Prediction of Total Organic Carbon Content of Source Rocks in Paleogene Salinized Lake Basin in Western Qaidam Basin

doi:10.3969/j.issn.1006-6535.2021.01.010

Abstract

Abstract: In view of the influence of salinized environment on organic carbon prediction of source rocks in western Qaidam Basin, the optimized ΔlgR method, multiple regression method and BR-BP neural network method were used to simulate organic carbon content according to salinity changes, and the differences of organic carbon prediction results of the three models were discussed. The results show that: The prediction effect of multiple regression model is general.The accuracy of the optimized ΔlgR model is higher than that of the multiple regression model, but its universality is general.The BR-BP neural network model has different performance in high salinity and medium-low salinity areas, but the prediction effect is better. Therefore, we propose applying the neural network model to predict in medium-low salinity areas, and conducting comprehensive calculation by reasonably adjusting the parameters of the neural network model and combining with the ΔlgR model in high salinity areas. The research results can improve the accuracy of source rock identification and guide accurate source rock evaluation in the basin.

Key words: organic carbon prediction, salinized environment, neural network, model optimization, prediction model, well logging parameter, western Qaidam Basin

CLC Number:

TE133

Tai Wanxue, Liu Chenglin, Tian Jixian, Feng Dehao, Zeng Xu, Li Pei, Kong Hua. Prediction of Total Organic Carbon Content of Source Rocks in Paleogene Salinized Lake Basin in Western Qaidam Basin[J]. Special Oil & Gas Reservoirs, 2021, 28(1): 74-80.

References

[1] TAN M J,LIU Q,ZHANG S Y.A dynamic adaptive radial basis function approach for total organic carbon content prediction in organic shale[J].Geophysics,2013,78(6):445-459.
[2] SHALABY M R,JUMAT N,LAI D,et al.Integrated TOC prediction and source rock characterization using machine learning,well logs and geochemical analysis:case study from the Jurassic source rocks in Shams Field,NW Desert,Egypt[J].Journal of Petroleum Science & Engineering.2019,176:369-380.
[3] 徐新德,陶倩倩,曾少军,等.基于地化-测井-地震联合反演的优质烃源岩研究方法及其应用——以涠西南凹陷为例[J].中国海上油气,2013,25(3):13-18.
XU Xinde,TAO Qianqian,ZENG Shaojun,et al.A method to evaluate high-quality source rocks based on geochemistry-logging-seismic joint-inversion and its application:a case of Weixinan Sag in Beibuwan Basin[J].China Offshore Oil and Gas,2013,25(3):13-18.
[4] 杨涛涛,范国章,吕福亮,等.烃源岩测井响应特征及识别评价方法[J].天然气地球科学,2013,24(2):414-422.
YANG Taotao,FAN Guozhang,LYU Fuliang,et al.The logging features and identificationg methods of source rock[J].Natural Gas Geoscience,2013,24(2):414-422.
[5] PASSEY Q R,CREANEY S,KULLA J B,et al.Practical model for organic richness from porosity and resistivity logs[J].AAPG Bulletin,1990,74(12):1777-1794.
[6] ZHAO P Q,MAO Z Q,HUANG Z Q,et al.A new method for estimating total organic carbon content from well logs[J].AAPG Bulletin,2016,100(8):1311-1327.
[7] 王祥,马劲风,张新涛,等.一种考虑密度因素的广义ΔlgR法预测总有机碳含量——以渤中凹陷西南部陆相深层烃源岩为例[J].地球物理学进展,2020,35(4):1471-1480.
WANG Xiang,MA Jinfeng,ZHANG Xintao,et al.Prediction of total organic carbon content by a generalized ΔlgR method considering density factors:illustrated by the example of deep continental source rocks in the southwestern part of the Bozhong Sag[J].Progress in Geophysics,2020,35(4):1471-1480.
[8] 边雷博,柳广弟,孙明亮,等.优化的ΔlgR技术及其在中—深层烃源岩总有机碳含量预测中的应用[J].油气地质与采收率,2018,25(4):40-45.
BIAN Leibo,LIU Guangdi,SUN Mingliang.Improved ΔlgR technique and its application to predicting total organic carbon of source rocks with middle and deep burial depth[J].Petroleum Geology and Recovery Efficiency,2018,25(4):40-45.
[9] JOHNSON L M,REAZAEE R,KADKHODAIE A,et al.Geochemical property modelling of a potential shale reservoir in the Canning Basin (Western Australia),using artificial neural networks and geostatistical tools[J].Computers & Geosciences.2018,120:73-81.
[10] 庞国印,唐俊,王琪,等.利用概率神经网络预测成岩相——以鄂尔多斯盆地合水地区延长组长₈段储层为例[J].特种油气藏,2013,20(2):43-47.
PANG Guoyin,TANG Jun,WANG Qi,et al.Prediction of diagenetic facies with probabilistic neural network:taking member Chang₈ of Heshui Area in Ordos Basin as an example[J].Special Oil & Gas Reservoirs,2013,20(2):43-47.
[11] 刘志刚,肖佃师,许少华.基于离散过程神经网络页岩油气储层有机碳含量预测[J].中国石油大学学报(自然科学版),2017,41(2):80-87.
LIU Zhigang,XIAO Dianshi,XU Shaohua.Total organic carbon content prediction of shale reservoirs based on discrete process neural network[J].Journal of China University of Petroleum(Edition of Natural Science),2017,41(2):80-87.
[12] 袁颖,谭丁,于少将,等.基于贝叶斯正则化改进BP神经网络的页岩气有机碳含量预测模型[J].地质与勘探,2019,55(4):1082-1091.
YUAN Ying,TAN Ding,YU Shaojiang,et al.A prediction model for shale gas organic carbon content based on improved BP neural network using Bayesian regularization[J].Geology and Exploration,2019,55(4):1082-1091.
[13] GUO P,LIU C Y ,WANG L Q,et al.Mineralogy and organic geochemistry of the terrestrial lacustrine pre-salt sediments in the Qaidam Basin:implications for good source rock development[J].Marine and Petroleum Geology,2019,107:149-162.
[14] 张俊彪,陈雯,蔡春芳,等.采用主成分分析和BP神经网络算法预测池塘养鱼产量和换水量[J].河南农业科学,2020,49(6):174-180.
ZHANG Junbiao,CHEN Wen,CAI Chunfang,et al.Prediction of fish production and amount of exchanged water of aquaculture pond by principal component analysis and BP neural network algorithm[J].Journal of Henan Agricultural Sciences,2020,49(6):174-180.