Conventional geological modeling methods are typically constrained by limited borehole data and are unable to effectively capture irregular stratigraphic variations within complex geological structures, resulting in modeling inaccuracies. To overcome these limitations, a novel geological modeling approach was proposed. In this method, a multi-layer perceptron model was employed to integrate borehole data with seismic interpretation data, enabling the learning of deviation patterns between seismic interpretation horizons and actual horizons. A multi-scale iterative prediction process based on horizon errors was then developed, in which horizon errors at different scales were progressively predicted and corrected to achieve accurate prediction of the spatial morphology of geological structures in unexplored regions. The proposed approach was validated using synthetic data from the North Sea Continental Shelf. The experimental results demonstrate that, in regular geological structures, an average prediction accuracy of 99.94% is achieved, with mean horizon boundary errors of 1.135 m, 1.266 m, and 1.127 m, corresponding to reductions of 98.3%, 97.65%, and 97.83%, respectively, compared with the IC-XGBoost method. In irregular geological structures, an average prediction accuracy of 99.95% is achieved, with mean horizon boundary errors of 1.021 m, 1.279 m, and 1.057 m, representing reductions of 98.82%, 97.37%, and 98.91%, respectively. These results verify that the proposed method can significantly enhance the accuracy and robustness of geological modeling in complex structural settings.It is obvious that the proved method plays an obvious role in improving the prediction accuracy of the layer and the stability of geological modeling.
DING Chen-wen, WANG Zhao-jun, CHEN Dong, LI Wen-ji, ZHUANG Jia-fan, YE Zhi-hui, FAN Zhun.
Machine Learning-based Stratigraphic Interface Prediction Model of Joint Inversion of Seismic and Borehole Data[J].
Science Technology and Engineering, 2026, 26(11): 4511-4523 DOI:10.12404/j.issn.1671-1815.2504228
基于仿真数据开展了地质建模与分析实验,旨在验证本文研究模型在建模准确性和层位深度预测精度上的优势,并与现有的IC-XGBoost(factor IC prediction using XGBoost)模型[18]进行对比分析。实验在以下硬件环境下完成:Intel(R) Core(TM) i7-9700KCPU(3.60 GHz)、NVIDIA GeForceGTX1660GPU和32GBRAM,操作系统为64位Windows11。
MinChao, WenGuoquan, LiXiaogang, et al. Research progress and application prospect of interpretable machinelearning in artificial intelligence of oil and gas industry[J]. Natural Gas Industry, 2024, 44(9): 114-126.
ZhongChuannan, SunWei, LiZeqi, et al. Discussion on hydrocarbon accumulation of deep carbonate rocks in Dayi Area of Southwest Sichuan[J]. Science Technology and Engineering, 2023, 23(27): 11570-11583.
LiYang, XueZhaojie, ChengZhe, et al. Progress and development directions of deep oil and gas exploration and development in China[J]. China Petroleum Exploration, 2020, 25(1): 45-57.
GuoXusheng, HuDongfeng, HuangRenchun, et al. Deep and ultra-deep natural gas exploration in the Sichuan Basin: progress and prospect[J]. Natural Gas Industry, 2020, 40(5): 1-14.
HeZhiliang, ZhaoXiangyuan, ZhangWenbiao, et al. Progress and direction of geological modeling for deep and ultra-deep carbonate reservoirs[J]. Oil & Gas Geology, 2023, 44(1): 16-33.
FanYuting, TaoSiying, LiHongbin, et al. Enlightenment of the three-dimensional model of Sijiazhai gold deposit in Western Sichuan to prospecting prediction[J]. Science Technology and Engineering, 2024, 24(12): 4861-4868.
ZhangWenbiao, ZhangYaxiong, DuanTaizhong, et al. Hierarchy modeling of the Ordovician fault-karst carbonate reservoir in Tuoputai area, Tahe oilfield, Tarim Basin, NW China[J]. Oil & Gas Geology, 2022, 43(1): 207-218.
[15]
XueL, LiD, DouH. Artificial intelligence methods for oil and gas reservoir development: current progresses and perspectives[J]. Advances in Geo-Energy Research, 2023, 10(1): 65-70.
LiYang, ZhongBaorong, XuXiaohong, et al. A spatial interpolation method based on multidimemsional scaling and adaptive boosting regressor: a geological attribute body case study[J]. Science Technology and Engineering, 2022, 22(26): 11334-11341.
WangYanmei, LiuXing. Three-dimensional geological modeling of pinch out bifurcation coal seam: method based on geostatistics and symbolic matrix[J]. Science Technology and Engineering, 2024, 24(4): 1402-1410.
[20]
PereiraP E C, RabeloM N, RibeiroC C, et al. Geological modeling by an indicator kriging approach applied to a limestone deposit in Indiara City-Goiás[J]. REM-International Engineering Journal, 2017, 70(3): 331-337.
[21]
AugustoF O, SoaresW, IrigarayC. Mapping of compactness by depth in a quaternary geological formation using deterministic and geostatistical interpolation models[J]. Environmental Earth Sciences, 2017, 76(17): 607.
WangMingchuan, DuanTaizhong. Facies sequence-based MPS reservoir facies modeling algorithm and its application[J]. Oil & Gas Geology, 2023, 44(1): 238-246.
[24]
AbulkhairS, MadaniN. Stochastic modeling of iron in coal seams using two-point and multiple-point geostatistics: a case study[J]. Mining, Metallurgy & Exploration, 2022, 39(3): 1313-1331.
JiaAilin, GuoZhi, GuoJianlin, et al. Research achievements on reservoir geological modeling of China in the past three decades[J]. Acta Petrolei Sinica, 2021, 42(11): 1506-1515.
[27]
LiuH, XiaS, FanC, et al. 3D geo-modeling framework for multisource heterogeneous data fusion based on multimodal deep learning and multipoint statistics: a case study in South China Sea[J]. EGUsphere, 2024, 2024: 1-44.
WangLixin, YinYanshu, WangHui, et al. A method of reconstructing 3D model from 2D geological cross-section based on self-adaptive spatial sampling: a case study of Cretaceous McMurray reservoirs in a block of Canada[J]. Petroleum Exploration and Development, 2021, 48(2): 347-359.
[30]
ShiC, WangY. Development of subsurface geological cross-section from limited site-specific boreholes and prior geological knowledge using iterative convolution XGBoost[J]. Journal of Geotechnical and Geoenvironmental Engineering, 2021(9): 147.
[31]
GuoJ, XuX, WangL, et al. GeoPDNN 1. 0: a semi-supervised deep learning neural network using pseudo-labels for three-dimensional shallow strata modelling and uncertainty analysis in urban areas from borehole data[J]. Geoscientific Model Development, 2024, 17(3): 957-982.
HuangYuan, DuanTaizhong, FanTailiang, et al. Depositional evolution history and formation mechanism of Cambrian carbonate platforms in Tahe Area: insights from stratigraphic forward modelling[J]. Acta Petrolei Sinica, 2022, 43(5): 617-636.
[34]
LiuJ, ZhaoJ, LiuQ, et al. Integration and application of 3D visualization technology and numerical simulation technology in geological research[J]. Environmental Earth Sciences, 2021, 80: 1-7.
ZhouYongzhang, XiaoFan. Overview: a glimpse of the latest advances in artificial intelligence and big data geoscience research[J]. Earth Science Frontiers, 2024, 31(4): 1-6.
XiongJiuqi, LiuXing. A 3D geological model of the north one mining area of Gubei coal mine based on the support vector machine[J]. Science Technology and Engineering, 2022, 22(19): 8194-8199.
[39]
YangZ, ChenQ, CuiZ, et al. Automatic reconstruction method of 3D geological models based on deep convolutional generative adversarial networks[J]. Computational Geosciences, 2022, 26(5): 1135-1150.
[40]
WangB, HuangY, ZhangD, et al. Numerical modeling of deep coalbed methane accumulation in the Central-Eastern Ordos Basin, China[J]. Natural Gas Industry B, 2024, 11(4): 405-419.
MaYongsheng, CaiXunyu, LiMaowen, et al. Research advances on the mechanisms of reservoir formation and hydrocarbon accumulation and the oil and gas development methods of deep and ultra-deep marine carbonates[J]. Petroleum Exploration and Development, 2024, 51(4): 692-707.
FengYijiang, ZhaoHongyan, ShiWenrui, et al. Research and application of key geosteering technology in Hongxing Area, Western Hubei-Eastern Chongqing[J]. Science Technology and Engineering, 2023, 23(30): 12883-12891.
[45]
AbdelmaksoudA, RadwanA A. Integrating 3D seismic interpretation, well log analysis and static modelling for characterizing the late miocene reservoir, Ngatoro Area, New Zealand[J]. Geomechanics and Geophysics for Geo-Energy and Geo-Resources, 2022, 8(2): 63.
[46]
AoY, LuW, XuP, et al. Seismic dip estimation with a domain knowledge constrained transfer learning approach[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-16.
LiuQingyou, ZhuHaiyan, ChenPengju. Research progress and direction of geology-engineering integrated drilling technology: a case study on the deep shale gas reservoirs in the Sichuan Basin[J]. Natural Gas Industry, 2021, 41(1): 178-188.
ShiYizuo, WangShejiao, XiaoHongping, et al. 3D geomodeller-based simulation of the geothermal field in the northern Songliao Basin[J]. Natural Gas Industry, 2022, 42(4): 46-53.
LiaoZhou, LiMei. Research on the 3D implicit potential field modeling method for urban underground space based on the open-source GemPy[J]. Earth Science Frontiers, 2024, 31(3): 482-497.
LiangXing, ZhuDouxing, HanBing, et al. Seismic geology engineering integration technology and its application in mountainous shale gas exploration and development[J]. Natural Gas Industry, 2022, 42(S1): 8-15.
[55]
AlaudahY, MichałowiczP, AlfarrajM, et al. A machine-learning benchmark for facies classification[J]. Interpretation, 2019, 7: 175-187.