Comparison of Random Forest, SVR and KNN Based Models in Sea Level Prediction for Erdemli Coast of Mersin

Abstract

Seawater level prediction is very important in terms of future planning of human living conditions, flood prevention and coastal construction. Nevertheless, it is hard to correctly predict the daily future of sea water level because of the atmospheric conditions and effects. Therefore, Random Forest (RF), Support Vector Regression (SVR) and K-Nearest Neighbor (KNN) methods were used for the prediction of seawater level on Erdemli coast of Mersin in this study. In this paper, root mean square error (RMSE) and coefficient of determination (R2) were applied as model evaluation criteria. In addition, 15-minute sea water level data of Erdemli Station for approximately 18 months were obtained and used as is. The results depict that Random Forest model can predict the seawater level for 1st and 2nd days with R2 of 0.80, 0.63, respectively, KNN model can predict for 1st and 2nd days with R2 of 0.80, 0.64, respectively, and SVR model can predict for 1st and 2nd days with R2 of 0.77, 0.60, respectively.

Keywords

• Random Forest
• SVR
• KNN
• sea level prediction
• Mersin Erdemli coast
• Mediterranean

References

1. [1]. Woodworth, PL, Hunter, JR, Marcos, M, Hughes, CW. 2021. Towards reliable global allowances for sea level rise. Global and Planetary Change; 203: 103522.
2. [2]. Yesudian, AN, Dawson, RJ. 2021. Global analysis of sea level rise risk to airports. Climate Risk Management; 31: 100266.
3. [3]. Jin, H, Zhong, R, Liu, M, Ye, C, Chen, X. 2023. Using EEMD mode decomposition in combination with machine learning models to improve the accuracy of monthly sea level predictions in the coastal area of China. Dynamics of Atmospheres and Oceans; 102: 101370.
4. [4]. Primo de Siqueira, BV, Paiva, A de M. 2021. Using neural network to improve sea level prediction along the southeastern Brazilian coast. Ocean Model; 168: 101898.
5. [5]. Zhao, J, Cai, R, Sun, W. 2021. Regional sea level changes prediction integrated with singular spectrum analysis and long-short-term memory network. Advances in Space Research; 68: 4534–4543.
6. [6]. Bernstein, A, Gustafson, MT, Lewis, R. 2019. Disaster on the horizon: The price effect of sea level rise. Journal of Financial Economics; 134: 253–272.
7. [7]. Meilianda, E, Pradhan, B, Comfort, LK, Alfian, D, Juanda, R, Syahreza, S, Munadi, K. 2019. Assessment of post-tsunami disaster land use/land cover change and potential impact of future sea-level rise to low-lying coastal areas: A case study of Banda Aceh coast of Indonesia. International Journal of Disaster Risk Reduction; 41: 101292.
8. [8]. Zakaria, MNA, Ahmed, AN, Malek, MA, Birima, AH, Khan, M MH, Sherif, M, Elshafie, A. 2023. Exploring machine learning algorithms for accurate water level forecasting in Muda river, Malaysia. Heliyon; 9(7).

9. [9]. Ishida, K, Tsujimoto, G, Ercan, A, Tu, T, Kiyama, M, Amagasaki, M. 2020. Hourly-scale coastal sea level modeling in a changing climate using long short-term memory neural network. Science of the Total Environment; 720: 137613.
10. [10]. Accarino, G, Chiarelli, M, Fiore, S, Federico, I, Causio, S, Coppini, G, Aloisio, G. 2021. A multi-model architecture based on Long Short-Term Memory neural networks for multi-step sea level forecasting. Future Generation Computer Systems; 124: 1–9.
11. [11]. Imani M, You RJ, Kuo CY. 2014. Forecasting Caspian Sea level changes using satellite altimetry data (June 1992–December 2013) based on evolutionary support vector regression algorithms and gene expression programming. Glob Planet Change; 121:53–63.
12. [12]. Kisi O, Shiri J, Karimi S, Shamshirband S, Motamedi S, Petkovi´c D, Hashim R. 2015. A survey of water level fluctuation prediction in Urmia Lake using Support Vector Machine with firefly algorithm. Appl Math Comput; 270:731–743.
13. [13]. Paul, GC, Senthilkumar, S, Pria, R. 2018. An efficient approach to forecast water levelsowing to the interaction of tide and surge associated with a storm along the coast of Bangladesh. Ocean Engineering; 148; 516–529.
14. [14]. Khaledian, MR, Isazadeh, M, Biazar, SM, & Pham, QB. 2020. Simulating Caspian Sea surface water level by artificial neural network and support vector machine models. Acta Geophysica; 68: 553-563.
15. [15]. Altunkaynak A, Kartal E. 2021. Transfer sea level learning in the Bosphorus Strait by wavelet based machine learning methods. Ocean Engineering; 233: 109116
16. [16]. Karsavran, Y, Erdik, T. 2021. Artificial Intelligence Based Prediction of Seawater Level: A Case Study for Bosphorus Strait. International Journal of Mathematical, Engineering and Management Sciences; 6(5): 1242.
17. [17]. Balogun, AL, Adebisi, N. 2021. Sea level prediction using ARIMA, SVR and LSTM neural network: assessing the impact of ensemble Ocean-Atmospheric processes on models’ accuracy. Geomatics, Natural Hazards and Risk; 12(1): 653-674.
18. [18]. Alshouny, A, Elnabwy, MT, Kaloop, MR, Baik, A, Miky, Y. 2022. An integrated framework for improving sea level variation prediction based on the integration Wavelet-Artificial Intelligence approaches. Environmental Modelling & Software; 152: 105399.
19. [19]. Guyennon, N, Salerno, F, Rossi, D, Rainaldi, M, Calizza, E, Romano, E. 2021. Climate change and water abstraction impacts on the long-term variability of water levels in Lake Bracciano (Central Italy): A Random Forest approach. Journal of Hydrology: Regional Studies; 37: 100880.
20. [20]. Karsavran, Y. 2024. Comparison of ANN and SVR based models in sea level prediction for the Black Sea coast of Sinop. Turkish Journal of Maritime and Marine Sciences; 1-8.
21. [21]. Liaw, A, Wiener, M. 2002. Classification and regression by random Forest. R news; 2 (3): 18–22.
22. [22]. Loh, WY. 2011. Classification and regression trees. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery; 1 (1): 14–23.
23. [23]. Başakın, EE, Ekmekcioğlu, Ö, Özger, M. 2023. Developing a novel approach for missing data imputation of solar radiation: A hybrid differential evolution algorithm based eXtreme gradient boosting model. Energy Conversion and Management; 280: 116780.
24. [24]. Patil, SG, Mandal, S, Hegde, AV. 2012. Genetic algorithm based support vector machine regression in predicting wave transmission of horizontally interlaced multilayer moored floating pipe breakwater. Advances in Engineering Software; 45: 203–212.
25. [25]. Lin, GQ, Li, LL, Tseng, ML, Liu, HM, Yuan, DD, Tan, RR. 2020. An improved moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation. Journal of Cleaner Production; 253: 119966.
26. [26]. Li, G, Liu, F, Yang, H. 2022. Research on feature extraction method of ship radiated noise with K-nearest neighbor mutual information variational mode decomposition, neural network estimation time entropy and self-organizing map neural network. Measurement; 199: 111446.
27. [27]. Mehr AD, Kahya E, Olyaie E. 2013. Streamflow prediction using linear genetic programming in comparison with a neuro-wavelet technique. J Hydrology; 505: 240–249.
28. [28]. Karsavran, Y, Erdik, T, & Ozger, M. 2023. An improved technique for streamflow forecasting between Turkish straits. Acta Geophysica; 1-12.
29. [29]. Wang, WC, Chau, KW, Cheng, CT, Qiu, L. 2009. A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series. Journal of Hydrology; 374(3-4): 294-306.