VARIANTS OF RECURRENT NEURAL NETWORK MODELS FOR REAL-TIME FLOOD FORECASTING IN KELANI RIVER BASIN, SRI LANKA
DOI:
https://doi.org/10.17501/2513258X.2023.7105Keywords:
box-cox, data science, gated recurrent unit, long- and short- term model, statistical toolsAbstract
The rapid advancement in computer technology has supported flood forecasting, especially neural networks (NN), an application of data-driven models. However, prediction reliability is compromised due to the data manipulation strategies and the length of the predictive horizon, especially the one-month horizon, which is ample for pre-flood management. Therefore, six (06) variants of recurrent neural networks (RNN) such as Long- and Short-Term Model (LSTM), Gated Recurrent Unit (GRU), Stacked Bidirectional and Unidirectional LSTM (SBU-LSTM), SBU-GRU, Convolution Neural Network LSTM (CNN-LSTM) and CNN-GRU, were developed for the Kelani River Basin to validate their applicability in encouraging the accuracy of monthly flood forecasting by adapting a proper data manipulation technique. Initially, climatic, and physiographic factors of the basin, where the social and economic values are grievously interrupted by frequent floods, were gathered for the study. Then, the hydrological and data science cleansing strategies were adapted to enhance the quality of the data. Besides, a Box-Cox transformation was implemented to redistribute the hydrological data into a Gaussian form to remove the significant deviation between higher and lower values. Next, grid analysis was conducted using statistical tools to quantify the performance, while the influence of data handling and model architecture was examined using uncertainty and sensitivity analysis. LSTM, GRU, SBU-LSTM, SBU-GRU, CNN-LSTM, and CNN-GRU expressed nearly 81%, 81%, 83%, 83%, 76%, and 62%, respectively, for the coefficient of determination (R2) which measures how well the forecasted values fit with the actual values. SBU-LSTM and SBU-GRU interpreted similar behavior to LSTM and GRU; however, the pattern was different in CNN-LSTM and CNN-GRU. Specifically, simple variants LSTM and GRU provided satisfactory results for the uncertainty and sensitivity analysis categories.
Downloads
References
Ashok, A., Rani, H. P., & Jayakumar, K. V. (2021). Monitoring of dynamic wetland changes using NDVI and NDWI based landsat imagery. Remote Sensing Applications: Society and Environment, 23(May), 100547. https://doi.org/10.1016/j.rsase.2021.100547
Blum, L., Elgendi, M., & Menon, C. (2022). Impact of Box-Cox Transformation on Machine-Learning Algorithms. Frontiers in Artificial Intelligence, 5(April), 1–16 https://doi.org/10.3389/frai.2022.877569
Chen, C., Hui, Q., Xie, W., Wan, S., Zhou, Y., & Pei, Q. (2021). Convolutional Neural Networks for forecasting flood process in Internet-of-Things enabled smart city. Computer Networks, 186, 107744. https://doi.org/10.1016/j.comnet.2020.107744
Cui, Z., Ke, R., Pu, Z., & Wang, Y. (2020). Stacked bidirectional and unidirectional LSTM recurrent neural network for forecasting network-wide traffic state with missing values. Transportation Research Part C: Emerging Technologies, 118(March 2019), 102674. https://doi.org/10.1016/j.trc.2020.102674
de la Fuente, A., Meruane, V., & Meruane, C. (2019). Hydrological Early Warning System Based on a Deep Learning Runoff Model Coupled with a Meteorological Forecast. Water, 11(9), 1808. https://doi.org/10.3390/w11091808
Di Nunno, F., & Granata, F. (2020). Groundwater level prediction in Apulia region (Southern Italy) using NARX neural network. Environmental Research, 190(July), 1–17. https://doi.org/10.1016/j.envres.2020.110062
Géron, A. (2019). Hands-on Machine Learning with Scikit-Learn, Keras & TensorFlow (2nd Edition). O’Reilly Media. http://oreilly.com/catalog/errata.csp?isbn=9781492032649
Hassan, M., & Hassan, I. (2021). Improving Artificial Neural Network Based Streamflow Forecasting Models through Data Preprocessing. KSCE Journal of Civil Engineering, 25(9), 3583–3595. https://doi.org/10.1007/s12205-021-1859-y
Hussain, F., Wu, R.-S., & Wang, J.-X. (2021). Comparative study of very short-term flood forecasting using physics-based numerical model and data-driven prediction model. Natural Hazards, 107(1), 249–284. https://doi.org/10.1007/s11069-021-04582-3
Jain, S., Jaiswal, R. K., Lohani, A. K., & Galkate, R. (2021). Development of Cloud-Based Rainfall–Run-Off Model Using Google Earth Engine. Current Science, 121(11), 1433. https://doi.org/10.18520/cs/v121/i11/1433-1440
Jiang, F., Dong, Z., Wang, Z., Zhu, Y., Liu, M., Luo, Y., & Zhang, T. (2021). Flood forecasting using an improved NARX network based on wavelet analysis coupled with uncertainty analysis by Monte Carlo simulations: a case study of Taihu Basin, China. Journal of Water and Climate Change, 12(6), 2674–2696. https://doi.org/10.2166/wcc.2021.019
Ketkar, N., & Moolayil, J. (2021). Deep Learning with Python. In Deep Learning with Python. A press. https://doi.org/10.1007/978-1-4842-5364-9
Kottagoda, S., & Abeysingha, N. (2017). Morphometric analysis of watersheds in Kelani River basin for soil and water conservation. Journal of the National Science Foundation of Sri Lanka, 45(3), 273. https://doi.org/10.4038/jnsfsr.v45i3.8192
Manawadu, L., & Wijeratne, V. P. I. S. (2021). Anthropogenic drivers and impacts of urban flooding- A case study in Lower Kelani River Basin, Colombo Sri Lanka. International Journal of Disaster Risk Reduction, 57(January), 102076. https://doi.org/10.1016/j.ijdrr.2021.102076
Nashwan, M. S., Shahid, S., & Wang, X. (2019). Uncertainty in Estimated Trends Using Gridded Rainfall Data: A Case Study of Bangladesh. Water, 11(2), 349. https://doi.org/10.3390/w11020349
Rodrigues, G. C., & Braga, R. P. (2021). Evaluation of NASA POWER Reanalysis Products to Estimate Daily Weather Variables in a Hot Summer Mediterranean Climate. Agronomy, 11(6), 1207. https://doi.org/10.3390/agronomy11061207
Sha, J., Li, X., Zhang, M., & Wang, Z.-L. (2021). Comparison of Forecasting Models for Real-Time Monitoring of Water Quality Parameters Based on Hybrid Deep Learning Neural Networks. Water, 13(11), 1547. https://doi.org/10.3390/w13111547
Shamshirband, S., Jafari Nodoushan, E., Adolf, J. E., Abdul Manaf, A., Mosavi, A., & Chau, K. (2019). Ensemble models with uncertainty analysis for multi-day ahead forecasting of chlorophyll a concentration in coastal waters. Engineering Applications of Computational Fluid Mechanics, 13(1), 91–101. https://doi.org/10.1080/19942060.2018.1553742
Shen, H., & Lin, J. (2020). Investigation of crowd shipping delivery trip production with real-world data. Transportation Research Part E: Logistics and Transportation Review, 143(August), 102106. https://doi.org/10.1016/j.tre.2020.102106
Song, T., Ding, W., Liu, H., Wu, J., Zhou, H., & Chu, J. (2020). Uncertainty Quantification in Machine Learning Modeling for Multi-Step Time Series Forecasting: Example of Recurrent Neural Networks in Discharge Simulations. Water, 12(3), 912. https://doi.org/10.3390/w12030912
Subramanya, K. (2017). Engineering Hydrology. In African, American (Third Edit). Zed Books Ltd. https://doi.org/10.5040/9781350218178.0013
Tang, W. Y., Kassim, A. H. M., & Abubakar, S. H. (1996). Comparative studies of various missing data treatment methods - Malaysian experience. Atmospheric Research, 42(1–4), 247–262. https://doi.org/10.1016/0169-8095(95)00067-4
Vivekanandan, N. (2019). Use of Catchment Physiographic Factors in Selection of Design Storm and its Effect on Floods Estimated for Ungauged Catchments. Civil Engineering Research Journal, 9(2), 67–75. https://doi.org/10.19080/CERJ.2019.09.555759
Wan, H., Guo, S., Yin, K., Liang, X., & Lin, Y. (2020). CTS-LSTM: LSTM-based neural networks for correlated time series prediction. Knowledge-Based Systems, 191(xxxx), 105239. https://doi.org/10.1016/j.knosys.2019.105239
Xu, Y., Hu, C., Wu, Q., Li, Z., Jian, S., & Chen, Y. (2021). Application of temporal convolutional network for flood forecasting. Hydrology Research, 52(6), 1455–1468. https://doi.org/10.2166/nh.2021.021
Zhang, J., Chen, X., Khan, A., Zhang, Y., Kuang, X., Liang, X., Taccari, M. L., & Nuttall, J. (2021). Daily runoff forecasting by deep recursive neural network. Journal of Hydrology, 596(December 2020), 126067. https://doi.org/10.1016/j.jhydrol.2021.126067
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 The Proceedings of The International Conference on Climate Change
This work is licensed under a Creative Commons Attribution 4.0 International License.
