DAILY DANUBE RIVER WATER LEVEL PREDICTION USING EXTREME LEARNING MACHINE APPROACH

Miljana Milić, Novak Radivojević, Jelena Milojković, Miljan Jeremić

DOI Number
https://doi.org/10.22190/FUACR240111002M
First page
077
Last page
094

Abstract


Anticipating water levels in vast riverbeds is crucial for preventing and mitigating floods or droughts, assessing power plant capacity, and facilitating navigation management. This study introduces an innovative water level prediction model utilizing an Extreme Learning Machine developed to solve the issues of low performance of existing forecasting methods. Development of such a system is of extreme importance when talking about the largest European river – the Danube River. Experimental findings reveal the model's satisfactory performance across various accuracy metrics, complexity considerations, and calculation speed. The prediction with the highest error rate based on MAPE criteria was for Prahovo water level prediction over a 365-day period at 2.02%, whilst the most accurate predictions were for Novi Sad and Banatska Palanka over 30 days and 180 days horizons, respectively, at 0.0550%. The highest coefficient of determination (R2) was achieved with the Novi Sad data at 0.9968, whilst the lowest was observed with the Prahovo data at 0.7353. The ELM model achieved high precision by adjusting the activation functions of the hidden layer neurons, which involved using different combinations of sigmoid and radial-basis activation functions.

Keywords

Extreme learning machine, Danube river level, time series, forecasting

Full Text:

PDF

References


J. Fabryka-Martin, and J. Merz, “The Study of Water and Water Problems: A Challenge for Today and Tomorrow”, Universities Council on Water Resources, Hydrology, Carbondale, Ill., 1983.

P. Dabral, and Z. M. Mharhoni. “Modelling and forecasting of rainfall time series using SARIMA“, Envir. Processes, vol. 4, no. 2, pp. 399-419, 2017, doi.org/10.1007/s40710-017-0226-y.

O. Bazrafshan, A. Salajegheh, J. Bazrafshan, M. Mahdavi, and A. F. Maraj. “Hydrological drought forecasting using ARIMA models (case study: Karkheh Basin)“, Ecopersia vol.3, no. 3, pp. 1099-1117, 2015.

W. Handoko, and A. N. Handayani. “Forecasting Solar Irradiation on Solar Tubes Using the LSTM Method and Exponential Smoothing“, J. Ilm. Tek. Elektro Komput. dan Inform, vol. 9, no. 3, pp. 649-660, 2023, DOI: http://dx.doi.org/10.26555/jiteki.v9i3.26395.

Y. Du, J. Wang, W. F. S. Pan, T. R. Xu, and C. Wang. “Adarnn: Adaptive learning and forecasting of time series“, In Proceedings of the 30th ACM international conference on information & knowledge management, pp. 402-411. 2021.

M. Bender, and S. Simonovic. “Time-series modeling for long-range stream-flow forecasting“, Journal of Water Resources Planning and Management, vol. 120, no. 6, pp. 857-870, 1994, https://doi.org/10.1061/(ASCE)0733-9496(1994)120:6(857)

D. Noakes, A. I. McLeod, and K. Hipel. “Forecasting monthly riverflow time series“, International Journal of Forecasting, vol. 1, no. 2, pp. 179-190, 1985, https://doi.org/10.1016/0169-2070(85)90022-6.

J. Torres, D. Hadjout, A. Sebaa, F. Martínez-Álvarez, and A. Troncoso. “Deep learning for time series forecasting: a survey“, Big Data vol. 9, no. 1, pp. 3-21. 2021, doi.org/10.1089/big.2020.0159.

D. C. McKinney. “Modeling water resources management at the basin level: Review and future directions“, International Water Management Institute, (1999), ISBN: 9789290903765.

H. Maier, and G. C. Dandy. “Application of artificial neural networks to forecasting of surface water quality variables: issues, applications and challenges“, Artificial neural networks in hydrology (Book Section) - Springer, pp. 287-309, 2000, doi.org/10.1007/978-94-015-9341-0_15

R. Solgi, H. Loaiciga, and M. Kram. “Long short-term memory neural network (LSTM-NN) for aquifer level time series forecasting using in-situ piezometric observations“, Journal of Hydrology vol. 601, October 2021, 126800, doi.org/10.1016/j.jhydrol.2021.126800.

H. Han, C. Choi, J. Jung, and H. Kim. “Application of sequence to sequence learning based LSTM model (LSTM-s2s) for forecasting dam inflow“, Journal of Korea Water Resources Association vol. 54, no. 3, pp. 157-166, 2021,

K. Park, Y. Seong, Y. Jung, I. Youn, and C. K. Choi. “Development of Water Level Prediction Improvement Method Using Multivariate Time Series Data by GRU Model“, Water vol. 15, no. 3 pp. 587, 2023, doi.org/10.3390/w15030587.

K. Park, Y. Jung, Y. Seong, and S. Lee. “Development of deep learning models to improve the accuracy of water levels time series prediction through multivariate hydrological data“, Water vol.14, no. 3, pp. 469, 2022, doi.org/10.3390/w14030469.

N. Bezak et al., “A catalogue of the flood forecasting practices in the Danube River Basin”, River Research and Applications, vol. 37, no. 7, pp. 909-918, 2021, doi.org/10.1002/rra.3826.

T. Zabolotnia, L. Gorbachova, and B. Khrystiuk, “Estimation of the long-term cyclical fluctuations of snow-rain floods in the Danube basin within Ukraine”, Meteorology Hydrology and Water Management. Research and Operational Applications, vol.7, no. 2, pp. 3-11, 2019.

I. M. Santos et al., “Analysis of seasonal hindcasts for mean-term hydrological forecasting in the Upper Danube River Basin”, Geophysical Research Abstracts, vol. 21, ISSN: 1029-7006, 2019.

A. Z. Liptay, and B. Gauzer, “Operational River Ice and Water Temperature Forecasting on the Hungarian Danube Reach”, FLOOD risk 2020 - 4th European Conference on Flood Risk Management, Budapest University of Technology and Economics, http://hdl.handle.net/10890/15156, 2021.

D. Hussain et al., “A deep learning approach for hydrological time-series prediction: A case study of Gilgit river basin”, Earth Science Informatics, vol. 13, pp. 915-927, 2020, doi.org/10.1007/s12145-020-00477-2.

Z. Wang, and Y. Lou, “Hydrological time series forecast model based on wavelet de-noising and ARIMA-LSTM”, In 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), pp. 1697-1701, IEEE, March, 2019.

Z. M. Yaseen et al., “Non-tuned machine learning approach for hydrological time series forecasting”, Neural Computing and Application, vol. 30, pp. 1479-1491, 2018.

W. J. Niu et al., “Parallel computing and swarm intelligence based artificial intelligence model for multi-step-ahead hydrological time series prediction”, Sustainable Cities and Society, vol. 66, 2021, doi.org/10.1016/j.scs.2020.1026.

Z. K. Feng et al., “Evolutionary artificial intelligence model via cooperation search algorithm and extreme learning machine for multiple scales nonstationary hydrological time series prediction”, Journal of Hydrology, vol. 595, 2021, doi.org/10.1016/j.jhydrol.2021.1260.

J. Qin et al., “Simulating and Predicting of Hydrological Time Series Based on TensorFlow Deep Learning”, Polish Journal of Environmental Studies, vol. 28, no. 2, 2019, DOI: 10.1524/pjoes/81557.

M. Jeremić, M. Milić, J. Milojković, and M. Gocić, “Development of geo-da based android application for spatial and statistical analysis of Serbian long-term precipitation data”, FACTA UNIVERSITATIS Series: Automatic Control and Robotics, vol. 21, no. 3, pp. 131-145, 2021, doi.org/10.2219/FUACR220623011J.

M. D. Mijatović, Ž. Bjelajac, and I. Joksić, Overview of the ecological, economic and security capacities of the Danube River (in Serbian), Danubius, ISSN: 2217-4826, 2012.

P. Pekarova et al., “Statistical analysis of hydrological regime of the Danube River at Ceatal Izmail Station”, IOP Conference Series: Earth and Environmental Science. vol. 221, no. 1. IOP Publishing, 2019, DOI 10.1088/1755-1315/221/1/012035.

T. Pulka et al., “A Near Real-Time Hydrological Information System for the Upper Danube Basin”, Hydrology vol. 8, no. 4, 2021, doi.org/10.3390/hydrology8040144.

ICPDR. Danube Basin: Facts & Figures. International Commission for the Protection of the Danube River. Available online:

https://www.icpdr.org/flowpaper/viewer/default/files/nodes/documents/icpdr_facts_figures.pdf (accessed on 1 December 2020).

P. Pekárová et al., “Identification of long-term high-flow regime changes in selected stations along the Danube River”, Journal of Hydrology and Hydromechanics, vol. 64, no. 4, pp. 393-403, 2016, DOI: 10.1515/johh-2016-0045.

J. Wesemann, H. Holzmann, K. Schulz, and M. Herrnegger, “Behandlung künstlicher Speicher und Überleitungen in der alpinen Niederschlags-Abfluss-Vorhersage”, Osterr. Wasser Abfallwirtsch. vol.70, no. 11, pp. 485-496, 2018, DOI: 10.1007/s00506-018-0501-9.

D. Bănăduc et al., “The Danube Delta: The Achilles Heel of Danube River–Danube Delta–Black Sea Region Fish Diversity under a Black Sea Impact Scenario Due to Sea Level Rise—A Prospective Review”, Fishes, vol. 8, no. 7, 2023, doi.org/10.3390/fishes8070355.

A. M. Petrović, I. Novković, and S. Kostadinov, “Hydrological analysis of the September 2014 torrential floods of the Danube tributaries in the Eastern Serbia”, Natural Hazards, vol. 108, pp. 1373-1387, 2021.

K. P. Schneider et al., “A Distributed Power System Control Architecture for Improved Distribution System Resiliency”, IEEE Access, vol. 7, pp. 9957-9970, DOI: 10.1109/ACCESS.2019.2891, 2019.

A. Bidram, F. L. Lewis and A. Davoudi, “Distributed Control Systems for Small-Scale Power Networks: Using Multiagent Cooperative Control Theory,” IEEE Control Systems Magazine, vol. 34, no. 6, pp. 56-77, Dec. 2014, doi: 10.1109/MCS.2014.2350.

Flood recovery and prevention, Studie, https://neighbourhood-enlargement.ec.europa.eu/system/files/2016-12/ipa2014_037788.06_rs_floods_recovery_and_prevention.pdf.

G. B. Huang, Q. Y. Zhu and C. K. Siew, “Extreme Learning Machine: Theory and Applications”, Neurocomputing, vol. 70, no. 1, pp. 489-501, 2006, doi.org/10.1016/j.neucom.2005.12.126.

C. W. Deng, G. B. Huang, J. Xu, and J. X. Tang, "Extreme learning machines: new trends and applications" Science China, Information Sciences, vol. 58, no. 2, pp. 020301–020301, 2015, doi.org/10.1007/s11432-014-5269-3.

G. B. Huang, D. H. Wang, and Y. Lan, "Extreme Learning Machines: A Survey", International Journal of Machine Learning and Cybernetics, vol. 2, no. 2, pp. 107-122, 2011, doi.org/10.1007/s13042-011-0019-y.

Aranildo R. Lima, Alex J. Cannon, William W. Hsieh, "Nonlinear regression in environmental sciences using extreme learning machines: A comparative evaluation", Environmental Modelling & Software, vol. 73, pp. 175-188, 2015, doi.org/10.1016/j.envsoft.2015.08.002

S. Ding, H. Zhao, Y. Zhang, X. Xu and R, Nie, "Extrem.e learning machine: algorithm, theory and applications", Artificial Intelligence Review, vol. 44, no. 1, pp. 103–115, 2015, doi.org/10.1007/s10462-013-9405-z.

M. van Heeswijk, Y. Miche, E. Oja, A. Lendasse, "GPU-accelerated and parallelized ELM ensembles for large-scale regression", Neurocomputing, vol. 74, no. 16, pp. 2430-2437, 2011, doi.org/10.1016/j.neucom.2010.11.034.

J. C. A. Barata, M. S. Hussein, “The Moore-Penrose Pseudoinverse. A Tutorial Review of the Theory”, Brazilian Journal of Physics, vol. 42, pp. 146-165, 2011, doi.org/10.4855/arXiv.1110.6882

Annual reports for hydrological data of Danube River 1991-2021 (in Serbian), available online at: https://www.hidmet.gov.rs/ciril/hidrologija, Accessed on 10th of December 2023.

“Operational jobs in general working program of surface water hydrological stations network”, Republic Hydrometeorological Service of Serbia, available online at:

https://www.hidmet.gov.rs/latin/hidrologija/delatnost_mreza.php, Accessed on 10th of January 2024.

M. Andrejević Stošović, N. Radivojević, I. Jovanović and A.

Petrušić, “Artificial Neural Networks Application to Prediction of Electricity Consumption”. Facta Universitatis, Series: Automatic Control and Robotics, 20(1), 033-042. Doi: HTTPs://doi.org/10.2219/FUACR201231003A.

Y. Miche et al., “OP-ELM: Optimally Pruned Extreme Learning Machine”, in IEEE Transactions on Neural Networks, vol. 21, no. 1, pp. 158-162, Jan. 2010, DOI: 10.1109/TNN.2009.2036.

T. Similä and J. Tikka, “Multiresponse sparse regression with application to multidimensional scaling”, in Proc. Int. Conf. Artif. Neural Netw., pp. 97–102, 2005 DOI:10.1007/11550907_16.

Ch. S. K. Dash, A. K. Behera, S. Dehuri and S. B. Cho, (2016). “Radial basis function neural networks: A topical state-of-the-art survey”, Open Computer Science, vol. 6, no. 1, 2016, DOI 10.1515/comp-2016-0005.




DOI: https://doi.org/10.22190/FUACR240111002M

Refbacks

  • There are currently no refbacks.


Print ISSN: 1820-6417
Online ISSN: 1820-6425