Abstract
Accurate water level forecasting is important to understand and provide an early warning of flood risk and discharge. It is also crucial for many plants and animal species that needs specific ranges of water level. This research focused on long term multi-step ahead forecasting of daily flood water level in duration of (2005–2021) at two stations (i.e., Baryulgil and Lilydale) of the Clarence River, in Australia, introducing a novel hybrid framework coupling time varying filter-based empirical mode decomposition (TVF-EMD), classification and regression trees (CART) feature selection, and four advanced machine learning (ML) models. The implemented ML approaches are including Long-Short Term Memory (LSTM), cascaded forward neural network (CFNN), gradient boosting decision tree (GBDT), and multivariate adaptive regression spline (MARS). Here, original time series of WL in each station was decomposed into the optimal intrinsic mode functions (IMFs) using the TVF-EMD technique and the significant lagged-time components for two desired horizons (t + 1 and t + 7 time ahead) in each station was extracted by using the CART-feature selection method. Then, the IMFs and corresponded residual obtained from the pre-processing procedure were separately implemented to feed the ML models and produce the CART-TVF-EMD-LSTM, CART-TVF-EMD-CFNN, CART-TVF-EMD-MARS, and CART-TVF-EMD-GBDT by assembling all the individual sub-sequences outcomes. Several goodness-of-fit metrics such as correlation coefficient (R), Mean absolute percentage error (MAPE), and Kling-Gupta efficiency (KGE) and the infographic tools and diagnostic analysis were employed to evaluate the robustness of the provided techniques. The outcomes of developed expert systems ascertained that CART-TVF-EMD-CFNN for one- and seven-day horizons in both stations outperformed the CART-TVF-EMD-MARS, CART-TVF-EMD-LSTM, CART-TVF-EMD-GBDT, and all the standalone counterpart models (i.e., CFNN, MARS, LSTM, and GBDT) respectively. As one of the most important achievements of this research, the LSTM did not lead to superior and promising results in the long-term highly nonstationary time series.
Similar content being viewed by others
Availability of Data and Materials
No data were used to support this study.
References
Abadi M (2016) TensorFlow: Learning functions at scale. Proc 21st ACM SIGPLAN Int Conf Funct Program. https://doi.org/10.1145/2951913.2976746
Abdullahi SI, Habaebi MH, Malik NA (2018) Flood disaster warning system on the go. In: 2018 7th International Conference on Computer and Communication Engineering (ICCCE). IEEE, pp 258–263
Ahmed AAM, Deo RC, Feng Q, Ghahramani A, Raj N, Yin Z, Yang L (2021) Deep learning hybrid model with Boruta-Random forest optimiser algorithm for streamflow forecasting with climate mode indices, rainfall, and periodicity. J Hydrol 599:126350
Alizamir M, Kim S, Kisi O, Zounemat-Kermani M (2020) A comparative study of several machine learning based non-linear regression methods in estimating solar radiation: Case studies of the USA and Turkey regions. Energy 117239
Alotaibi S, Amooie MA, Ahmadi MH, Nabipour N, Chau K (2020) Modeling thermal conductivity of ethylene glycol-based nanofluids using multivariate adaptive regression splines and group method of data handling artificial neural network. Eng Appl Comput Fluid Mech 14:379–390. https://doi.org/10.1080/19942060.2020.1715843
Alvisi S, Mascellani G, Franchini M, Bárdossy A (2006) Water level forecasting through fuzzy logic and artificial neural network approaches. Hydrol Earth Syst Sci. https://doi.org/10.5194/hess-10-1-2006
Anbazhagan S, Kumarappan N (2012) A neural network approach to day-ahead deregulated electricity market prices classification. Electr Power Syst Res 86:140–150. https://doi.org/10.1016/j.epsr.2011.12.011
Arnold TB (2017) kerasR: R Interface to the Keras deep learning library. J Open Source Softw 2:296
Badde DS, Gupta A, Patki VK (2009) Cascade and feed forward back propagation artificial neural network models for prediction of compressive strength of ready mix concrete. IOSR J Mech Civ Eng 1–6
Bafitlhile TM, Li Z (2019) Applicability of ε-Support Vector Machine and artificial neural network for flood forecasting in humid, semi-humid and semi-arid basins in China. Water (switzerland). https://doi.org/10.3390/w11010085
Bhattacharya B, Solomatine DP (2005) Neural networks and M5 model trees in modelling water level–discharge relationship. Neurocomputing 63:381–396. https://doi.org/10.1016/j.neucom.2004.04.016
Breiman L, Friedman JH, Olshen RA, Stone CJ (2017) Classification and regression trees. Classif Regression Trees. https://doi.org/10.1201/9781315139470
Dalagnol R, Gramcianinov CB, Crespo NM, Luiz R, Chiquetto JB, Marques MTA, Neto GD, de Abreu RC, Li S, Lott FC (2022) Extreme rainfall and its impacts in the Brazilian Minas Gerais state in January 2020: Can we blame climate change? Clim Resil Sustain 1:e15
Deo RC, Kisi O, Singh VP (2017) Drought forecasting in eastern Australia using multivariate adaptive regression spline, least square support vector machine and M5Tree model. Atmos Res. https://doi.org/10.1016/j.atmosres.2016.10.004
Deo RC, Şahin M (2016) An extreme learning machine model for the simulation of monthly mean streamflow water level in eastern Queensland. Environ Monit Assess. https://doi.org/10.1007/s10661-016-5094-9
Fan J, Yue W, Wu L, Zhang F, Cai H, Wang X, Lu X, Xiang Y (2018) Evaluation of SVM, ELM and four tree-based ensemble models for predicting daily reference evapotranspiration using limited meteorological data in different climates of China. Agric for Meteorol 263:225–241. https://doi.org/10.1016/j.agrformet.2018.08.019
Feng D, Fang K, Shen C (2020) Enhancing streamflow forecast and extracting insights using long-short term memory networks with data integration at continental scales. Water Resour Res. https://doi.org/10.1029/2019WR026793
Ferreira LB, da Cunha FF (2020) Multi-step ahead forecasting of daily reference evapotranspiration using deep learning. Comput Electron Agric 178:105728. https://doi.org/10.1016/j.compag.2020.105728
Firat M, Turan ME, Yurdusev MA (2010) Comparative analysis of neural network techniques for predicting water consumption time series. J Hydrol 384:46–51. https://doi.org/10.1016/j.jhydrol.2010.01.005
Friedman JH (2002) Stochastic gradient boosting. Comput Stat Data Anal 38:367–378
Friedman JH (1991) Multivariate adaptive regression splines. Ann Stat 19:1–67. https://doi.org/10.1214/aos/1176347963
Fu M, Le C, Fan T, Prakapovich R, Manko D, Dmytrenko O, Lande D, Shahid S, Yaseen ZM (2021) Integration of complete ensemble empirical mode decomposition with deep long short-term memory model for particulate matter concentration prediction. Environ Sci Pollut Res 1–12
Galelli S, Castelletti A (2013) Tree-based iterative input variable selection for hydrological modeling. Water Resour Res 49(7):4295–4310
Gebremariam SY, Martin JF, DeMarchi C, Bosch NS, Confesor R, Ludsin SA (2014) A comprehensive approach to evaluating watershed models for predicting river flow regimes critical to downstream ecosystem services. Environ Model Softw 61:121–134
Ghimire S, Yaseen ZM, Farooque AA, Deo RC (2021) Streamflow prediction using an integrated methodology based on convolutional neural network and long short - term memory networks. Sci Rep 1–26. https://doi.org/10.1038/s41598-021-96751-4
Ghorbani MA, Deo RC, Karimi V, Yaseen ZM, Terzi O (2017) Implementation of a hybrid MLP-FFA model for water level prediction of Lake Egirdir, Turkey. Stoch Environ Res Risk Assess 1–15. https://doi.org/10.1007/s00477-017-1474-0
Ghorbani MA, Khatibi R, Karimi V, Yaseen ZM, Zounemat-Kermani M (2018) Learning from multiple models using artificial intelligence to improve model prediction accuracies: Application to river flows. Water Resour Manag 32:4201–4215. https://doi.org/10.1007/s11269-018-2038-x
Hayder G, Solihin MI, Mustafa HM (2020) Modelling of river flow using particle swarm optimized cascade-forward neural networks: a case study of Kelantan river in Malaysia. Appl Sci 10:8670. https://doi.org/10.3390/app10238670
Hochreiter S, Schmidhuber JJ (1997) Long short-term memory. Neural Comput 9:1–32. https://doi.org/10.1162/neco.1997.9.8.1735
Jahanpanah E, Khosravinia P, Sanikhani H, Kisi O (2019) Estimation of discharge with free overfall in rectangular channel using artificial intelligence models. Flow Meas Instrum 67:118–130. https://doi.org/10.1016/j.flowmeasinst.2019.04.005
Jamei M, Karbasi M, Alawi OA, Kamar HM, Khedher KM, Abba SI, Yaseen ZM (2022a) Earth skin temperature long-term prediction using novel extended Kalman filter integrated with Artificial Intelligence models and information gain feature selection. Sustain Comput Informatics Syst 35:100721
Jamei M, Ahmadianfar I, Jamei M, Karbasi M, Heidari AA, Chen H (2022b) Estimating daily global solar radiation in hot semi-arid climate using an efficient hybrid intelligent system. Eur Phys J plus 137:1–25
Javidan N, Kavian A, Pourghasemi HR, Conoscenti C, Jafarian Z (2019) Gully erosion susceptibility mapping using multivariate adaptive regression splines-replications and sample size scenarios. Water (switzerland). https://doi.org/10.3390/w11112319
Kagoda PA, Ndiritu J, Ntuli C, Mwaka B (2010) Application of radial basis function neural networks to short-term streamflow forecasting. Phys Chem Earth 35:571–581. https://doi.org/10.1016/j.pce.2010.07.021
Kalagotla SK, Gangashetty SV, Giridhar K (2021) A novel stacking technique for prediction of diabetes. Comput Biol Med 135:1–11
Karbasi M, Karbasi M, Jamei M, Malik A, Azamathulla HM (2022) Development of a new wavelet-based hybrid model to forecast multi-scalar SPEI drought index (case study: Zanjan city, Iran). Theor Appl Climatol 147:499–522. https://doi.org/10.1007/s00704-021-03825-4
Khan MS, Coulibaly P (2006) Application of support vector machine in lake water level prediction. J Hydrol Eng. https://doi.org/10.1061/(asce)1084-0699(2006)11:3(199)
Kim HI, Kim BH (2020) Flood hazard rating prediction for urban areas using random forest and LSTM. KSCE J Civ Eng. https://doi.org/10.1007/s12205-020-0951-z
Kim S, Seo Y, Rezaie-Balf M, Kisi O, Ghorbani MA, Singh VP (2019) Evaluation of daily solar radiation flux using soft computing approaches based on different meteorological information: peninsula vs continent. Theor Appl Climatol 137:693–712. https://doi.org/10.1007/s00704-018-2627-x
Kisi O, Choubin B, Deo RC, Yaseen ZM (2019a) Incorporating synoptic-scale climate signals for streamflow modelling over the Mediterranean region using machine learning models. Hydrol Sci J
Kisi O, Khosravinia P, Nikpour MR, Sanikhani H (2019b) Hydrodynamics of river-channel confluence: toward modeling separation zone using GEP, MARS, M5 Tree and DENFIS techniques. Stoch Environ Res Risk Assess. https://doi.org/10.1007/s00477-019-01684-0
Krause P, Boyle DP, Bäse F (2005) Comparison of different efficiency criteria for hydrological model assessment. Advances Geosci 5:89–97
Li F, Wang Z, Qiu J (2019) Long-term streamflow forecasting using artificial neural network based on preprocessing technique. J Forecast 38:192–206. https://doi.org/10.1002/for.2564
Li H, Li Z, Mo W (2017a) A time varying filter approach for empirical mode decomposition. Signal Process 138:146–158. https://doi.org/10.1016/j.sigpro.2017.03.019
Li J, Burian SJ (2022) Effects of nonstationarity in urban land cover and rainfall on historical flooding intensity in a semiarid catchment. J Sustain Water Built Environ 8:4022002
Li J, Johnson F, Evans J, Sharma A (2017b) A comparison of methods to estimate future sub-daily design rainfall. Adv Water Resour. https://doi.org/10.1016/j.advwatres.2017.10.020
Li J, Stones RJ, Wang G, Li Z, Liu X, Xiao K (2016) Being accurate is not enough: New metrics for disk failure prediction. In: 2016 IEEE 35th Symposium on Reliable Distributed Systems (SRDS), pp 71–80
Li X, Xu W, Ren M, Jiang Y, Fu G (2022) Hybrid CNN-LSTM models for river flow prediction. Water Supply. https://doi.org/10.2166/ws.2022.170
Livieris IE, Pintelas E, Pintelas P (2020) A CNN–LSTM model for gold price time-series forecasting. Neural Comput Appl 32:17351–17360. https://doi.org/10.1007/s00521-020-04867-x
Lu X, Ju Y, Wu L, Fan J, Zhang F, Li Z (2018) Daily pan evaporation modeling from local and cross-station data using three tree-based machine learning models. J Hydrol. https://doi.org/10.1016/j.jhydrol.2018.09.055
Malik A, Kumar A, Kisi O, Shiri J (2019) Evaluating the performance of four different heuristic approaches with Gamma test for daily suspended sediment concentration modeling. Environ Sci Pollut Res. https://doi.org/10.1007/s11356-019-05553-9
Masrur Ahmed AA, Deo RC, Raj N, Ghahramani A, Feng Q, Yin Z, Yang L (2021) Deep learning forecasts of soil moisture: Convolutional neural network and gated recurrent unit models coupled with satellite-derived modis, observations and synoptic-scale climate index data. Remote Sens. https://doi.org/10.3390/rs13040554
Mehr AD, Kahya E, Olyaie E (2013) Streamflow prediction using linear genetic programming in comparison with a neuro-wavelet technique. J Hydrol 505:240–249. https://doi.org/10.1016/j.jhydrol.2013.10.003
Nearing GS, Kratzert F, Sampson AK, Pelissier CS, Klotz D, Frame JM, Prieto C, Gupta HV (2021) What role does hydrological science play in the age of machine learning? Water Resour Res. https://doi.org/10.1029/2020WR028091
Pal SC, Chowdhuri I, Das B, Chakrabortty R, Roy P, Saha A, Shit M (2022) Threats of climate change and land use patterns enhance the susceptibility of future floods in India. J Environ Manage 305:114317
Pappenberger F, Dutra E, Wetterhall F, Cloke HL (2012) Deriving global flood hazard maps of fluvial floods through a physical model cascade. Hydrol Earth Syst Sci 16:4143–4156
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V (2011) Scikit-learn: Machine learning in Python. J Mach Learn Res 12:2825–2830
Prasad R, Ali M, Xiang Y, Khan H (2020) A double decomposition-based modelling approach to forecast weekly solar radiation. Renew Energy. https://doi.org/10.1016/j.renene.2020.01.005
Rezaie-Balf M, Naganna SR, Kisi O, El-Shafie A (2019) Enhancing streamflow forecasting using the augmenting ensemble procedure coupled machine learning models: case study of Aswan High Dam. Hydrol Sci J. https://doi.org/10.1080/02626667.2019.1661417
Sanikhani H, Deo RC, Samui P, Kisi O, Mert C, Mirabbasi R, Gavili S, Yaseen ZM (2018) Survey of different data-intelligent modeling strategies for forecasting air temperature using geographic information as model predictors. Comput Electron Agric 152:242–260
Seng D, Zhang Q, Zhang X, Chen G, Chen X (2021) Spatiotemporal prediction of air quality based on LSTM neural network. Alexandria Eng J 60:2021–2032. https://doi.org/10.1016/j.aej.2020.12.009
Sharafati A, Yaseen ZM, Pezeshki E (2020) Strategic assessment of dam overtopping reliability using a stochastic process approach. J Hydrol Eng. https://doi.org/10.1061/(ASCE)HE.1943-5584.0001938
Sharda VN, Prasher SO, Patel RM, Ojasvi PR, Prakash C (2008) Performance of multivariate adaptive regression splines (MARS) in predicting runoff in mid-Himalayan micro-watersheds with limited data. Hydrol Sci J 53:1165–1175. https://doi.org/10.1623/hysj.53.6.1165
Shiri J, Kisi O (2010) Short-term and long-term streamflow forecasting using a wavelet and neuro-fuzzy conjunction model. J Hydrol 394:486–493. https://doi.org/10.1016/j.jhydrol.2010.10.008
Sloughter JM, Gneiting T, Raftery AE (2010) Probabilistic wind speed forecasting using ensembles and Bayesian model averaging. J Am Stat Assoc 105(489):25–35
Tao H, Al-Bedyry NK, Khedher KM, Shahid S, Yaseen ZM (2021a) River water level prediction in coastal catchment using hybridized relevance vector machine model with improved grasshopper optimization. J Hydrol 598:126477
Singh UK, Jamei M, Karbasi M, Malik A, Pandey M (2022) Application of a modern multi-level ensemble approach for the estimation of critical shear stress in cohesive sediment mixture. J Hydrol 127549
Tao H, Awadh SM, Salih SQ, Shafik SS, Yaseen ZM (2021b) Integration of extreme gradient boosting feature selection approach with machine learning models: application of weather relative humidity prediction. Neural Comput Appl. https://doi.org/10.1007/s00521-021-06362-3
Tao H, Salih S, Oudah AY, Abba SI, Ameen AMS, Awadh SM, Alawi OA, Mostafa RR, Surendran UP, Yaseen ZM (2022) Development of new computational machine learning models for longitudinal dispersion coefficient determination: Case study of natural streams, United States. Environ Sci Pollut Res. https://doi.org/10.1007/s11356-022-18554-y
Tengeleng S, Armand N (2014) Performance of using cascade forward back propagation neural networks for estimating rain parameters with rain drop size distribution. Atmosphere (basel) 5:454–472. https://doi.org/10.3390/atmos5020454
Tiwari MK, Chatterjee C (2011) A new wavelet–bootstrap–ANN hybrid model for daily discharge forecasting. J Hydroinf 13(3):500–519
Tran Q-K, Song S (2017) Water level forecasting based on deep learning: a use case of Trinity River-Texas-The United States. J KIISE 44:607–612
Wang K, Fu W, Chen T, Zhang B, Xiong D, Fang P (2020) A compound framework for wind speed forecasting based on comprehensive feature selection, quantile regression incorporated into convolutional simplified long short-term memory network and residual error correction. Energy Convers Manag 222:113234. https://doi.org/10.1016/j.enconman.2020.113234
Wang M, Rezaie-Balf M, Naganna SR, Yaseen ZM (2021) Sourcing CHIRPS precipitation data for streamflow forecasting using Intrinsic Time-scale Decomposition based Machine Learning models. Hydrol Sci J
Wang Y, Yuan Z, Liu H, Xing Z, Ji Y, Li H, Fu Q, Mo C (2022) A new scheme for probabilistic forecasting with an ensemble model based on CEEMDAN and AM-MCMC and its application in precipitation forecasting. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2021.115872
Warsito B, Santoso R, Yasin H (2018) Cascade forward neural network for time series prediction. In: Journal of Physics: Conference Series. IOP Publishing, p 12097
Wu L, Peng Y, Fan J, Wang Y (2019) Machine learning models for the estimation of monthly mean daily reference evapotranspiration based on cross-station and synthetic data. Hydrol Res. https://doi.org/10.2166/nh.2019.060
Wu Y, Zhang Q, Hu Y, Sun-Woo K, Zhang X, Zhu H, Li S et al (2022) Novel binary logistic regression model based on feature transformation of XGBoost for type 2 Diabetes Mellitus prediction in healthcare systems. Futur Gener Comput Syst 129:1–12
Xiang Z, Yan J, Demir I (2020) A rainfall-runoff model with LSTM-based sequence-to-sequence learning. Water Resour Res. https://doi.org/10.1029/2019WR025326
Xu Z, Hou Z, Han Y, Guo W (2016) A diagram for evaluating multiple aspects of model performance in simulating vector fields. Geosci Model Dev 9:4365–4380. https://doi.org/10.5194/gmd-9-4365-2016
Yaseen ZM, Awadh SM, Sharafati A, Shahid S (2018a) Complementary data-intelligence model for river flow simulation. J Hydrol 567:180–190. https://doi.org/10.1016/j.jhydrol.2018.10.020
Yaseen ZM, El-Shafie A, Afan HA, Hameed M, Mohtar WHMW, Hussain A (2015) RBFNN versus FFNN for daily river flow forecasting at Johor River. Neural Comput. Appl, Malaysia. https://doi.org/10.1007/s00521-015-1952-6
Yaseen ZM, Sulaiman SO, Deo RC, Chau K-W (2019) An enhanced extreme learning machine model for river flow forecasting: State-of-the-art, practical applications in water resource engineering area and future research direction. J Hydrol 569:387–408. https://doi.org/10.1016/j.jhydrol.2018.11.069
Yaseen ZM, Sulaiman SO, Deo RC, Chau K-W (2018b) An enhanced extreme learning machine model for river flow forecasting: state-of-the-art, practical applications in water resource engineering area and future research direction. J Hydrol 569:387–408. https://doi.org/10.1016/j.jhydrol.2018.11.069
Yin J, Deng Z, Ines AVM, Wu J, Rasu E (2020) Forecast of short-term daily reference evapotranspiration under limited meteorological variables using a hybrid bi-directional long short-term memory model (Bi-LSTM). Agric Water Manag 242:106386. https://doi.org/10.1016/j.agwat.2020.106386
Zeng J, Jamei M, Amar MN, Hasanipanah M, Bayat P (2021) A novel solution for simulating air overpressure resulting from blasting using an efficient cascaded forward neural network. Eng Comput 1–13
Zhang J, Zhu Y, Zhang X, Ye M, Yang J (2018a) Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas. J Hydrol. https://doi.org/10.1016/j.jhydrol.2018.04.065
Zhang S, Xu F, Hu M, Zhang L, Liu H, Li M (2021) A novel denoising algorithm based on TVF-EMD and its application in fault classification of rotating machinery. Measurement 179:109337. https://doi.org/10.1016/j.measurement.2021.109337
Zhang X, Liu Z, Miao Q, Wang L (2018b) An optimized time varying filtering based empirical mode decomposition method with grey wolf optimizer for machinery fault diagnosis. J Sound Vib 418:55–78. https://doi.org/10.1016/j.jsv.2017.12.028
Zhao DH, Shen HW, Tabios GQ, Lai JS, Tan WY (1994) Finite-volume two-dimensional unsteady-flow model for river basins. J Hydraul Eng. https://doi.org/10.1061/(asce)0733-9429(1994)120:7(863)
Acknowledgements
The authors are thankful to the Bureau of Meteorology, Australia and the NSW Office of Water and the NSW Department of Service Technology and Administration (Manly Hydraulics Laboratory).
Funding
Authors declare that there is no funding source available.
Author information
Authors and Affiliations
Contributions
Mehdi Jamie: Writing- Visualization, Original draft preparation, Conceptualization, Methodology, and Software. Mumtaz Ali: Original draft preparation, Writing- Reviewing and Editing, Investigation, Supervision. Anurag Malik: Writing- Reviewing and Editing. Ramendra Prasad: Writing- Reviewing and Editing. Shahab Abdulla: Reviewing and Editing. Zaher Mundher Yaseen: Supervision, writing manuscript, visualizing, validation, investigation, reviewing and editing.
Corresponding authors
Ethics declarations
Ethics Approval
Not Applicable.
Consent to Participate
Not Applicable.
Consent to Publish
All authors are aware about this submission/Publication.
Competing Interests
The authors declare that there are no conflicts of interest regarding the publication of this article.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jamei, M., Ali, M., Malik, A. et al. Forecasting Daily Flood Water Level Using Hybrid Advanced Machine Learning Based Time-Varying Filtered Empirical Mode Decomposition Approach. Water Resour Manage 36, 4637–4676 (2022). https://doi.org/10.1007/s11269-022-03270-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11269-022-03270-6