A Deep Learning Approach Combining GLCM Features with ‎UNet++ and GNN for Salt Body Detection in Seismic Data

  • Authors

    • Sunkara Santhi Priya Research Scholar, Department of CSE, Shri Venkateshwara University, U.P, India
    • Dr. Deepti Sharma Professor, Department of CSE, Shri Venkateshwara University, U.P, India
    https://doi.org/10.14419/q28hjj73

    Received date: June 5, 2025

    Accepted date: July 2, 2025

    Published date: July 16, 2025

  • Salt Body Segmentation; UNet++; Graph Neural Networks (GNN); Gray-Level Co-Occurrence Matrix (GLCM); Seismic Image Analysis

  • Abstract

    Accurate detection and segmentation of salt bodies in seismic data is critical for effective subsurface interpretation and hydrocarbon exploration. Traditional methods often struggle with complex geological patterns, motivating the use of deep learning for enhanced accuracy. In this ‎study, we propose a hybrid deep learning framework that integrates Gray Level Co-occurrence Matrix (GLCM) texture features with the ‎UNet++ architecture and Graph Neural Networks (GNNs) to improve salt body detection. The model combines handcrafted texture ‎descriptors with deep hierarchical features and spatial relationships, offering a richer understanding of salt structures. The publicly available ‎TGS Salt Identification Challenge dataset is employed for training and evaluation. Preprocessing steps include denoising, contrast enhance-‎ment, and grayscale normalization, while GLCM is used to extract statistical texture patterns. These features are fused with encoder outputs ‎in UNet++ and further refined using GNN layers to exploit inter-pixel dependencies. Performance is evaluated using metrics such as Intersection over Union (IoU), Dice coefficient, Precision, Recall, and Accuracy. Experimental results demonstrate that the proposed approach ‎significantly outperforms baseline UNet and CNN models, especially in edge delineation and salt boundary preservation. This framework ‎holds promise for practical seismic interpretation workflows, particularly in complex stratigraphic environments‎.

  • References

    1. M. Mamdouh, M. Reda, M. Din, & T. Abdelhafeez, "3d petroleum reservoir modelling using seismic and well‐log data to assess hydrocarbon po-tential in abu roash (g) member, karama oil field, north‐western desert, egypt", Geological Journal, vol. 59, no. 1, p. 313-324, 2023. https://doi.org/10.1002/gj.4865.
    2. A. Alshangiti and H. Zhou, "Estimation of seismic attenuation for reservoirs mapping and inverse q‐filtering: an application on land seismic data", Geophysical Prospecting, vol. 71, no. 4, p. 682-697, 2023. https://doi.org/10.1111/1365-2478.13325.
    3. H. Zhang, T. Chen, Y. Liu, Y. Zhang, & J. Liu, "Automatic seismic facies interpretation using supervised deep learning", Geophysics, vol. 86, no. 1, p. IM15-IM33, 2021. https://doi.org/10.1190/geo2019-0425.1.
    4. N. Victor and L. Daniel, "Automated seismic interpretation: machine learning technologies are being used to develop automated seismic interpreta-tion to identify geological features, such as faults and stratigraphic horizons", International Journal of Artificial Intelligence and Machine Learning, vol. 3, no. 2, p. 74-98, 2023. https://doi.org/10.51483/IJAIML.3.2.2023.74-98.
    5. O. Orji and W. Ofuyah, "A cepstral technique for unmasking vital sub-seismic stratigraphic details embedded in dense 3d seismic data from niger delta", British Journal of Earth Sciences Research, vol. 11, no. 1, p. 1-15, 2023. https://doi.org/10.37745/bjesr.2013/vol11n1115.
    6. O. Ronneberger, P. Fischer, & T. Brox, "U-net: convolutional networks for biomedical image segmentation”, p. 234-241, 2015. https://doi.org/10.1007/978-3-319-24574-4_28.
    7. I. De, J. Souza, & J. Figueiredo, "Seismic facies identification using supervising deep learning: an application to 3d parahika seismic block (taranaki basin) “,, 2021. https://doi.org/10.22564/17cisbgf2021.308.
    8. R. Wang, H. Zhou, P. Fu, H. Shen, & Y. Bai, "A multiscale attentional unet model for automatic segmentation in medical ultrasound images", Ul-trasonic Imaging, vol. 45, no. 4, p. 159-174, 2023. https://doi.org/10.1177/01617346231169789.
    9. F. Yang and J. Ma, "Deep-learning inversion: a next-generation seismic velocity model building method", Geophysics, vol. 84, no. 4, p. R583-R599, 2019. https://doi.org/10.1190/geo2018-0249.1.
    10. J. Yao, Q. Liu, W. Liu, Y. Liu, X. Chen, & P. Mao, "3d reservoir geological modeling algorithm based on a deep feedforward neural network: a case study of the delta reservoir of upper urho formation in the x area of karamay, xinjiang, china", Energies, vol. 13, no. 24, p. 6699, 2020. https://doi.org/10.3390/en13246699.
    11. Z. Yan, Z. Zhang, & S. Liu, "Improving performance of seismic fault detection by fine-tuning the convolutional neural network pre-trained with synthetic samples", Energies, vol. 14, no. 12, p. 3650, 2021. https://doi.org/10.3390/en14123650.
    12. G. Ji and C. Wang, "A denoising method for seismic data based on svd and deep learning", Applied Sciences, vol. 12, no. 24, p. 12840, 2022. https://doi.org/10.3390/app122412840.
    13. J. Zhou, G. Cui, S. Hu, Z. Zhang, C. Yang, Z. Liuet al., "Graph neural networks: a review of methods and applications", Ai Open, vol. 1, p. 57-81, 2020. https://doi.org/10.1016/j.aiopen.2021.01.001.
    14. R. Benkert, M. Prabhushankar, & G. AlRegib, "Reliable uncertainty estimation for seismic interpretation with prediction switches",, p. 1740-1744, 2022. https://doi.org/10.1190/image2022-3745292.1.
    15. J. Wang, "A survey on graph neural networks", Icst Transactions on E-Education and E-Learning, vol. 8, no. 3, 2023. https://doi.org/10.4108/eetel.3466.
    16. V. Korolev, A. Mitrofanov, A. Korotcov, & V. Tkachenko, "Graph convolutional neural networks as “general-purpose” property predictors: the universality and limits of applicability", Journal of Chemical Information and Modeling, vol. 60, no. 1, p. 22-28, 2019. https://doi.org/10.1021/acs.jcim.9b00587.
    17. Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, & P. Yu, "A comprehensive survey on graph neural networks", Ieee Transactions on Neural Networks and Learning Systems, vol. 32, no. 1, p. 4-24, 2021. https://doi.org/10.1109/TNNLS.2020.2978386.
    18. Z. Li, N. Kovachki, K. Azizzadenesheli, B. Liu, K. Bhattacharya, A. Stuartet al., "Multipole graph neural operator for parametric partial differential equations",, 2020.
    19. Y. Cao, A. Vassantachart, J. Ye, C. Yu, D. Ruan, K. Shenget al., "Automatic detection and segmentation of multiple brain metastases on magnetic resonance image using asymmetric unet architecture", Physics in Medicine and Biology, vol. 66, no. 1, p. 015003, 2021. https://doi.org/10.1088/1361-6560/abca53.
    20. S. Gou, Y. Lu, N. Tong, L. Huang, N. Liu, & Q. Han, "Automatic segmentation and grading of ankylosing spondylitis on mr images via light-weight hybrid multi-scale convolutional neural network with reinforcement learning", Physics in Medicine and Biology, vol. 66, no. 20, p. 205002, 2021. https://doi.org/10.1088/1361-6560/ac262a.
    21. N. McConnell, A. Miron, Z. Wang, & Y. Li, "Integrating residual, dense, and inception blocks into the nnunet",, p. 217-222, 2022. https://doi.org/10.1109/CBMS55023.2022.00045.
    22. W. Zhao and Z. Zeng, "Multi scale supervised 3d u-net for kidney and tumor segmentation”, 2019. https://doi.org/10.24926/548719.007.
    23. J. Shi, X. Ding, X. Liu, Y. Li, W. Liang, & J. Wu, "Automatic clinical target volume delineation for cervical cancer in ct images using deep learn-ing", Medical Physics, vol. 48, no. 7, p. 3968-3981, 2021. https://doi.org/10.1002/mp.14898.
    24. Y. Shi, X. Wu, & S. Fomel, "Interactively tracking seismic geobodies with a deep-learning flood-filling network", Geophysics, vol. 86, no. 1, p. A1-A5, 2021. https://doi.org/10.1190/geo2020-0042.1.
    25. N. Maduna, M. Manzi, & G. Nwaila, "Comparative study of cnn-based and conventional fault interpretation methods: a study of the deep-water orange basin, south africa", Petroleum Geoscience, vol. 31, no. 1, 2025. https://doi.org/10.1144/petgeo2024-040.
    26. N. Liu, T. He, Y. Tian, B. Wu, J. Gao, & Z. Xu, "Common-azimuth seismic data fault analysis using residual unet", Interpretation, vol. 8, no. 3, p. SM25-SM37, 2020. https://doi.org/10.1190/INT-2019-0173.1.
    27. Y. Zhao, B. Chai, L. Shuo, Z. Li, H. Wu, & T. Wang, "Few-shot learning for seismic facies segmentation via prototype learning", Geophysics, vol. 88, no. 3, p. IM41-IM49, 2023. https://doi.org/10.1190/geo2022-0281.1.
    28. G. Jadhav, J. Shah, D. Vaghani, & J. Wadmare, "Automatic salt segmentation using deep learning techniques",, 2024. https://doi.org/10.21203/rs.3.rs-4360581/v1.
    29. Z. Zhao and J. Zhao, "Seismic horizon tracking based on the transunet model", Geophysics, vol. 90, no. 2, p. IM1-IM13, 2025. https://doi.org/10.1190/geo2023-0626.1.
    30. T. Yu, X. Wang, T. Chen, & C. Ding, "Fault recognition method based on attention mechanism and the 3d-unet", Computational Intelligence and Neuroscience, vol. 2022, p. 1-12, 2022. https://doi.org/10.1155/2022/9856669.
    31. Moraboena, S., Ketepalli, G., Ragam, P. (2020). A deep learning approach to network intrusion detection using deep autoencoder. Revue d'Intelli-gence Artificielle, Vol. 34, No. 4, pp. 457-463. https://doi.org/10.18280/ria.340410.
    32. M. Srikanth Yadav. and R. Kalpana., "Data Preprocessing for Intrusion Detection System Using Encoding and Normalization Approaches," 2019 11th International Conference on Advanced Computing (ICoAC), Chennai, India, 2019, pp. 265-269, https://doi.org/10.1109/ICoAC48765.2019.246851.
    33. M., Srikanth Yadav, and Kalpana R. "A Survey on Network Intrusion Detection Using Deep Generative Networks for Cyber-Physical Systems." Artificial Intelligence Paradigms for Smart Cyber-Physical Systems, edited by Ashish Kumar Luhach and Atilla Elçi, IGI Global, 2021, pp. 137-159. https://doi.org/10.4018/978-1-7998-5101-1.ch007.
    34. Srikanth yadav M., R. Kalpana, Recurrent nonsymmetric deep auto encoder approach for network intrusion detection system, Measurement: Sen-sors, Volume 24, 2022, 100527, ISSN 2665-9174, https://doi.org/10.1016/j.measen.2022.100527.
    35. Srikanth Yadav, M., Kalpana, R. (2022). Effective Dimensionality Reduction Techniques for Network Intrusion Detection System Based on Deep Learning. In: Jacob, I.J., Kolandapalayam Shanmugam, S., Bestak, R. (eds) Data Intelligence and Cognitive Informatics. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-16-6460-1_39.
    36. Gayatri, K., Premamayudu, B., Yadav, M.S. (2021). A Two-Level Hybrid Intrusion Detection Learning Method. In: Bhattacharyya, D., Thirupathi Rao, N. (eds) Machine Intelligence and Soft Computing. Advances in Intelligent Systems and Computing, vol 1280. Springer, Singapore. https://doi.org/10.1007/978-981-15-9516-5_21.
    37. Yadav, M. Srikanth, K. Sushma, and K. Gayatri. "Enhanced Network Intrusion Detection Using LSTM RNN." International Journal of Advanced Science and Technology 29.5 (2020): 7210-7220.
    38. Patil, A., and S. Yada. "Performance analysis of anomaly detection of KDD cup dataset in R environment." Int. J. Appl. Eng. Res. 13.6 (2018): 4576-4582.
    39. Saheb, M.C.P., Yadav, M.S., Babu, S., Pujari, J.J., Maddala, J.B. (2023). A Review of DDoS Evaluation Dataset: CICDDoS2019 Dataset. In: Szymanski, J.R., Chanda, C.K., Mondal, P.K., Khan, K.A. (eds) Energy Systems, Drives and Automations. ESDA 2021. Lecture Notes in Electri-cal Engineering, vol 1057. Springer, Singapore. https://doi.org/10.1007/978-981-99-3691-5_34.
    40. Patil, A., and M. Srikanth Yadav. "Performance analysis of misuse attack data using data mining classifiers." International Journal of Engineering & Technology 7.4 (2018): 261-263. https://doi.org/10.14419/ijet.v7i4.36.23782.
    41. R. Padmaja and P. R. Challagundla, "Exploring A Two-Phase Deep Learning Framework for Network Intrusion Detection," 2024 IEEE Interna-tional Students' Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, India, 2024, pp. 1-5, https://doi.org/10.1109/SCEECS61402.2024.10482198.
    42. Bhuyan, H.K., Ravi, V. & Yadav, M.S. multi-objective optimization-based privacy in data mining. Cluster Comput 25, 4275–4287 (2022). https://doi.org/10.1007/s10586-022-03667-3.
    43. D. Yaswanth, S. Sai Manoj, M. Srikanth Yadav and E. Deepak Chowdary, "Plant Leaf Disease Detection Using Transfer Learning Approach," 2024 IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, India, 2024, pp. 1-6, https://doi.org/10.1109/SCEECS61402.2024.10482053.
    44. R. G. V. L. Bharath, P. Sriram and S. Y. M, "Temporal Graph Attention Model for Enhanced Clinical Risk Prediction," 2024 IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, India, 2024, pp. 1-7, https://doi.org/10.1109/SCEECS61402.2024.10481970.
    45. B. Sushma, S. Divya Sree and M. Srikanth Yadav, "Rapid Response System Based on Graph Attention Network for Forecasting Clinical Decline In EHR," 2024 IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, India, 2024, pp. 1-6, https://doi.org/10.1109/SCEECS61402.2024.10482300.

  • Downloads

  • How to Cite

    Priya , S. S. ., & Sharma , D. D. . (2025). A Deep Learning Approach Combining GLCM Features with ‎UNet++ and GNN for Salt Body Detection in Seismic Data. International Journal of Basic and Applied Sciences, 14(3), 94-100. https://doi.org/10.14419/q28hjj73