Classification of Shale Oil Horizontal Well Production: A Case Study of the Chang-7 Interval in the Ordos Basin
DOI:
https://doi.org/10.62051/ijnres.v7n1.02Keywords:
Shale Oil; Horizontal Well; Classification and Evaluation; K-means Algorithm.Abstract
This study analyzes 70 shale-oil horizontal wells in the Chang-7 interval of the Qingcheng Oilfield, Ordos Basin, using the K-means clustering algorithm to evaluate production capacity. The objective is to provide a foundation for differentiated development and refined management. First-year cumulative oil production was selected as the primary classification metric. The silhouette coefficient and elbow methods were used to determine the optimal cluster number. Results indicate that a three-class division is most appropriate: Class I wells (> 4,300 t, 21.7%), Class II wells (2,900-4,300 t, 40.8%), and Class III wells (< 2,900 t, 37.5%). Correlation analysis revealed distinct controlling factors for each well type. Class I wells are jointly influenced by engineering and geological conditions, with key parameters including drilled lateral length, proppant volume, and log-interpreted Class I intervals. Class II wells are primarily affected by engineering parameters and production practices, notably injected fluid volume, cluster number, pump rate, and shut-in duration. Class III wells are mainly governed by geological factors, with permeability, porosity, and average total organic carbon content being the most critical. The findings suggest that fracture-design and production strategies should be tailored to the specific controlling factors of each well type to enhance shale-oil development efficiency and achieve targeted exploitation. This approach offers a practical technical pathway and theoretical reference for classification management and optimization of shale-oil horizontal wells in the region.
References
[1] Li, E., Wang, Z., Guo, Y., Zhang, J., Bi, S., & Sun, B. (2025). Research on the synergistic inhibition of wax formation in shale oil system using efficient wax inhibitors: Experiments and mechanisms. Chemical Engineering Science, 121902.
[2] Chen, Y. J., Wang, H. Y., & Sharma, M. (2025). The benefits and challenges of well monitoring of Gulong shale oil. Earth Energy Science.
[3] Cao, J., Cai, M., Li, J., Guo, Z., Jiang, X., & Dong, G. (2025). Optimization of Volumetric Fracturing Stages and Clusters in Continental Shale Oil Reservoirs Based on Geology-Engineering Integration. Energies, 18(12), 3066.
[4] Liu, J., Wang, R., Song, P., Li, Y., & Zheng, S. (2025). Quantitative Characterization and Flow Simulation of Micropore Structure in Clastic Gas Reservoirs Based on Micron CT Scanning. ACS omega, 10(20), 20686-20700.
[5] Zhang, Z., Hu, J., & Zhang, Y. (2025). A semi-analytical model for fractured horizontal wells production considering imbibition during shut-in periods. Petroleum Science and Technology, 43(15), 1891-1909.
[6] Chaikine, I. A., & Gates, I. D. (2021). A machine learning model for predicting multi-stage horizontal well production. Journal of Petroleum Science and Engineering, 198, 108133.
[7] Liang, Z., Li, X., Zhou, H., Meng, L., Sun, A., Wu, Q., & Wen, H. (2025). Continental Shale Oil Reservoir Lithofacies Identification and Classification with Logging Data—A Case Study from the Bohai Bay Basin, China. Minerals, 15(5), 484.
[8] Chen, S., Wang, X., Li, X., Sui, J., Yang, Y., Yang, Q., ... & Dai, C. (2024). Geophysical prediction technology for sweet spots of continental shale oil: A case study of the Lianggaoshan Formation, Sichuan Basin, China. Fuel, 365, 131146.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Jiaming Liu, Yuechen Li, Yutong Li, Ruifei Wang

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.







