Abstract
During the last few years, monitoring and controlling water quality in freshwater ecosystems was strongly facilitated by the increasing number of in situ stations, certainly in combination with the high number of developed models. Several water quality variables have received a great deal of attention regarding their environmental importance, while other variables have rarely been studied in detail using modeling strategies. Generally speaking, water variables were linked to building robust models and rarely are the models using fewer variables. Machine learning algorithm aiming to accurately build relationships between water quality variables are widely used and acknowledged. In the present investigation, we tried to introduce a new modeling strategy for predicting two water quality variables: water pH and specific conductance (SC) using kernel extreme learning machine models (KELM). The major contribution of our study is that we used only the river flow as relevant predictor and a single-input and single-output (SISO) model was proposed for predicting water pH and SC. Two scenarios were analyzed and compared. First, SISO models were developed and compared. Second, to greatly increase the performances of the KELM models, we have used the empirical wavelet transform (EWT) algorithm for decomposing the river flow time series into several multiresolution analysis components (MRA), which were used as new input variables. Data collected at the USG websites were used to test the proposed algorithms, and we find that the EWT clearly exhibited high accuracies compared with the SISO models, and it provides a very robust estimate of the water pH and SC. For water pH, it was found that the KELM models based on EWT were more accurate compared with the models without EWT, exhibiting R, NSE, RMSE, and MAE values ranging from 0.888 to 0.981, from 0.767 to 0.961, from 0.038 to 0.074, and from 0.027 to 0.058, respectively. In addition, for the SC, it was found that KELM models based on EWT were more accurate exhibiting R, NSE, RMSE, and MAE values ranging from 0.897 to 0.974, from 0.804 to 0.947, from 2.352 to 5.374, and from 1.528 to 4.152, respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahmadianfar I, Jamei M, Chu X (2020) A novel hybrid wavelet-locally weighted linear regression (W-LWLR) model for electrical conductivity (EC) prediction in surface water. J Contam Hydrol 232:103641. https://doi.org/10.1016/j.jconhyd.2020.103641
Babbar R, Babbar S (2017) Predicting river water quality index using data mining techniques. Environ Earth Sci 76(14):1–15. https://doi.org/10.1007/s12665-017-6845-9
Chen B, Guo R, Zeng K (2022) A nonlinear active noise control algorithm using the FEWT and channel-reduced recursive Chebyshev filter. Mech Syst Signal Process 166:108432. https://doi.org/10.1016/j.ymssp.2021.108432
Dabrowski JJ, Rahman A, Pagendam DE, George A (2020) Enforcing mean reversion in state space models for prawn pond water quality forecasting. Comput Electron Agric 168:105120. https://doi.org/10.1016/j.compag.2019.105120
Dow CL, Zampella RA (2000) Specific conductance and pH as indicators of watershed disturbance in streams of the New Jersey Pinelands, USA. Environ Manag 26(4):437–445. https://doi.org/10.1007/s002670010101
Eze E, Halse S, Ajmal T (2021) Developing a novel water quality prediction model for a South African aquaculture farm. Water 13(13):1782. https://doi.org/10.3390/w13131782
Fu Y, Hu Z, Zhao Y, Huang M (2021) A long-term water quality prediction method based on the temporal convolutional network in smart mariculture. Water 13(20):2907. https://doi.org/10.3390/w13202907
Gilles J (2013) Empirical wavelet transform. IEEE Trans Signal Process 61(16):3999–4010. https://doi.org/10.1109/TSP.2013.2265222
He J, Valeo C, Chu A, Neumann NF (2011) Prediction of event-based stormwater runoff quantity and quality by ANNs developed using PMI-based input selection. J Hydrol 400(1–2):10–23. https://doi.org/10.1016/j.jhydrol.2011.01.024
Hou Z, Lao W, Wang Y, Lu W (2021) Hybrid homotopy-PSO global searching approach with multi-kernel extreme learning machine for efficient source identification of DNAPL-polluted aquifer. Comput Geosci:104837. https://doi.org/10.1016/j.cageo.2021.104837
Huang GB, Chen L, Siew CK (2006a) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17(4):879–892. https://doi.org/10.1109/TNN.2006.875977
Huang GB, Zhu QY, Siew CK (2006b) Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501. https://doi.org/10.1016/j.neucom.2005.12.126
Huang GB, Zhou H, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern B Cybern 42(2):513–529. https://doi.org/10.1109/TSMCB.2011.2168604
Kouadri S, Pande CB, Panneerselvam B et al (2022) Prediction of irrigation groundwater quality parameters using ANN, LSTM, and MLR models. Environ Sci Pollut Res 29:21067–21091. https://doi.org/10.1007/s11356-021-17084-3
Lu H, Ma X (2020) Hybrid decision tree-based machine learning models for short-term water quality prediction. Chemosphere 249:126169. https://doi.org/10.1016/j.chemosphere.2020.126169
Lu S, Gao W, Hong C, Sun Y (2021) A newly-designed fault diagnostic method for transformers via improved empirical wavelet transform and kernel extreme learning machine. Adv Eng Inform 49:101320. https://doi.org/10.1016/j.aei.2021.101320
Moghadam SV, Sharafati A, Feizi H, Marjaie SMS, Asadollah SBHS, Motta D (2021) An efficient strategy for predicting river dissolved oxygen concentration: application of deep recurrent neural network model. Environ Monit Assess 193(12):1–18. https://doi.org/10.1007/s10661-021-09586-x
Peng L, Wang L, Xia D, Gao Q (2022) Effective energy consumption forecasting using empirical wavelet transform and long short-term memory. Energy 238:121756. https://doi.org/10.1016/j.energy.2021.121756
Piotrowski AP, Osuch M, Napiorkowski JJ (2021) Influence of the choice of stream temperature model on the projections of water temperature in rivers. J Hydrol 601:126629. https://doi.org/10.1016/j.jhydrol.2021.126629
Rizo-Decelis LD, Pardo-Igúzquiza E, Andreo B (2017) Spatial prediction of water quality variables along a main river channel, in presence of pollution hotspots. Sci Total Environ 605:276–290. https://doi.org/10.1016/j.scitotenv.2017.06.145
Rout SK, Sahani M, Dora C, Biswal PK, Biswal B (2022) An efficient epileptic seizure classification system using empirical wavelet transform and multi-fuse reduced deep convolutional neural network with digital implementation. Biomed Signal Process Control 72:103281. https://doi.org/10.1016/j.bspc.2021.103281
Sahoo GB, Ray C, De Carlo EH (2006) Use of neural network to predict flash flood and attendant water qualities of a mountainous stream on Oahu, Hawaii. J Hydrol 327(3–4):525–538. https://doi.org/10.1016/j.jhydrol.2005.11.059
Xie Z, Wu Z (2021) Maximum power point tracking algorithm of PV system based on irradiance estimation and multi-kernel extreme learning machine. Sustain Energy Technol Assess 44:101090. https://doi.org/10.1016/j.seta.2021.101090
Yang H, Liu S (2021) A prediction model of aquaculture water quality based on multiscale decomposition. Math Biosci Eng 18(6):7561–7579. https://doi.org/10.3934/mbe.2021374
Yang F, Moayedi H, Mosavi A (2021) Predicting the degree of dissolved oxygen using three types of multi-layer perceptron-based artificial neural networks. Sustainability 13(17):9898. https://doi.org/10.3390/su13179898
Yang R, Liu H, Nikitas N, Duan Z, Li Y, Li Y (2022) Short-term wind speed forecasting using deep reinforcement learning with improved multiple error correction approach. Energy 239:122128. https://doi.org/10.1016/j.energy.2021.122128
Yaseen ZM, Ehteram M, Sharafati A, Shahid S, Al-Ansari N, El-Shafie A (2018) The integration of nature-inspired algorithms with least square support vector regression models: application to modeling river dissolved oxygen concentration. Water 10(9):1124. https://doi.org/10.3390/w10091124
Yousefi A, Toffolon M (2022) Critical factors for the use of machine learning to predict lake surface water temperature. J Hydrol:127418. https://doi.org/10.1016/j.jhydrol.2021.127418
Acknowledgments
This study could not have been possible without the support of the USGS data survey. The author thanks the staffs of USGS web server for providing the data that makes this research possible.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Heddam, S. (2023). Hybrid Kernel Extreme Learning Machine-Based Empirical Wavelet Transform for Water Quality Prediction Using Only River Flow as Predictor. In: Pande, C.B., Moharir, K.N., Singh, S.K., Pham, Q.B., Elbeltagi, A. (eds) Climate Change Impacts on Natural Resources, Ecosystems and Agricultural Systems. Springer Climate. Springer, Cham. https://doi.org/10.1007/978-3-031-19059-9_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-19059-9_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19058-2
Online ISBN: 978-3-031-19059-9
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)