基于XGBoost的低渗油田储层粒度预测
作者:

Prediction of Reservoir Grain Size in Low Permeability Oilfield Based on XGBoost
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [19]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    针对低渗油田储层粒度预测问题, 本文提出利用机器学习中的极致剃度提升树(extreme gradient boosting, XGBoost)来对低渗油田储层粒度进行预测的方案. 首先, 根据问题构建合适的XGBoost模型, 然后根据已有的岩心储层粒度特征值与其余测井信息的关系, 选取适用于粒度预测的测井曲线建立样本库, 最后利用样本库数据对建立的XGBoost模型进行训练, 训练后的模型即可预测研究区域未知的储层粒度特征. 结果表明, 本文所设计的XGBoost模型对低渗油田的储层粒度预测方案在计算效率、预测准确率等方面均优于BP神经网络.

    Abstract:

    To address the prediction problems of reservoir grain sizes in low permeability oilfields, this study proposes a scheme for predicting reservoir grain sizes in low permeability oilfields with the extreme gradient boosting (XGBoost) in machine learning. First, a proper XGBoost model is built in consideration of the problems. Then, well logging curves suitable for grain size prediction are selected to create a sample database according to the established relationships of the characteristic values of the core reservoir grain size with other logging information. Finally, sample database data are employed to train the newly built XGBoost model. The trained model can predict unknown reservoir grain size characteristics in a study area. The results show that the XGBoost model designed in this study is superior to the back propagation (BP) neural network in calculation efficiency and prediction accuracy of reservoir grain sizes in low permeability oilfields.

    参考文献
    [1] 张金庆, 杨凯雷, 梁斌. 我国海上低渗油田分类标准研究. 中国海上油气, 2012, 24(6): 25–27
    [2] 童天喜, 刘敏. 成本控制的内生动力. 中国石油企业, 2014, (1–2): 100–101
    [3] 陈欢庆, 舒治睿, 林春燕, 等. 粒度分析在砾岩储层沉积环境研究中的应用——以准噶尔盆地西北缘某区克下组冲积扇储层为例. 西安石油大学学报(自然科学版), 2014, 29(6): 6–12, 34
    [4] 阎媛子. 红河油田长6段储层粒度分析. 中国石油和化工标准与质量, 2016, 36(12): 64–65. [doi: 10.3969/j.issn.1673-4076.2016.12.038
    [5] 田宇昕. 粒度分析及其地质应用. 西部探矿工程, 2020, 32(1): 159–160. [doi: 10.3969/j.issn.1004-5716.2020.01.052
    [6] 李月. 低渗油田提高单井产量技术策略探析. 化学工程与装备, 2020, (1): 146–147
    [7] Liu H, Guo R, Dong JC, et al. Productivity evaluation and influential factor analysis for Sarvak reservoir in South Azadegan oil field, Iran. Petroleum Exploration and Development, 2013, 40(5): 627–634. [doi: 10.1016/S1876-3804(13)60082-8
    [8] Hossain S, El-Shafie A, Wan Mohtar WHM. Application of intelligent optimization techniques and investigating the effect of reservoir size in calibrating the reservoir operating policy. Water Policy, 2015, 17(6): 1143–1162. [doi: 10.2166/wp.2015.023
    [9] Abedelrigeeb AG, Al-Khudafi AM, Baarimah SO, et al. Hybrid artificial intelligent approach for choke size estimation in volatile and black oil reservoirs. 2019 First International Conference of Intelligent Computing and Engineering. Hadhramout: IEEE, 2019. 1–5.
    [10] Li H, Misra S, He JB. Neural network modeling of in situ fluid-filled pore size distributions in subsurface shale reservoirs under data constraints. Neural Computing and Applications, 2020, 32(8): 3873–3885. [doi: 10.1007/s00521-019-04124-w
    [11] 杨宁, 王贵文, 赖锦, 等. 应用伽马测井曲线小波变换计算粒度参数. 现代地质, 2012, 26(4): 778–783. [doi: 10.3969/j.issn.1000-8527.2012.04.020
    [12] 王利华, 楼一珊, 马晓勇, 等. 储层粒度神经网络预测模型研究. 西南石油大学学报(自然科学版), 2016, 38(1): 53–59
    [13] 房茂军, 曾祥林, 梁丹. 人工神经网络在储层粒度预测中的应用. 油气藏监测与管理国际会议论文集. 西安: 西安华线网络信息服务有限公司, 2011. 99–104.
    [14] 邓浩阳. 高孔低渗碳酸盐岩储层孔隙结构及物性表征方法研究[博士学位论文]. 成都: 西南石油大学, 2018.
    [15] 李佳. 基于机器学习的多孔介质渗透率预测研究[硕士学位论文]. 杭州: 浙江大学, 2019.
    [16] Bagheri M, Rezaei H. Reservoir rock permeability prediction using SVR based on radial basis function kernel. Carbonates and Evaporites, 2019, 34(3): 699–707. [doi: 10.1007/s13146-019-00493-4
    [17] Zhang GY, Wang ZZ, Li HJ, et al. Permeability Prediction of isolated channel sands using machine learning. Journal of Applied Geophysics, 2018, 159: 605–615. [doi: 10.1016/j.jappgeo.2018.09.011
    [18] 李建平, 梁胜松, 范友贵. 基于量子神经网络的超深层储层评价. 计算机与数字工程, 2018, 46(12): 2499–2505. [doi: 10.3969/j.issn.1672-9722.2018.12.024
    [19] Chen T, Guestrin C. XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco: ACM, 2016. 785–794.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

李建平,张小庆,李莹.基于XGBoost的低渗油田储层粒度预测.计算机系统应用,2022,31(2):241-245

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-04-23
  • 最后修改日期:2021-05-19
  • 在线发布日期: 2022-01-28
文章二维码
您是第11418035位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号