Cross-Layer Seismic Data Gap Detection Using Bi-GRU Autoencoder and Hybrid CNN-BiGRU
DOI:
https://doi.org/10.32492/jeetech.v7i2.7204Keywords:
seismic, cross-layer, Bi-GRU, autoencoder, hybrid CNN-BiGRUAbstract
Continuous seismic waveform transmission is essential to the Indonesia Tsunami Early Warning System (InaTEWS), yet transmission gaps may originate from either communication-network degradation or disruption in the SeedLink application stream. This study develops an unsupervised cross-layer anomaly-detection framework for the TEBBI seismic site and compares a Bidirectional Gated Recurrent Unit (BiGRU) autoencoder with a Hybrid CNN-BiGRU model. Integrated Layer-3 PRTG and Layer-7 SeedLink logs from October 2025 to March 2026 produced 262,080 one-minute records with six operational features. Domain-aware missing-value treatment, fixed-range normalization, 30-minute sliding windows, chronological 80:10:10 partitioning, and one-class training on normal windows were applied. Validation reconstruction errors were converted into model-specific F1-max thresholds. The hybrid model achieved MAE 0.016637, RMSE 0.051577, F1-score 0.8737, and AUC-ROC 0.9595, compared with 0.016806, 0.051810, 0.8728, and 0.9590 for BiGRU. Cross-layer diagnosis separated normal operation, Layer-3 failure, Layer-7 blind spots, and systemic disruption; Layer-7 or systemic states represented 10.27% and 10.08% of test windows for the hybrid and BiGRU models, respectively. Inter-model diagnostic agreement reached 97.70%. The principal contribution is source-oriented, site-specific diagnosis that supports more targeted seismic-transmission troubleshooting at TEBBI
Downloads
References
R. S. Yuliatmoko et al., "Distribusi frekuensi gempa dan dimensi fraktal pada seismik gap di Indonesia," Jurnal Meteorologi dan Geofisika, vol. 22, no. 2, pp. 55-66, 2021, doi: 10.31172/jmg.v22i2.771.
W. Kurniawan et al., "Analisis sistem peringatan dini tsunami di zona megathrust Selat Sunda guna mewujudkan ketahanan nasional," PENDIPA Journal of Science Education, 2022.
L. N. Rachmawati, M. E. A. Octaviana, and Agussalim, "Monitoring jaringan menggunakan PRTG: Studi kasus FEB UPN Veteran Jawa Timur," Jurnal Ilmiah Teknologi Informasi dan Robotika, vol. 6, no. 1, pp. 44-53, 2024, doi: 10.33005/jifti.v6i1.149.
G. Airlangga, "Unsupervised machine learning for seismic anomaly detection: Isolation Forest algorithm application to Indonesian earthquake data," Jurnal Lebesgue, vol. 4, no. 3, pp. 1827-1836, 2023, doi: 10.46306/lb.v4i3.479.
G. Airlangga, "Advanced machine learning techniques for seismic anomaly detection in Indonesia: A comparative study of LOF, Isolation Forest, and One-Class SVM," Jurnal Lebesgue, vol. 5, no. 1, pp. 49-61, 2024, doi: 10.46306/lb.v5i1.490.
G. Pang et al., "Deep learning for anomaly detection: A review," ACM Computing Surveys, vol. 54, no. 2, Art. no. 38, 2021, doi: 10.1145/3439950.
R. Chalapathy and S. Chawla, "Deep learning for anomaly detection: A survey," arXiv:1901.03407, 2019, doi: 10.48550/arXiv.1901.03407.
K. Cho et al., "Learning phrase representations using RNN encoder-decoder for statistical machine translation," in Proc. EMNLP, 2014, pp. 1724-1734, doi: 10.3115/v1/D14-1179.
J. Chung et al., "Empirical evaluation of gated recurrent neural networks on sequence modeling," arXiv:1412.3555, 2014, doi: 10.48550/arXiv.1412.3555.
S. Kiranyaz et al., "1D convolutional neural networks and applications: A survey," Mechanical Systems and Signal Processing, vol. 151, Art. no. 107398, 2021, doi: 10.1016/j.ymssp.2020.107398.
K. Yang, J. Wang, and M. Li, "An improved intrusion detection method for IIoT using attention mechanisms, BiGRU, and Inception-CNN," Scientific Reports, vol. 14, Art. no. 19339, 2024, doi: 10.1038/s41598-024-70094-2.
T. Schlegl et al., "f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks," Medical Image Analysis, vol. 54, pp. 30-44, 2019, doi: 10.1016/j.media.2019.01.010.
J. Audibert et al., "USAD: Unsupervised anomaly detection on multivariate time series," in Proc. 26th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2020, pp. 3395-3404, doi: 10.1145/3394486.3403392.
Y. Su et al., "Robust anomaly detection for multivariate time series through stochastic recurrent neural network," in Proc. 25th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2019, pp. 2828-2837, doi: 10.1145/3292500.3330672.
H. Ren et al., "Time-series anomaly detection service at Microsoft," in Proc. 25th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2019, pp. 3009-3017, doi: 10.1145/3292500.3330680.
M. R. A. Prasetya, A. M. Priyatno, and Nurhaeni, "Penanganan imputasi missing values pada data time series dengan menggunakan metode data mining," Jurnal Informasi dan Teknologi, vol. 5, no. 2, pp. 52-62, 2023, doi: 10.37034/jidt.v5i2.324.
P. Laksana, A. F. Isnawati, and A. R. Noermartyas, "Comparative analysis of QoS VSAT IP and VSAT Star Telkomsat," Jurnal Nasional Teknik Elektro, vol. 13, no. 3, pp. 113-119, 2024, doi: 10.25077/jnte.v13n3.1258.2024.
H. A. Nugroho, S. Hasanah, and M. Yusuf, "Seismic data quality analysis based on image recognition using convolutional neural network," JUITA: Jurnal Informatika, vol. 10, no. 1, pp. 67-75, 2022.
T. O. Hodson, "Root mean square error (RMSE) or mean absolute error (MAE): When to use them or not," Geoscientific Model Development, vol. 15, pp. 5481-5487, 2022, doi: 10.5194/gmd-15-5481-2022.
V. Plevris, G. Solorzano, N. P. Bakas, and M. E. A. Ben Seghier, "Investigation of performance metrics in regression analysis and machine learning-based prediction models," in Proc. ECCOMAS Congress, Oslo, Norway, 2022, doi: 10.23967/eccomas.2022.155.
Published
How to Cite
Issue
Section
Copyright (c) 2026 Aziz Setiawan, Ahmad Musyafa, Makhsun, Ceppy Multi Anggara
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
