Multi resolution wavelet attention deep networks for real-time flood detection in the Cauveri River Basin

Abstract

The paper introduces a flood detection system that is complete and makes use of the combination of wavelet transformation and deep learning, looking at different aspects of it, especially self-window modulation in this case, in the Cauvery Basin of Southern India. The research examines 4,971 daily samples from 2000 to 2013, consisting of 500 flood and 495 drought incidents. We put forward two models, wavelet–long short–term and wavelet–gated recurrent unit of with self-window modulation, which perform better than traditional methods by a significant margin. The wavelet-long-short term model that we have developed reaches 89.44% accuracy, 82.29% precision, 78.71% recall, and 84.67% F1-score, thereby also surpassing conventional long-short-term model by 7.1% accuracy. The method entails a combination of the discrete wavelet transform using the Daubechies-4 wavelet (energy: 1.37e+08, entropy: 21.43), feature extraction that points Flow_Mean14d (importance: 0.92) as the most informative and worthy feature to be selected, and selfwindow modulation technique asserting 48.2% input from window-1 in temporal study. A comparative study reveals that the integration of wavelets has improved the performance of the model by 6-9% on self-window modulation serent metrics, while self-window modulation contribution is an extra 3-5% boost. The system is capable of detecting floods in real–time with wavelet–long short–term and wavelet–gated recurrent units attaining AUC scores of 1.000 and 0.998, respectively, and at the same time providing large language model-generated safety advisories as support for operational decision-making.

Keywords

• Cauveri Basin
• flood detection
• hydrological forecasting
• GRU
• LSTM
• self-window modulation
• wavelet transform

References

1. [1] R. R. Sahay and A. Srivastava, Predicting Monsoon Floods in Rivers Embedding Wavelet Transform, Genetic Algorithm and Neural Network, Water Resour. Manag. 28 (1), 99–115, 2014.
2. [2] A. Refice, D. Capolongo, M. Chini, L. Lacava and V. Pasquariello, Improving Flood Detection and Monitoring through Remote Sensing, Water 14 (3), 364, 2022.
3. [3] P. K. Yeditha, V. Kasi, M. Rathinasamy and S. Mohan, Forecasting of extreme flood events using different satellite precipitation products and wavelet-based machine learning methods, Chaos 30 (6), 063124, 2020.
4. [4] F. Wang and X. Feng, Flood change detection model based on an improved U-net network and multi-head attention mechanism, Sci. Rep. 15 (1), 3295, 2025.
5. [5] H. Huang, X. Lei, W. Liao, Z. Liu and Y. Zhang, A Real-Time Detecting Method for Continuous Urban Flood Scenarios Based on Computer Vision on Block Scale, Remote Sens. 15 (6), 1696, 2023.
6. [6] S. Wei, H. Yang, J. Song and X. Wang, A wavelet-neural network hybrid modelling approach for estimating and predicting river monthly flows, Hydrol. Sci. J. 58 (2), 374–389, 2013.
7. [7] W. Tan, N. Qin, Y. Zhang, H. Liu and L. Chen, A rapid high-resolution multisensory urban flood mapping framework via DEM upscaling, Remote Sens. Environ. 301, 113956, 2024.
8. [8] F. Noor, S. Haq, M. G. S. Rakib and M. A. Hossain, Water Level Forecasting Using Spatiotemporal Attention-Based Long Short-Term Memory Network, Water 14 (4), 612, 2022.

9. [9] S. W. Lo, J. H. Wu, J. Y. Chang and Y. T. Lin, Deep Sensing of Urban Waterlogging, IEEE Access 9, 126057–126071, 2021.
10. [10] J. H. Ougahi and J. S. Rowan, Enhanced streamflow forecasting using hybrid modelling integrating glacio-hydrological outputs, deep learning and wavelet transformation, Sci. Rep., 2025.
11. [11] C. Ni, P. S. Fam and M. F. Marsani, A Data-Driven Method and Hybrid Deep Learning Model for Flood Risk Prediction, Int. J. Intell. Syst. 2024 (1), 3562709, 2024.
12. [12] S. M. Heydari, T. N. M. Aris, R. Yaakob and M. A. Ismail, Data-Driven Forecasting and Modeling of Runoff Flow to Reduce Flood Risk Using a Novel Hybrid Wavelet- Neural Network Based on Feature Extraction, Sustainability 13 (20), 11537, 2021.
13. [13] W. Du, N. Chen, Y. Yang and L. Hu, Sensor web-enabled flood event process detection and instant service, Environ. Model. Softw. 117, 65–74, 2019.
14. [14] Y. H. Chen, T. A. Bui, P. J. Lee, Y. C. Lin and C. H. Chen, Spatial Reduction Attention in Multiscale Vision Transform for Surface Water-Land Interface Zone Segmentation, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 17, 10333–10342, 2024.
15. [15] S. D. Khan and S. Basalamah, Multi-Scale and Context-Aware Framework for Flood Segmentation in Post-Disaster High Resolution Aerial Images, Remote Sens. 15 (8), 2208, 2023.
16. [16] Z. Hao, N. Xiang, X. Cai, Y. Liu and H. Zhang, Remote Sensing of River Discharge From Medium-Resolution Satellite Imagery Based on Deep Learning, Water Resour. Res. 60 (9), e2023WR036880, 2024.
17. [17] G. Patidar, J. Indu and S. Karmakar, ExtendinG SUb-DAily River Discharge data over INdia (GUARDIAN), Sci. Data 11 (1), 939, 2024.
18. [18] L. Tao, Z. Cui, Y. He and Y. Wang, An explainable multiscale LSTM model with wavelet transform and layer-wise relevance propagation for daily streamflow forecasting, Sci. Total Environ. 921, 172465, 2024.
19. [19] Y. Wang, Y. Huang and M. Xiao, Medium-long-term prediction of water level based on an improved spatio-temporal attention mechanism for long short-term memory networks, J. Hydrol. 616, 129163, 2023.
20. [20] F. Ghobadi and D. K. Kang, Improving long-term streamflow prediction in a poorly gauged basin using geo-spatiotemporal mesoscale data and attention-based deep learning, J. Hydrol. 614, 128608, 2022.
21. [21] W. H. Hu, Y. Yu and J. Yan, Water Flow Prediction Based on Improved Spatiotemporal Attention Mechanism of Long Short-Term Memory Network, Water 16 (11), 1600, 2024.
22. [22] B. Yang, L. Chen and B. Yi, Local Weather and Global Climate Data-Driven Long- Term Runoff Forecasting Based on Local–Global–Temporal Attention Mechanisms and Graph Attention Networks, Remote Sens. 16 (19), 3659, 2024.
23. [23] W. Li, J. Wu and H. Chen, UNet Combined With Attention Mechanism Method for Extracting Flood Submerged Range, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 15, 5447–5458, 2022.
24. [24] S. Dong, T. Yu and H. Farahmand, Predictive multi-watershed flood monitoring using deep learning on integrated physical and social sensors data, Environ. Plan. B Urban Anal. City Sci. 49 (8), 2075–2091, 2022.
25. [25] J. J. Makwana and M. K. Tiwari, Intermittent Streamflow Forecasting and Extreme Event Modelling using Wavelet based Artificial Neural Networks, Water Resour. Manag. 28 (13), 4857–4873, 2014.
26. [26] K. Ma, D. He and S. Liu, Novel time-lag informed deep learning framework for enhanced streamflow prediction and flood early warning in large-scale catchments, J. Hydrol. 630, 130841, 2024.
27. [27] F. Hossain and D. P. Lettenmaier, Flood prediction in the future: Recognizing hydrologic issues in anticipation of the Global Precipitation Measurement mission, Water Resour. Res. 42 (11), W11501, 2006.
28. [28] F. Montello, E. Arnaudo and C. Rossi, MMFlood: A Multimodal Dataset for Flood Delineation From Satellite Imagery, IEEE Access 10, 89431–89447, 2022.
29. [29] J. Feng, L. Yan and T. Hang, Stream-flow forecasting based on dynamic spatiotemporal attention, IEEE Access 7, 135964–135976, 2019.
30. [30] M. Perumal and B. Sahoo, Limitations of real-time models for forecasting river flooding from monsoon rainfall, Nat. Hazards 41 (2), 297–313, 2007.
31. [31] K. R. Shahi, A. Camero and J. Eudaric, DC4Flood: A deep clustering framework for rapid flood detection using Sentinel-1 SAR imagery, IEEE Geosci. Remote Sens. Lett. 21, 1–5, 2024.
32. [32] X. Wu, Z. Zhang and S. Xiong, A Near-Real-Time Flood Detection Method Based on Deep Learning and SAR Images, Remote Sens. 15 (8), 2046, 2023.
33. [33] Y. F. Sang, A review on the applications of wavelet transform in hydrology time series analysis, Atmos. Res.122, 8–15, 2013.
34. [34] G. E. Karniadakis, I. G. Kevrekidis and L. Lu, Physics-informed machine learning, Nat. Rev. Phys. 3 (6), 422–440, 2021.
35. [35] A. B. Hassan, Modelling Seasonal Flood in the Downstream of Shiroro Dam, Niger State, Nigeria, PhD thesis, Ahmadu Bello Univ., Zaria, 2021.
36. [36] Z. Zhang, V. Koren and S. Reed, SAC-SMA a priori parameter differences and their impact on distributed hydrologic model simulations, J. Hydrol. 420, 216–227, 2012.
37. [37] B. Yan, R. Mu and J. Guo, Flood risk analysis of reservoirs based on full-series ARIMA model under climate change, J. Hydrol. 610, 127979, 2022.
38. [38] D. Han, L. Chan and N. Zhu, Flood forecasting using support vector machines, J. Hydroinform. 9 (4), 267–276, 2007.
39. [39] S. Ghimire, Z. M. Yaseen and A. A. Farooque, Streamflow prediction using an integrated methodology based on convolutional neural network and long short-term memory networks, Sci. Rep. 11 (1), 17497, 2021.
40. [40] K. Ren, W. Fang and J. Qu, Comparison of eight filter-based feature selection methods for monthly streamflow forecasting–three case studies on CAMELS data sets, J. Hydrol. 586, 124897, 2020.
41. [41] S. Lachure and A. Tiwari, Hydrological predictive modeling for Indian River: leveraging LSTM and GRU attention mechanisms, SN Comput. Sci. 6 (6), 749, 2025.
42. [42] A. Jović, K. Brkić and N. Bogunović, A review of feature selection methods with applications, in: 2015 38th Int. Conv. Inf. Commun. Technol. Electron. Microelectron. (MIPRO), 1200–1205, 2015.
43. [43] S. Mallat, A wavelet tour of signal processing, Elsevier, 1999.
44. [44] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit and L. Jones, Attention is all you need, Adv. Neural Inf. Process. Syst. 30, 2017.
45. [45] S. Martinis, A. Twele and S. Voigt, Towards operational near real-time flood detection using a split-based automatic thresholding procedure on high resolution TerraSAR-X data, Nat. Hazards Earth Syst. Sci. 9 (2), 303–314, 2009.
46. [46] M. J. Azur, E. A. Stuart, C. Frangakis and P. J. Leaf, Multiple imputation by chained equations: what is it and how does it work?, Int. J. Methods Psychiatr. Res. 20 (1), 40–49, 2011.
47. [47] H. H. Hsu, C. W. Hsieh and M. D. Lu, Hybrid feature selection by combining filters and wrappers, Expert Syst. Appl. 38 (7), 8144–8150, 2011.