Multiscale fusion AOT-GAN intelligent filling of blank strip for formation microresistivity imaging logging

Authors

HUANG Luyi, School of Geological Engineering and Geomatics, Chang’an University, Xi’an 710064, ChinaFollow
WANG Fei, School of Geological Engineering and Geomatics, Chang’an University, Xi’an 710064, ChinaFollow
KONG Lingsong, Qinghai Branch, China National Logging Corporation, Dunhuang 736202, China
JIANG Qishu, Qinghai Branch, China National Logging Corporation, Dunhuang 736202, China

Abstract

Objective Formation microresistivity imaging (FMI) images features incomplete borehole coverage and thus contain blank strips due to the gaps between electrode pads, as well as their pushing and attachment mechanisms. Traditional blank strip filling methods suffer from several limitations, including susceptibility to image distortion and difficulty in retaining information on fine-scale structures such as fractures. This study developed an aggregated contextual-transformation generative adversarial network (AOT-GAN) for blank strip filling, aiming to achieve high-precision and high-fidelity information reconstruction. Methods Initially, a high-quality dataset was prepared based on original FMI images, along with full-borehole images obtained through image inpainting using CIFLog. Then, adaptive context awareness and multi-scale feature enhancement mechanisms were incorporated into the GAN. Finally, through dynamic optimization using four loss functions, the AOT-GAN integrating both global semantics and local details was developed. After optimal hyperparameters were selected based on image evaluation metrics, the AOT-GAN was employed to the perform blank strip filling for FMI images with varying fracture network patterns and texture characteristics. Furthermore, the filling effects were compared to those derived using three classical algorithms, i.e., GAN, Criminisi algorithm, and Bicubic interpolation. [Results and Conclusions] The AOT-GAN outperformed the three classical algorithms in both peak signal-to-noise ratio (PSNR, 32.93 dB) and structural similarity index measure (SSIM, 77.58%). This network generated natural, seamless FMI images, effectively maintaining the continuity of high-angle and reticular fractures while also accurately restoring the details of textures such as convolute beddings and flint nodules. The results of this study provide reliable data support and a theoretical basis for calculating reservoir parameters based on FMI images.

Keywords

formation microresistivity imaging (FMI) logging, image inpainting, generative adversarial network (GAN), AOT-GAN, borehole wall fracture

DOI

10.12363/issn.1001-1986.25.05.0383

Recommended Citation

HUANG Luyi, WANG Fei, KONG Lingsong, et al. (2026) "Multiscale fusion AOT-GAN intelligent filling of blank strip for formation microresistivity imaging logging," Coal Geology & Exploration: Vol. 54: Iss. 2, Article 21.
DOI: 10.12363/issn.1001-1986.25.05.0383
Available at: https://cge.researchcommons.org/journal/vol54/iss2/21

Reference

[1] XU Fanghui，WANG Zhuwen，WANG Wwenhua. Evaluation of fractured-vuggy reservoir by electrical imaging logging based on a de-noising method[J]. Acta Geophysica，2021，69(3)：1−12.

[2] 张浩，王亮，司马立强，等. 基于图像区域分割和卷积神经网络的电成像缝洞表征[J]. 石油地球物理勘探，2021，56(4)：698−706.

ZHANG Hao，WANG Liang，SIMA Liqiang，et al. Characterization of fractures and vugs by electrical imaging based on image region segmentation and convolutional neural network[J]. Oil Geophysical Prospecting，2021，56(4)：698−706.

[3] 刘瑞林，谢芳，肖承文，等. 基于小波变换图像分割技术的电成像测井资料裂缝、孔洞面孔率提取方法[J]. 地球物理学报，2017，60(12)：4945−4955.

LIU Ruilin，XIE Fang，XIAO Chengwen，et al. Extracting fracture–vug plane porosity from electrical imaging logging data using dissection of wavelet–transform–based image[J]. Chinese Journal of Geophysics，2017，60(12)：4945−4955.

[4] 齐宝权，杨小兵，张树东，等. 应用测井资料评价四川盆地南部页岩气储层[J]. 天然气工业，2011，31(4)：44−47.

QI Baoquan，YANG Xiaobing，ZHANG Shudong，et al. Logging evaluation of shale gas reservoirs in the southern Sichuan Basin[J]. Natural Gas Industry，2011，31(4)：44−47.

[5] 李宁，冯周，武宏亮，等. 中国陆相页岩油测井评价技术方法新进展[J]. 石油学报，2023，44(1)：28−44.

LI Ning，FENG Zhou，WU Hongliang，et al. New advances in methods and technologies for well logging evaluation of continental shale oil in China[J]. Acta Petrolei Sinica，2023，44(1)：28−44.

[6] WU Xingneng，SU Yuanda，ZHANG Chengsen，et al. A novel evaluation method of dolomite reservoir using electrical image logs：The Cambrian dolomites in Tarim Basin，China[J]. Geoenergy Science and Engineering，2024，233：212509.

[7] 谢芳，张承森，刘瑞林，等. 碳酸盐岩缝洞储集层电成像测井产量预测[J]. 石油勘探与开发，2018，45(2)：349−356.

XIE Fang，ZHANG Chengsen，LIU Ruilin，et al. Production prediction for fracture–vug carbonate reservoirs using electric imaging logging data[J]. Petroleum Exploration and Development，2018，45(2)：349−356.

[8] 李昌，司马立强，沈安江，等. 电成像测井储层非均质性评价方法在川东北G地区FC段地层的应用[J]. 地球物理学进展，2015，30(2)：725−732.

LI Chang，SIMA Liqiang，SHEN Anjiang，et al. The application of the reservoir heterogeneity evaluate method with micro–resistivity image log in FC formation of G region in northeastern Sichuan[J]. Progress in Geophysics，2015，30(2)：725−732.

[9] 孙建孟，赵建鹏，赖富强，等. 电测井图像空白条带填充方法[J]. 测井技术，2011，35(6)：532−537.

SUN Jianmeng，ZHAO Jianpeng，LAI Fuqiang，et al. Methods to fill in the gaps between pads of electrical logging images[J]. Well Logging Technology，2011，35(6)：532−537.

[10] 夏文鹤，韩玉娇，郭全兴，等. 融合裂缝形态信息的电阻率测井成像图空白条带填充方法[J]. 石油地球物理勘探，2024，59(3)：533−542.

XIA Wenhe，HAN Yujiao，GUO Quanxing，et al. A filling method of blank strip for electrical logging images based on morphological information of fractures[J]. Oil Geophysical Prospecting，2024，59(3)：533−542.

[11] 张翔，张猛，肖小玲，等. 复杂地层情况下全井周电成像图像修复方法[J]. 石油物探，2018，57(1)：148−153.

ZHANG Xiang，ZHANG Meng，XIAO Xiaoling，et al. Image inpainting for fullbore electrical imaging logging in complex formations[J]. Geophysical Prospecting for Petroleum，2018，57(1)：148−153.

[12] SHEN Jianhong，CHAN T F``. Mathematical models for local nontexture inpaintings[J]. SIAM Journal on Applied Mathematics，2002，62(3)：1019−1043.

[13] 罗歆，闫建平，王敏，等. FMI测井图像井壁复原方法优化及应用[J]. 测井技术，2021，45(4)：386−393.

LUO Xin，YAN Jianping，WANG Min，et al. Optimization and application of borehole wall restoration method of FMI logging image[J]. Well Logging Technology，2021，45(4)：386−393.

[14] 陈玙璠，王杨，蒋薇，等. 基于深度学习的FMI测井图像裂缝分割研究[J]. 地球物理学进展，2025，40(1)：143−154.

CHEN Yufan，WANG Yang，JIANG Wei，et al. Research on fracture segmentation of FMI logging images based on deep learning[J]. Progress in Geophysics，2025，40(1)：143−154.

[15] 王昊京，王建立，王鸣浩，等. 采用双线性插值收缩的图像修复方法[J]. 光学精密工程，2010，18(5)：1234−1241.

WANG Haojing，WANG Jianli，WANG Minghao，et al. Efficient image inpainting based on bilinear interpolation downscaling[J]. Optics and Precision Engineering，2010，18(5)：1234−1241.

[16] QUAN Weize，CHEN Jiaxi，LIU Yanli，et al. Deep learning-based image and video inpainting：A survey[J]. International Journal of Computer Vision，2024，132(7)：2367−2400.

[17] GOODFELLOW I J，POUGET–ABADIE J，MIRZA M，et al. Generative adversarial nets[C]//Proceedings of the 28^th International Conference on Neural Information Processing Systems. Montreal，2014：2672–2680.

[18] 张全，吕晓雨，雷芩，等. 基于改进pix2pix GAN的多次波压制算法[J]. 石油地球物理勘探，2024，59(4)：664−674.

ZHANG Quan，LYU Xiaoyu，LEI Qin，et al. Multiple attenuation algorithm based on improved pix2pix GAN network[J]. Oil Geophysical Prospecting，2024，59(4)：664−674.

[19] 杜春雨，邢强，张晋言，等. 基于注意力约束深度生成网络的测井电成像空白条带填充[J]. 地球物理学进展，2022，37(4)：1548−1558.

DU Chunyu，XING Qiang，ZHANG Jinyan，et al. Blank strips filling for electrical logging images based on attention–constrained deep generative network[J]. Progress in Geophysics，2022，37(4)：1548−1558.

[20] 康正明，武辰升，杨国栋，等. 生成对抗网络算法在电成像测井裂缝空白条带填充中的应用[J]. 煤田地质与勘探，2025，53(3)：197−207.

KANG Zhengming，WU Chensheng，YANG Guodong，et al. Application of a generative adversarial network algorithm to filling blank strips of fractures in formation microresistivity imaging images[J]. Coal Geology & Exploration，2025，53(3)：197−207.

[21] 王珺，杨长春，许大华，等. 微电阻率扫描成像测井方法应用及发展前景[J]. 地球物理学进展，2005，20(2)：357−364.

WANG Jun，YANG Changchun，XU Dahua，et al. Application and prospect of the formation microresistivity image well logging[J]. Progress in Geophysics，2005，20(2)：357−364.

[22] 汪进超，邹俊鹏，李生海，等. 深部开采覆岩结构面演变过程孔壁图像数字式描述方法[J]. 煤田地质与勘探，2025，53(6)：212−222.

WANG Jinchao，ZOU Junpeng，LI Shenghai，et al. The borehole wall image digital description method of the overlying rock structural planes evolution process in deep mining[J]. Coal Geology & Exploration，2025，53(6)：212−222.

[23] 屈海洲，张福祥，王振宇，等. 基于岩心–电成像测井的裂缝定量表征方法：以库车坳陷ks2区块白垩系巴什基奇克组砂岩为例[J]. 石油勘探与开发，2016，43(3)：425−432.

QU Haizhou，ZHANG Fuxiang，WANG Zhenyu，et al. Quantitative fracture evaluation method based on core–image logging：A case study of Cretaceous Bashijiqike Formation in ks2 well area，Kuqa Depression，Tarim Basin，NW China[J]. Petroleum Exploration and Development，2016，43(3)：425−432.

[24] 黄振华，程礼军，刘俊峰，等. 微电阻率成像测井在识别页岩岩相与裂缝中的应用[J]. 煤田地质与勘探，2015，43(6)：121−123.

HUANG Zhenhua，CHENG Lijun，LIU Junfeng，et al. Application of micro–resistivity image logging in identifying shale facies and fractures[J]. Coal Geology & Exploration，2015，43(6)：121−123.

[25] RADFORD A，METZ L，CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. arXiv，2015，1511：06434.

[26] MIRZA M，OSINDERO S. Conditional generative adversarial nets[J]. arXiv：1411. 1784，2014.

[27] 董新桐，钟铁，王洪洲，等. 基于卷积对抗降噪网络的塔里木盆地沙漠地震资料消噪方法研究[J]. 地球物理学报，2022，65(7)：2661−2672.

DONG Xintong，ZHONG Tie，WANG Hongzhou，et al. The denoising of desert seismic data acquired from Tarim Basin based on convolutional adversarial denoising network[J]. Chinese Journal of Geophysics，2022，65(7)：2661−2672.

[28] ZENG Yanhong，FU Jianlong，CHAO Hongyang，et al. Aggregated contextual transformations for high–resolution image inpainting[J]. IEEE Transactions on Visualization and Computer Graphics，2023，29(7)：3266−3280.

[29] CHEN L C，ZHU Yukun，PAPANDREOU G，et al. Encoder–decoder with atrous separable convolution for semantic image segmentation[C]//Computer Vision–ECCV 2018. Cham：Springer，2018：833–851.

[30] ZENG Yanhong，FU Jianlong，CHAO Hongyang，et al. Learning pyramid–context encoder network for high–quality image inpainting[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach：IEEE，2019：1486–1494.

[31] JOHNSON J，ALAHI A，LI Feifei. Perceptual losses for real–time style transfer and super–resolution[C]//Computer Vision– ECCV 2016. Cham：Springer，2016：694–711.

[32] GATYS L A，ECKER A S，BETHGE M. Image style transfer using convolutional neural networks[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas：IEEE，2016：2414–2423.

[33] 李雪瑾，李昕，徐艳杰. 基于生成对抗网络的数字图像修复技术[J]. 电子测量与仪器学报，2019，33(1)：40−46.

LI Xuejin，LI Xin，XU Yanjie. Digital image restoration technology based on generative adversarial networks[J]. Journal of Electronic Measurement and Instrumentation，2019，33(1)：40−46.

[34] LIN Guilan，FANG Sinan，LI Manxin，et al. Application of a dual-stream network collaboratively based on wavelet and spatial-channel convolution in the inpainting of blank strips in marine electrical imaging logging images：A case study in the South China Sea[J]. Journal of Marine Science and Engineering，2025，13(5)：997.