Abstract:The artificial interpretation of seismic facies requires a lot of time and energy and is highly subjective and uncertain, which directly affects the accuracy of seismic data interpretation. Although deep learning algorithms have been widely used in seismic facies classification, due to the diversity of patterns and spatial scales of seismic facies, it remains a challenging task to improve computational efficiency while ensuring high resolution and precision. Therefore, an automatic seismic facies classification method based on LinkNet is proposed. The weighted linear combination of the multi-class cross entropy and Tversky is used as the loss function of network training. Tversky improves the description accuracy of the boundaries of minority classes of seismic facies in the unbalanced data by adjusting the parameters to balance the false positive and false negative classes and improving the recall rate and other indicators. LinkNet's decoding layer shares the learning characteristics of the encoding layer, which makes its structure simpler and greatly raises computational efficiency. The tests on the F3 block of the North Sea in the Netherlands show that the accuracy of the proposed method for describing seismic facies is higher than that of U-Net + PPM, and when faced with unbalanced data, it pays more attention to the minority classes and has better boundary characterization ability. LinkNet has fast computing speed and can run on devices with lower configurations, which is more practical than U-Net + PPM.
NIVLET P.Uncertainties in seismic facies analysis for reservoir characterisation or monitoring:causes and consequences[J].Oil & Gas Science and Technology-Rev.IFP,2007,62(2):225-235.
[2]
JOHN A K,LAKE L,TORRES-VERDIN C,et al.Seismic facies identification and classification using simple statistics[J].SPE Reservoir Evaluation & Engineering,2008,11(6):984-990.
[3]
顾元,朱培民,荣辉,等.基于贝叶斯网络的地震相分类[J].地球科学——中国地质大学学报,2013,38(5):1143-1152.GU Yuan,ZHU Peimin,RONG Hui,et al.Seismic facies classification based on Bayesian network[J].Earth Science-Journal of China University of Geoscien-ces,2013,38(5):1143-1152.
[4]
王翠华,韩德贵,李志荣.人工神经网络在地震相划分中的应用[J].南方油气地质,1995,1(4):47-51.WANG Cuihua,HAN Degui,LI Zhirong.The application of artificial neural network to the discrimination of seismic facies[J].Southern China Petroleum Geology,1995,1(4):47-51
[5]
DUBOIS M K,BOHLING G C,CHAKRABARTI S.Comparison of four approaches to a rock facies classification problem[J].Computers & Geosciences,2007,33(5):599-617
[6]
张珂,冯晓晗,郭玉荣,等.图像分类的深度卷积神经网络模型综述[J].中国图象图形学报,2021,26(10):2305-2325.ZHANG Ke,FENG Xiaohan,GUO Yurong,et al.Overview of deep convolution neural networks for image classification[J]. Journal of Image and Graphics,2021,26(10):2305-2325.
[7]
曾文献,马月,丁宇,等.基于深度学习的图像语义分割方法研究综述[J].现代计算机,2021,(21):115-122.ZENG Wenxian,MA Yue,DING Yu,et al.Survey of image semantic segmentation algorithms based on deep learning [J].Modern Computer,2021,(21):115-122.
[8]
赵立新,邢润哲,白银光,等.深度学习在目标检测的研究综述[J].科学技术与工程,2021,21(30):12787-12795.ZHAO Lixin,XING Runzhe,BAI Yinguang,et al.Review on survey of deep learning in target detection [J].Science Technology and Engineering,2021,21(30):12787-12795.
[9]
QIAN F,YIN M,LIU X Y,et al.Unsupervised seismic facies analysis via deep convolutional autoenco-ders[J].Geophysics,2018,83(3):A39-A43.
[10]
LI K,LIU Z,SHE B,et al.Orthogonal deep auto-encoders for unsupervised seismic facies analysis[C].SEG Technical Program Expanded Abstracts,2019,38:2023-2028.
[11]
WANG J,ZHENG X,HUANG H.Seismic facies analysis based on 3D-CNN and seismic stratigraphic slice[C].SEG Technical Program Expanded Abstracts,2019,38:2609-2613.
[12]
王树华,于会臻,谭绍泉,等.基于深度卷积神经网络的地震相识别技术研究[J].物探化探计算技术,2020,42(4):475-480.WANG Shuhua,YU Huizhen,TAN Shaoquan,et al.Research on seismic phase recognition technology based on deep convolution neural network[J].Computing Techniques for Geophysical and Geochemical Exploartion,2020,42(4):475-480.
[13]
李梦怡,朱定局.基于全卷积网络的图像语义分割方法综述[J].计算机系统应用,2021,30(9):41-52.LI Mengyi,ZHU Dingju.Review on image semantic segmentation based on fully convolutional network[J].Computer System & Application,2021,30(9):41-52.
[14]
张岩,周一帆,宋利伟,等.基于物理约束U-Net网络的地震数据低频延拓[J].石油地球物理勘探,2023,58(1):31-45.ZHANG Yan,ZHOU Yifan,SONG Liwei,et al.Low frequency continuation of seismic data based on physically constrained U-Net network[J].Oil Geophysical Prospecting,2023,58(1):31-45.
[15]
陈德武,杨午阳,魏新建,等.基于混合网络U-SegNet的地震初至自动拾取[J].石油地球物理勘探,2020,55(6):1188-1201.CHEN Dewu,YANG Wuyang,WEI Xinjian,et al.Automatic picking of seismic first arrivals based on hybrid network U-SegNet[J].Oil Geophysical Prospecting,2020,55(6):1188-1201.
[16]
ZHANG Y,LIU Y,ZHANG H,et al.Seismic facies analysis based on deep learning[J].IEEE Geoscience and Remote Sensing Letters,2020,17(7):1119-1123.
[17]
FENG R,BALLING N,GRANA D,et al.Bayesian convolutional neural networks for seismic facies classification[J].IEEE Transactions on Geoscience and Remote Sensing,2021,59(10):8933-8940.
[18]
MUKHOPADHYAY P,MALLICK S.Bayesian deep learning for seismic facies classification and its uncertainty estimation[C].SEG Technical Program Expanded Abstracts,2019,38:2488-2492.
[19]
闫星宇,顾汉明,罗红梅,等.基于改进深度学习方法的地震相智能识别[J].石油地球物理勘探,2020,55(6):1169-1177.YAN Xingyu,GU Hanming,LUO Hongmei,et al.Intelligent seismic facies classification based on an improved deep learning method[J].Oil Geophysical Prospecting,2020,55(6):1169-1177.
[20]
常德宽,雍学善,王一惠,等.基于深度卷积神经网络的地震数据断层识别方法[J].石油地球物理勘探,2021,56(1):1-8.CHANG Dekuan,YONG Xueshan,WANG Yihui,et al. Seismic fault interpretation based on deep convolutional neural networks[J].Oil Geophysical Prospecting,2021,56(1):1-8.
[21]
杨知,欧文浩,刘晓燕,等.基于LinkNet卷积神经网络的高分辨率遥感影像水体信息提取[J].云南大学学报(自然科学版),2019,41(5):932-938.YANG Zhi,OU Wenhao,LIU Xiaoyan,et al.Water information extraction for high resolution remote sensing image based on LinkNet convolutional neural network[J].Journal of Yunnan University (Natural Science Edition),2019,41(5):932-938.
[22]
CHAURASIA A,CULURCIELLO E.LinkNet:Exploiting encoder representations for efficient semantic segmentation[C].2017 IEEE Visual Communications and Image Processing,2017,doi:10.1109/VCIP.2017.8305148.
[23]
谢文鑫,苑金辉,胡晓飞.基于全卷积神经网络的左心室图像分割方法[J].软件导刊,2020,19(5):19-22.XIE Wenxin,YUAN Jinhui,HU Xiaofei.Left ventri-cular image segmentation method based on full convolution neural network[J].Software Guide,2020,19(5):19-22.
[24]
SALEHI S S,ERDOGMUS D,GHOLIPOUR A.Tversky loss function for image segmentation using 3D fully convolutional deep networks[C].Interna-tional Workshop on Machine Learning in Medical Ima-ging,2017,379-387.
[25]
唐杰,孟涛,韩盛元,等.基于多分辨率U-Net网络的地震数据断层检测方法[J].石油地球物理勘探,2021,56(3):436-445.TANG Jie,MENG Tao,HAN Shengyuan,et al.A fault detection method of seismic data based on MultiResU-Net[J].Oil Geophysical Prospecting,2021,56(3):436-445.
[26]
ALAUDAH Y,MICHALOWICZ P,ALFARRAJ M,et al.A machine-learning benchmark for facies classification[J].Interpretation,2019,7(3):SE175-SE187.