A Study on Anomaly Detection and Hybrid Forecasting Model Using Underground Stormwater Pipe Water Level Time-Series Data for Urban Flood Prediction
Abstract
As urban flooding risks intensify due to climate change, developing accurate and real-time predictive systems has become critical for disaster preparedness and response. This study proposes an AI-based flood prediction model that leverages real-time rainfall and inflow water level time-series data. The system consists of two core modules: an anomaly detection and auto-correction module to ensure data reliability and quality, and a deep learning-based time-series forecasting module for predicting inflow levels based on rainfall trends.
The anomaly detection module employs a reconstruction error method based on Long Short-Term Memory (LSTM) networks to identify abnormal data points that deviate from normal time-series patterns. Detected anomalies are corrected via linear interpolation, where the anomalous data points are removed and replaced with new values estimated from surrounding normal data points.
The forecasting module, built upon the LSTM architecture, captures complex rainfall-runoff relationships and temporal dynamics to provide accurate water level predictions. Additionally, hybrid models including ConvLSTM and LSTM-Transformer were designed and evaluated for comparative performance.
Experimental results demonstrated that the proposed system achieved over 95% accuracy in anomaly detection and correction. On real-world datasets, the LSTM model outperformed baseline methods, achieving a Mean Squared Error (MSE) of 0.000089, a Mean Absolute Error (MAE) of 0.006778, and a high R2 score of 0.972614. These results suggest the model's potential to enhance the reliability and efficiency of urban flood response decision-making and to contribute to the strengthening of disaster management capabilities.
References
- Bargam, B., Boudhar, A., Kinnard, C., Bouamri, H., Nifa, K., & Chehbouni, A. (2024). Evaluation of the support vector regression (SVR) and the random forest (RF) models accuracy for streamflow prediction under a data-scarce basin in Morocco. Discover Applied Sciences, 6(6), Article 306. https://doi.org/10.1007/s42452-024-05994-z
- Boateng, E. A., & Bruce, J. W. (2023). Unsupervised ensemble methods for anomaly detection in PLC-based process control. arXiv preprint arXiv:2302.02097.
- Braei, M., & Wagner, S. (2020). Anomaly detection in univariate time-series: A survey on the state-of-the-art. arXiv preprint arXiv:2004.00433. https://arxiv.org/abs/2004.00433
- Fan, Z., Zhang, J., Chen, Y., & Xu, H. (2025). Urban flood prediction model based on Transformer-LSTM Sparrow Search Algorithm. Water, 17(3), 385. https://doi.org/10.3390/w17030385
- Freeman, C., Merriman, J., Beaver, I., & Mueen, A. (2021). Experimental comparison and survey of twelve time series anomaly detection algorithms. arXiv preprint arXiv:2109.08055. https://arxiv.org/abs/2109.08055
- Oddo, P. C., Bolten, J. D., Kumar, S. V., & Cleary, B. (2024). Deep convolutional LSTM for improved flash flood prediction. Journal of Hydrology, 627, 130260. https://doi.org/10.1016/j.jhydrol.2023.130260
- Taylor, S. J., & Letham, B. (2017). Forecasting at scale. The American Statistician, 72(1), 37-45. https://doi.org/10.1080/00031305.2017.1380080
- Shahanas, S., Akthar, A., Anand, S., Rakshitha, & Amirthavalli, M. (2024). Anomaly detection in time series data in IoT environment. International Journal of Innovative Research in Technology, 11(5).
- Widiasari, I. R., & Efendi, R. (2024). Utilizing LSTM-GRU for IoT-based water level prediction using multi-variable rainfall time series data. Informatics, 11(4), 73. https://doi.org/10.3390/informatics11040073
Keywords
Details
| Section | Articles |
| Issue | Vol. 2 No. 1 (2025): Volume 2 Issue 1 (November 2025) |
| Published | 2025-11-28 |
| Pages | 2-16 |
- Graduated from Seoul School of Integrated Sciencs & Technologies(aSSIST), Graduate School of AI, Department of AI Advanced Studies, Major in AI Big Data(Master of Engineering)
- Research Interests : AI, Time Series Data Forecasting,
- Digital Transformation, Generative, Data Analysis.
- Research Professor,The Institute for Industrial Policy Studies Visting Professor, Seoul School of Integrated Sciences & Technologies(aSSIST)
- Head of Process Management Team, Mirae Asset Securities
- Ph.D. in Business Administration , aSSIST University
- Research Interests : AI, Finance, Time Series, Business Strategy
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.