Academic Journal of Engineering and Technology Science, 2025, 8(1); doi: 10.25236/AJETS.2025.080103.
Penghu Liu1, Mancang Dong1, Xing Yang1, Qiang Cui2,3, Shasha Yang2
1Fuxian Oil Production Plant of Yanchang Oilfield Co., Ltd, Yan'an, Shaanxi, 727500, China
2School of Petroleum Engineering and Environmental Engineering, Yan'an University, Yan'an, Shaanxi, 716000, China
3Engineering Research Center of Efficient Exploitation of Oil and Gas Resources and Protection Ecological Environment, Yan'an, Shaanxi, 716000, China
The accurate identification of oil and gas reservoir space is paramount in the field of oil and gas exploration, as it directly influences the success and efficiency of drilling operations. In recent years, deep learning technology, particularly convolutional neural networks (CNN), has emerged as the most widely adopted artificial intelligence method for image recognition tasks. By leveraging the powerful feature extraction capabilities of CNN, researchers and industry professionals can now identify the type and content of reservoir spaces with unprecedented objectivity and accuracy. This approach not only minimizes human error and subjective interpretation but also significantly reduces labor costs and enhances overall work efficiency. Notably, the application of CNN in the identification of the reservoir space of the Chang 8 oil-bearing group in the Ordos Basin has yielded impressive results, demonstrating its practical value and promotion significance in the oil and gas industry. This technological advancement holds great promise for improving the exploration and development of oil and gas resources worldwide.
Recognition of Oil and Gas Reservoir Space, Convolutional Neural Network, Chang 8 Reservoir
Penghu Liu, Mancang Dong, Xing Yang, Qiang Cui, Shasha Yang. Recognition of Oil and Gas Reservoir Space Based on Convolutional Neural Network. Academic Journal of Engineering and Technology Science (2025) Vol. 8, Issue 1: 18-23. https://doi.org/10.25236/AJETS.2025.080103.
[1] Du Chenyu. Research on Reservoir Identification Methods Based on Convolutional Neural Networks [D]. Chengdu University of Technology, 2018.
[2] Hu Qing. Research on Aircraft Target Detection Technology in Remote Sensing Images Based on Convolutional Neural Networks [D]. Strategic Support Force Information Engineering University, 2022.
[3] Liu Xiuli, Xu Xiaoli. Fault Diagnosis Method Based on Feature Pyramid Convolutional Recurrent Neural Network [J]. Journal of Shanghai Jiao Tong University, 2022, 56(02): 182-190.
[4] Lin Jing. Elastic Parameter Inversion of Tight Reservoirs Based on a Physics-Model-Driven Deep Convolutional Neural Network [D]. Xi'an Jiaotong University, 2021.
[5] Liu Ye, Pan Yan, Xia Rongkai, et al. FP-CNNH: A Fast Image Hashing Algorithm Based on Deep Convolutional Neural Networks [J]. Computer Science, 2016, 43(09): 39-46+51.
[6] Gong Ying. Provenance Analysis of the Triassic Sediments in the Southern Margin of the Ordos Basin and Its Basin-Mountain Coupling Relationship [D]. Chang'an University, 2022.
[7] Zhang Tianyu. Geo-Morphological Evolution of the Late Cenozoic Basin in the Southwestern Margin of the Ordos Basin [D]. Chang'an University, 2020.
[8] Liu Weigang. Sedimentary Tectonics and Evolutionary Characteristics of the Southern Segment of the Western Margin of the Ordos Basin in the Early Paleozoic Era [D]. Northwest University, 2014.
[9] Cao Hongxia. Study on the Migration and Evolution of Depositional Centers in the Ordos Basin during the Late Triassic Period [D]. Northwest University, 2008.
[10] Liu Xiaobo. Evolution of the Cenozoic Basin in the Western Margin of the Ordos Block [D]. Chinese Academy of Geological Sciences, 2019.