ZHANG Jiachen1,2, DENG Jin'gen1,2, TAN Qiang1,2, SHI Lin1
1. College of Petroleum Engineering, China University of Petroleum (Beijing), Beijing 102249, China; 2. State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum (Beijing), Beijing 102249, China
Abstract：Well logs play an important role in the formation evaluation. However, well log data might be missing or incomplete due to operational and geological issues in the logging process. As the reconstruction of well logs based on traditional empirical models and multiple regression method is less accurate, machine learning is proposed. Considering the limitation of the traditional neural network, XGBoost is utilized to build the reconstruction model for well logs. The directional wells in Bohai Bay Basin are exemplified to verify the model with the experiments of well log imputation and generation. The proposed model is compared with traditional machine learning models such as gradient lifting decision tree (GBDT), random forest (RF), and fully connected neural network (FNN) through K-fold cross-validation. The prediction effect is analyzed combined with the geological background. Results show that reconstruction of well logs based on XGBoost achieves high prediction accuracy, stability, and strong generalization ability.
张家臣, 邓金根, 谭强, 石林. 基于XGBoost的测井曲线重构方法[J]. 石油地球物理勘探, 2022, 57(3): 697-705.
ZHANG Jiachen, DENG Jin'gen, TAN Qiang, SHI Lin. Reconstruction of well logs based on XGBoost. Oil Geophysical Prospecting, 2022, 57(3): 697-705.
王濡岳, 丁文龙, 王哲, 等. 页岩气储层地球物理测井评价研究现状[J]. 地球物理学进展, 2015, 30(1):228-241.WANG Ruyue, DING Wenlong, WANG Zhe, et al. Progress of geophysical well logging in shale gas re-servoir evaluation[J]. Progress in Geophysics, 2015, 30(1):228-241.
[2]
HEIDARI Z, TORRES-VERDÍN C, PREEG W E. Improved estimation of mineral and fluid volumetric concentrations from well logs in thinly bedded and invaded formations[J]. Geophysics Journal of the Socie-ty of Exploration Geophysicists, 2012, 77(3):WA79.
[3]
AVSETH P, SKJEI N, SKALNES A. Rock physics modelling of 4D time-shifts and time-shift derivatives using well log data:a North Sea demonstration[J]. Geophysical Prospecting, 2013, 61(2):380-390.
[4]
SINGH U K. Fuzzy inference system for identification of geological stratigraphy off Prydz Bay, East Antarctica[J]. Journal of Applied Geophysics, 2011, 75(4):687-698.
[5]
CHEN Y K, CHEN H M, XIANG K, et al. Geologi-cal structure guided well log interpolation for high-fidelity full waveform inversion[J]. Geophysical Journal International, 2016, 207(2):1313-1331.
[6]
OWOLABI A O, OMANG B O, OYETADE O P, et al. Reservoir evaluation and volumetric analysis of Rancho field, Niger delta, using well log and 3D seismic data[J]. Open Journal of Geology, 2019, 9(13):974-987.
[7]
廖茂辉. 多元回归方法校正扩径对密度曲线声波曲线的影响[J]. 物探与化探, 2014, 38(1):174-179, 184.LIAO Maohui. The application of multiple regression method to the calibration of the influence of hole enlargementon density and acoustic logs[J]. Geophysical and Geochemical Exploration, 2014, 38(1):174-179, 184.
[8]
MOUSAVI S M A, SHADIZADEH S R, RIAHI M A, et al. NMR log prediction from seismic attributes:Using multiple linear regression and neural network methods[J]. Energy Sources Part A-Recovery Utilization and Environmental Effects, 2015, 37(7):781-789.
[9]
LORENZEN R. Multivariate linear regression of so-nic logs on petrophysical logs for detailed reservoir characterization in producing fields[J]. Interpretation, 2018, 6(3):T531-T541.
[10]
HILL E J, PEARCE M A, STROMBERG J M. Improving automated geological logging of drill holes by incorporating multiscale spatial methods[J]. Mathematical Geosciences, 2021, 53(1):21-53.
[11]
何旭, 李忠伟, 刘昕, 等. 应用卷积神经网络识别测井相[J]. 石油地球物理勘探, 2019, 54(5):1159-1165.HE Xu, LI Zhongwei, LIU Xin, et al. Log facies re-cognition based on convolutional neural network[J]. Oil Geophysical Prospecting, 2019, 54(5):1159-1165.
[12]
WANG G C, CARR T R, JU Y W, et al. Identifying organic-rich Marcellus Shale lithofacies by support vector machine classifier in the Appalachian basin[J]. Computers & Geosciences, 2014, 64(3):52-60.
[13]
REN X X, HOU J G, SONG S H, et al. Lithology identification using well logs:A method by integrating artificial neural networks and sedimentary patterns[J]. Journal of Petroleum Science and Engineering, 2019, 182(5):106336.
[14]
付超, 林年添, 张栋, 等. 多波地震深度学习的油气储层分布预测案例[J]. 地球物理学报, 2018, 61(1):293-303.FU Chao, LIN Niantian, ZHANG Dong, et al. Prediction of reservoirs using multi-component seismic data and the deep learning method[J]. Chinese Journal of Geophysics, 2018, 61(1):293-303.
[15]
张国印, 王志章, 林承焰, 等. 基于小波变换和卷积神经网络的地震储层预测方法及应用[J]. 中国石油大学学报(自然科学版), 2020, 44(4):83-93.ZHANG Guoyin, WANG Zhizhang, LIN Chengyan, et al. Seismic reservoir prediction method based on wavelet transform and convolutional neural network and its application[J]. Journal of China University of Petroleum (Edition of Natural Science), 2020, 44(4):83-93.
[16]
MA Y Z, GOMEZ E, LUNEAU B. Integration of seismic and well-log data using statistical and neural network methods[J]. The Leading Edge, 2017, 36(4):324-329.
[17]
张东晓, 陈云天, 孟晋. 基于循环神经网络的测井曲线生成方法[J]. 石油勘探与开发, 2018, 45(4):598-607.ZHANG Dongxiao, CHEN Yuntian, MENG Jin. Synthetic well logs generation via recurrent neural networks[J]. Petroleum Exploration and Development, 2018, 45(4):598-607.
[18]
ONALO D, ADEDIGBA S, KHAN F, et al. Data driven model for sonic well log prediction[J]. Journal of Petroleum Science & Engineering, 2018, 170:1022-1037.
[19]
HAN J, LU C H, CAO Z M, et al. Integration of deep neural networks and ensemble learning machines for missing well logs estimation[J]. Flow Measurement and Instrumentation, 2020, 73:101748.
[20]
张宝录, 罗丹婷, 胡鹏, 等. 一种基于深度神经网络模型的测井曲线生成方法[J]. 电子测量技术, 2020, 43(11):107-111.ZHANG Baolu, LUO Danting, HU Peng, et al. A well log curve generation method based on deep neural network[J]. Electronic Measurement Technology, 2020, 43(11):107-111.
[21]
余本国. BP神经网络局限性及其改进的研究[J]. 山西农业大学学报(自然科学版), 2009, 29(1):89-93.YU Benguo. Discussion on the limitation and improvement of BP neural network[J]. Journal of Shanxi Agricultural University(Natural Science Edition), 2009, 29(1):89-93.
[22]
FENG R H, GRANA D, BALLING N. Imputation of missing well log data by random forest and its uncertainty analysis[J]. Computers & Geosciences, 2021, 152:104763.
[23]
CHEN T Q, GUESTRIN C. XGBoost:A scalable tree boosting system[C]. Proceedings of the 22nd ACM SIGKDD International Conference on Know-ledge Discovery and Data Mining, 2016, 785-794.
[24]
FAN Z Y, ZHAN Q M, YANG C, et al. Estimating PM2.5 concentrations using spatially local XGBoost based on Full-Covered SARA AOD at the urban scale[J]. Remote Sensing, 2020, 12(20):3368.
[25]
陈振宇, 刘金波, 李晨, 等. 基于LSTM与XGBoost组合模型的超短期电力负荷预测[J]. 电网技术, 2020, 44(2):614-620.CHEN Zhenyu, LIU Jinbo, LI Chen, et al. Ultra short-term power load forecasting based on combined LSTM-XGBoost model[J]. Power System Technology, 2020, 44(2):614-620.
[26]
闫星宇, 顾汉明, 肖逸飞, 等. XGBoost算法在致密砂岩气储层测井解释中的应用[J]. 石油地球物理勘探, 2019, 54(2):447-455.YAN Xingyu, GU Hanming, XIAO Yifei, et al. XGBoost algorithm applied in the interpretation of tight-sand gas reservoir on well logging data[J]. Oil Geophysical Prospecting, 2019, 54(2):447-455.
[27]
谷宇峰, 张道勇, 鲍志东. 测井资料PSO-XGBoost渗透率预测[J]. 石油地球物理勘探, 2021, 56(1):26-37.GU Yufeng, ZHANG Daoyong, BAO Zhidong. Permeability prediction using PSO-XGBoost based on logging data[J]. Oil Geophysical Prospecting, 2021, 56(1):26-37.
[28]
ZHONG R Z, JOHNSON R, CHEN Z W. Generating pseudo density log from drilling and logging-while-drilling data using extreme gradient boosting (XGBoost)[J]. International Journal of Coal Geology, 2020, 220:103416.
[29]
SAGI O, ROKACH L. Approximating XGBoost with an interpretable decision tree[J]. Information Sciences, 2021, 572:522-542.
[30]
GÓMEZ-RÍOS A, LUENGO J, HERRERA F. A study on the noise label influence in boosting algorithms:AdaBoost, GBM and XGBoost[C]. International Conference on Hybrid Artificial Intelligent Systems, 2017.
