Boosting Medium-Size Reservoir Water Level Predictions using Cyclical Encoding
Received: 16 February 2025 | Revised: 24 March 2025, 7 April 2025, and 10 April 2025 | Accepted: 12 April 2025 | Online: 4 June 2025
Corresponding author: Wiroj Thasana
Abstract
Effective feature engineering is crucial for machine learning models to capture complex data patterns. This study explores cyclical encoding, a novel technique designed to enhance the performance of machine learning algorithms on datasets with inherent periodicity. This study addresses the challenge faced by medium-sized reservoirs that lack modern data collection equipment by applying cyclical encoding to improve predictive models. Using medium-sized reservoir data, cyclical encoding was applied to enhance the predictive capabilities of models including Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting Regressor (GBR), Linear Regression (LR), and Artificial Neural Networks (ANN). The results show that cyclical encoding significantly enhances the ability of nonlinear models to capture cyclical patterns, reducing error metrics by up to 75%. However, LR showed minimal improvement due to its inherent linear limitations. Feature importance analysis identified cumulative outflow and inflow volumes as key predictors. These findings highlight the vital role of advanced feature-engineering techniques such as cyclical encoding in boosting the accuracy and robustness of nonlinear machine learning models, especially for medium-sized reservoirs without modern equipment. This study underscores its potential for broader applications in domains with periodic data, such as climate modeling and financial time series.
Keywords:
feature engineering, cyclical encoding, water level prediction, medium-sized reservoir, hydrologyDownloads
References
C. Carvalho-Santos, A. T. Monteiro, J. C. Azevedo, J. P. Honrado, and J. P. Nunes, "Climate Change Impacts on Water Resources and Reservoir Management: Uncertainty and Adaptation for a Mountain Catchment in Northeast Portugal," Water Resources Management, vol. 31, no. 11, pp. 3355–3370, Sep. 2017. DOI: https://doi.org/10.1007/s11269-017-1672-z
S. M. Vicente-Serrano et al., "Global drought trends and future projections," Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, vol. 380, no. 2238, Oct. 2022, Art. no. 20210285. DOI: https://doi.org/10.1098/rsta.2021.0285
V. Lai, Y. F. Huang, C. H. Koo, A. N. Ahmed, and A. El-Shafie, "A Review of Reservoir Operation Optimisations: from Traditional Models to Metaheuristic Algorithms," Archives of Computational Methods in Engineering, vol. 29, no. 5, pp. 3435–3457, Aug. 2022. DOI: https://doi.org/10.1007/s11831-021-09701-8
M. Acreman, "Managed flood releases from reservoirs," presented at the EGS - AGU - EUG Joint Assembly, Apr. 2003, Art. no. 9487.
R. Obringer and R. Nateghi, "Predicting Urban Reservoir Levels Using Statistical Learning Techniques," Scientific Reports, vol. 8, no. 1, Mar. 2018, Art. no. 5164. DOI: https://doi.org/10.1038/s41598-018-23509-w
W. J. Wee, N. B. Zaini, A. N. Ahmed, and A. El-Shafie, "A review of models for water level forecasting based on machine learning," Earth Science Informatics, vol. 14, no. 4, pp. 1707–1728, Dec. 2021. DOI: https://doi.org/10.1007/s12145-021-00664-9
J. Payen, J. M. Faurès, and D. Vallée, "Small reservoirs and water storage for smallholder farming--the case for a new approach," Gates Open Research, vol. 3, no. 387, Feb. 2019, Art. no. 387.
J. E. Nash and J. V. Sutcliffe, "River flow forecasting through conceptual models part I — A discussion of principles," Journal of Hydrology, vol. 10, no. 3, pp. 282–290, Apr. 1970. DOI: https://doi.org/10.1016/0022-1694(70)90255-6
H. R. Maier and G. C. Dandy, "Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications," Environmental Modelling & Software, vol. 15, no. 1, pp. 101–124, Jan. 2000. DOI: https://doi.org/10.1016/S1364-8152(99)00007-9
C. W. Dawson and R. L. Wilby, "Hydrological modelling using artificial neural networks," Progress in Physical Geography, vol. 25, no. 1, pp. 80–108, Mar. 2001. DOI: https://doi.org/10.1191/030913301674775671
M. S. Khan and P. Coulibaly, "Application of Support Vector Machine in Lake Water Level Prediction," Journal of Hydrologic Engineering, vol. 11, no. 3, pp. 199–205, May 2006. DOI: https://doi.org/10.1061/(ASCE)1084-0699(2006)11:3(199)
D. P. Solomatine and A. Ostfeld, "Data-driven modelling: some past experiences and new approaches," Journal of Hydroinformatics, vol. 10, no. 1, pp. 3–22, Jan. 2008. DOI: https://doi.org/10.2166/hydro.2008.015
I. S. Msiza, F. V. Nelwamondo, and T. Marwala, "Water Demand Prediction using Artificial Neural Networks and Support Vector Regression," Journal of Computers, vol. 3, no. 11, Nov. 2008. DOI: https://doi.org/10.4304/jcp.3.11.1-8
H. Liao and W. Sun, "Forecasting and Evaluating Water Quality of Chao Lake based on an Improved Decision Tree Method," Procedia Environmental Sciences, vol. 2, pp. 970–979, Jan. 2010. DOI: https://doi.org/10.1016/j.proenv.2010.10.109
O. Kisi, J. Shiri, and B. Nikoofar, "Forecasting daily lake levels using artificial intelligence approaches," Computers & Geosciences, vol. 41, pp. 169–180, Apr. 2012. DOI: https://doi.org/10.1016/j.cageo.2011.08.027
N. Seckin, M. Cobaner, R. Yurtal, and T. Haktanir, "Comparison of Artificial Neural Network Methods with L-moments for Estimating Flood Flow at Ungauged Sites: the Case of East Mediterranean River Basin, Turkey," Water Resources Management, vol. 27, no. 7, pp. 2103–2124, May 2013. DOI: https://doi.org/10.1007/s11269-013-0278-3
C. C. Nwobi-Okoye and A. C. Igboanugo, "Predicting Water Levels at Kainji Dam Using Artificial Neural Networks," Nigerian Journal of Technology, vol. 32, no. 1, pp. 129–136, Apr. 2013.
N. Valizadeh and A. El-Shafie, "Forecasting the Level of Reservoirs Using Multiple Input Fuzzification in ANFIS," Water Resources Management, vol. 27, no. 9, pp. 3319–3331, Jul. 2013. DOI: https://doi.org/10.1007/s11269-013-0349-5
A. Altunkaynak, "Predicting Water Level Fluctuations in Lake Michigan-Huron Using Wavelet-Expert System Methods," Water Resources Management, vol. 28, no. 8, pp. 2293–2314, Jun. 2014. DOI: https://doi.org/10.1007/s11269-014-0616-0
X. Xu et al., "A real-time probabilistic channel flood-forecasting model based on the Bayesian particle filter approach," Environmental Modelling & Software, vol. 88, pp. 151–167, Feb. 2017. DOI: https://doi.org/10.1016/j.envsoft.2016.11.010
A. Ogilvie et al., "Combining Landsat observations with hydrological modelling for improved surface water monitoring of small lakes," Journal of Hydrology, vol. 566, pp. 109–121, Nov. 2018. DOI: https://doi.org/10.1016/j.jhydrol.2018.08.076
J. Li et al., "Intelligent identification of effective reservoirs based on the random forest classification model," Journal of Hydrology, vol. 591, Dec. 2020, Art. no. 125324. DOI: https://doi.org/10.1016/j.jhydrol.2020.125324
Y. O. Ouma et al., "Dam Water Level Prediction Using Vector AutoRegression, Random Forest Regression and MLP-ANN Models Based on Land-Use and Climate Factors," Sustainability, vol. 14, no. 22, Jan. 2022, Art. no. 14934. DOI: https://doi.org/10.3390/su142214934
J. Zhang, Y. Zhu, X. Zhang, M. Ye, and J. Yang, "Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas," Journal of Hydrology, vol. 561, pp. 918–929, Jun. 2018. DOI: https://doi.org/10.1016/j.jhydrol.2018.04.065
F. Unes, M. Demirci, B. Tasar, Y. Z. Kaya, and H. Varcin, "Estimating dam reservoir level fluctuations using data-driven techniques," Polish Journal of Environmental Studies, vol. 28, no. 5, 2019. DOI: https://doi.org/10.15244/pjoes/93923
V. Kaushik and N. Awasthi, "Simulation of reservoir outflows using regression tree and support vector machine," AI in Civil Engineering, vol. 2, no. 1, Apr. 2023, Art. no. 2. DOI: https://doi.org/10.1007/s43503-023-00012-4
M. Cho, C. Kim, K. Jung, and H. Jung, "Water Level Prediction Model Applying a Long Short-Term Memory (LSTM)–Gated Recurrent Unit (GRU) Method for Flood Prediction," Water, vol. 14, no. 14, Jan. 2022, Art. no. 2221. DOI: https://doi.org/10.3390/w14142221
L. Liu, C. Mou, and F. Xu, "Improved Wildlife Recognition through Fusing Camera Trap Images and Temporal Metadata," Diversity, vol. 16, no. 3, Mar. 2024, Art. no. 139. DOI: https://doi.org/10.3390/d16030139
J. Chen and Z. Yang, "Revolutionizing Time Series Data Preprocessing with a Novel Cycling Layer in Self-Attention Mechanisms," Applied Sciences, vol. 14, no. 19, Jan. 2024, Art. no. 8922. DOI: https://doi.org/10.3390/app14198922
R. El Moghrabi, R. Tian, L. Liboni, and M. Capretz, "Data Preprocessing for Machine Learning Modules," in Undergraduate Student Research Internships Conference, Aug. 2022.
T. Mahajan, G. Singh, and G. Bruns, "An Experimental Assessment of Treatments for Cyclical Data," presented at the Computer Science Conference for CSU Undergraduates, 2021.
A. H. Blasi, M. A. Abbadi, and R. Al-Huweimel, "Machine Learning Approach for an Automatic Irrigation System in Southern Jordan Valley," Engineering, Technology & Applied Science Research, vol. 11, no. 1, pp. 6609–6613, Feb. 2021. DOI: https://doi.org/10.48084/etasr.3944
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.
K. P. Murphy, Machine Learning: A Probabilistic Perspective. MIT Press, 2012.
Downloads
How to Cite
License
Copyright (c) 2025 Sakchan Luangmaneerote, Wiroj Thasana
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
