Keywords
noisy time series
diffusion denoising
Abstract
Ocean buoy monitoring systems collect continuous time series from wave height, sea-surface temperature, salinity, wind speed, current velocity, dissolved oxygen, and sensor battery status. These signals are often affected by strong environmental noise, missing segments, sensor drift, storm disturbance, and communication instability. Such noise may mask abnormal marine events or cause conventional reconstruction models to generate excessive false alarms. This study proposes a diffusion-based noise separation method for robust anomaly detection in ocean buoy monitoring time series. The method first applies a conditional diffusion denoising module to recover latent clean signal trajectories from noisy observations. A disentangled representation layer is then used to separate environmental fluctuation components from sensor-fault and event-related components. Finally, anomaly scores are calculated using denoised residuals and component-level deviation boundaries. Experiments are conducted on a coastal buoy dataset containing 286 buoys, 34 monitoring variables, and 10-minute records collected over 28 months. The dataset contains 41.8 million time-stamped observations and 1,360 expert-labeled abnormal episodes, including sensor fouling, abnormal wave spikes, salinity probe drift, battery degradation, dissolved oxygen collapse, and transmission instability. The proposed method reduces median event detection delay from 5.7 hours to 1.9 hours compared with a standard denoising autoencoder. False alerts are reduced to 1.6 cases per buoy-month under storm-season noise. The signal-to-noise ratio of reconstructed trajectories increases by 7.4 dB after diffusion denoising, and the average event-boundary deviation decreases by 46 minutes. Online inference processes 18,200 buoy records per second with a median scoring latency of 39 ms per monitoring window. The results show that diffusion-driven denoising and disentangled representation learning can improve anomaly detection in noisy marine time series.
References
1. Zhang, Z. (2026). A Study on the Identification of Manipulative Design in Subscription and Payment Interfaces of Digital Consumer Platforms and Its Behavioral Effects. Available at SSRN 6734760.
2. Bhaskar TVS, U., & Reddem, V. S. (2026). Analysis and quality control of tide gauge data: Case studies on cyclone and swell surge events over the Indian ocean. Ocean Dynamics, 76(1), 3.
3. Xu, T., Zhu, W., & Zhang, J. (2026). Stability and Consistency of Explainable Deep Learning Methods in Credit Risk Assessment. Available at SSRN 6893938.
4. Rinn, P., Boruta, F., Czermak, P., & Ebrahimi, M. (2025). Fouling Control of Ion-Selective Electrodes (ISEs) in Aquatic and Aquacultural Environments: A Comprehensive Review. Sensors, 25(24), 7515.
5. Chen, X., Xiao, H., Zeng, Z., Zhang, S., & Xiao, R. (2025). Fine-Grained Multivariate Time Series Anomaly Detection via Causal Inference. Knowledge-Based Systems, 114765.
6. Yahya, M. A., Moya, A. R., & Ventura, S. (2025). Deep learning for multivariate time series anomaly detection: An evaluation of reconstruction-based methods. Artificial Intelligence Review, 58(12), 400.
7. Zhou, Y., & Jia, R. (2025). Research on Driving Behavior Risk Identification and Safety Assessment Methods Based on Artificial Intelligence. Artificial Intelligence and Machine Learning Review, 6(2), 1-15.
8. Zhang, Z., Gao, Y., & Tong, Y. (2026). Semantic-Temporal Graph Learning for Demand Forecasting and Resource Allocation in Public Information Systems. Available at SSRN 6792279.
9. Alapati, N. K. (2025, September). Enhancing Anomaly Detection in Time-Series Data Using Transformer-Based Models. In 2025 5th International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT) (pp. 1-5). IEEE.
10. Qi, C., & Qiao, X. (2026, May). From Traditional Machine Learning to Large Language Models: The Evolution of Infrastructure from an Engineering Perspective. In 2026 6th International Symposium on Computer Technology and Information Science (ISCTIS) (pp. 503-506). IEEE.
11. Su, D., & Zhang, H. Developing a Data-Driven Computational Framework for Scalable Special Education Practices for Autism and Intellectual Disabilities in the US Public School System.
12. Modi, A., Bhaskar, T. U., PG, R., Reddem, V. S., Suneeta, P., Shivaprasad, S., ... & Nair, T. B. (2026). Quality control of wave rider buoy data and its applications to cyclones and swell surges in the Indian ocean. Ocean Dynamics, 76(2), 16.
13. Ma, Y. (2026). Industrial Financial Risk Prediction Model Based on Graph Neural Network and Knowledge Graph Inference. Journal of Circuits, Systems and Computers, 35(16), 2650103.
14. Gao, G., Gao, R., Lu, C., Gao, R., & Kuang, Y. (2026, March). Security Governance Methods and Quantitative Evaluation for Enterprise SMS and Verification Code Systems. In 2026 International Conference on Generative Artificial Intelligence and Information Security (GAIIS) (pp. 455-458). IEEE.
15. Kaur, A., & Dong, G. (2023). A complete review on image denoising techniques for medical images. Neural Process. Lett., 55(6), 7807-7850.
16. Gui, H., Wang, B., Lu, Y., & Fu, Y. (2025). Computational Modeling-Based Estimation of Residual Stress and Fatigue Life of Medical Welded Structures.
17. Chen, F., Liang, H., Li, S., Yue, L., & Xu, P. (2025). Design of Domestic Chip Scheduling Architecture for Smart Grid Based on Edge Collaboration.
18. Gracic, M., Gubnisky, G., & Diamant, R. (2024). Survey of Click Detection Algorithms For Studying of Cetacean Communications.
19. Liang, R., Ye, Z., Liang, Y., & Li, S. (2025). Deep Learning-Based Player Behavior Modeling and Game Interaction System Optimization Research.
20. Wu, C., & Chen, H. (2025). Research on system service convergence architecture for AR/VR system.
21. Pathirannahalage, I., Jayasooriya, V., Samarabandu, J., & Subasinghe, A. (2025). A comprehensive analysis of real-time video anomaly detection methods for human and vehicular movement. Multimedia Tools and Applications, 84(10), 7519-7564.
22. Zamanzadeh Darban, Z., Webb, G. I., Pan, S., Aggarwal, C., & Salehi, M. (2024). Deep learning for time series anomaly detection: A survey. ACM Computing Surveys, 57(1), 1-42.
23. Yin, J., Huang, Y., & Rao, H. (2026). A Study on User Behavior Signal-Driven Predictive Models for Digital Platform Consumption Trends. Available at SSRN 6607298.
24. Yang, J. (2026). Stage‐Coupled Computational Framework for Stratified Accessibility and Equity Analysis in Community‐Based Elderly Care Services.
25. Rahman, H. (2026). Architecture-Level Fusion of SCADA and ERA5 Reanalysis Data for Enhanced Winter Fault Detection in Offshore Wind Turbines.
26. Li, Y., & Liu, S. (2026, May). A Study on Dynamic Optimization of Alerting Policies and Multi-Agent Decision-Making Mechanisms in Cloud Environments. In 2026 7th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) (pp. 703-706). IEEE.
27. Xu, T., Zhang, J., & Zhu, W. (2026). Reproducible Modeling Pipelines and Cross-Window Stability in Subprime Auto Loan Credit Risk Assessment. Available at SSRN 6893861.
28. Opari, M., & Fredette, M. (2024). Reducing the Magnitude of Measurement Error in EEG Data by Modelling the Cyclic Behavior of Electrical Brain Signal (Doctoral dissertation, HEC Montréal).
29. Lingampally, S. P., Adupa, C., & Maurya, G. K. (2026). Deep Learning–Enabled and Quantization-Aware Burst-Resilient LDPC Decoding for 6G Sensor and IoT Communication Systems: A Review. IEEE Sensors Journal.
30. Pei, Z., Huang, Q., & Wang, S. (2026). When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning. arXiv preprint arXiv:2606.29354.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright (c) 2026 Mikkel Andersen, Sofie Nielsen, Lars Petersen (Author)