development. Building upon this foundation, the study quantitatively dissects the impact of various engineering parameters on the efficacy of SRV fracturing. The proposed quantitative characterization method is adept for widespread application across multiple wells in oil and gas fields, offering a distinct advantage for the swift and precise assessment of SRV fracturing outcomes in naturally fractured unconventional hydrocarbon reservoirs. The research method, which is based on readily accessible fracturing construction data and is more convenient, can to a certain extent improve the efficiency of hydraulic fracturing evaluation work.

show abstract

Section: Introductionmentioning

confidence: 99%

Quantitative characterization of stimulated reservoir volume (SRV) fracturing effects in naturally fractured unconventional hydrocarbon reservoirs

Ren,

Dou,

Dong

et al. 2024

Front. Earth Sci.

View full text Add to dashboard Cite

show abstract

Generative Adversarial Network-Based Framework for Accurate DTS Logging Curve Generation in Heterogeneous Reservoirs

Luo,

Kang,

Cheng

et al. 2024

Day 1 Wed, June 26, 2024

View full text Add to dashboard Cite

Accurate generation of missing share wave slowness (DTS) logging curve is significant for the precise reservoir evaluation. While various data-driven prediction models have been proposed, only a few addresses the intricate details of the DTS curve shape, and it is significant for reservoirs with strong heterogeneity. In this study, a novel DTS generation framework consisting of generator and discriminator was established based on generative adversarial network. In the generator, with the input of compressional wave slowness and compensated neutron curves, the recurrent neural network was applied to gain insight into the general pattern and generate DTS curves. In the discriminator, the convolutional neural network was adopted to compare the detailed shape and evaluate the realness of generated DTS curves. Both the generator and discriminator underwent concurrent training, aiming for model convergence and achieving a close distribution resemblance between the generated DTS curves and authentic data. The proposed DTS generation framework was practically applied in a shale gas field in the Sichuan basin of China. By segmenting the complete logging curves from over 100 wells, 47200 sequences with a length of 32 were obtained in the dataset. After 50 rounds and 26900 training cycles, the generation model exhibited robust performance with an average relative error of 0.015, and a coefficient of determination of 0.91. The frequency distribution of the generated DTS value closely resembled that of the real ones, confirming the generation ability for both overall fluctuation and local detailed shape. Moreover, a blind test on logging curves in 8 wells revealed a high shape agreement between the generated and real DTS curves, indicating the applicability of the proposed generation framework. Unlike the conventional approaches emphasizing the overall trend of DTS curves, the proposed framework introduces an additional discriminator to enhance the generation ability for intricate local details, leading to significantly improved generation performance. This study underscores the potential of advanced artificial intelligence methodologies for precious logging curve generation.

show abstract

Stacking ensemble learning based inversion for three-dimensional distribution region of hydraulic fractures in shale

Cited by 2 publications

References 22 publications

Quantitative characterization of stimulated reservoir volume (SRV) fracturing effects in naturally fractured unconventional hydrocarbon reservoirs

Quantitative characterization of stimulated reservoir volume (SRV) fracturing effects in naturally fractured unconventional hydrocarbon reservoirs

Generative Adversarial Network-Based Framework for Accurate DTS Logging Curve Generation in Heterogeneous Reservoirs

Contact Info

Product

Resources

About