EFFECT OF SEASONAL-TREND DECOMPOSITION ON MACHINE LEARNING-BASED SUSPENDED SEDIMENT LOAD PREDICTION PERFORMANCE

Cihangir Köyceğiz; Meral Büyükyıldız

doi:10.17780/ksujes.1502136

EN TR

EFFECT OF SEASONAL-TREND DECOMPOSITION ON MACHINE LEARNING-BASED SUSPENDED SEDIMENT LOAD PREDICTION PERFORMANCE

Abstract

Forecasting of sediment is vital for water resources management. In this study, the machine learning-based prediction performance of suspended sediment load (SSL) at Bulakbaşı station of Kızılırmak River was investigated. Also, the effect of seasonal decomposition on the prediction performance was searched. Accordingly, Support Vector Machine (SVM), Adaptive Boosting (AdaBoost), and Generalized Regression Neural Network (GRNN) methods were used for SSL prediction. Grid Search (GS) algorithm was preferred for hyperparameter optimization. The seasonal component was obtained by Seasonal-Trend decomposition using the LOESS (STL) method. Six input combinations were generated using flow (Qt), flow lag (Qt-1), and the seasonal component of SSL (S-SSLt). According to the findings, AdaBoost (M6-NSETrain=0.914, M4-NSETest=0.765), SVM (M6-NSETrain=0.912, M6-NSETest=0.863), and GRNN (M6-NSETrain=0.912, M4-NSETest=0.834) models produced quite consistent results. In the test phase, SVM-M6 (R2=0.893, NSE=0.863) is the most successful model according to various evaluation metrics. It was also observed that the last three input combinations, where the seasonal component of SSL was added, generally improved the performance. For SVM in the test phase, which is the most successful model, R2=0.873, NSE=0.820 values were obtained in the combination without the seasonal component (M3), and R2=0.893, NSE=0.863 values were obtained in the combination with the seasonal component (M6)

Keywords

MEVSİMSEL-TREND AYRIŞTIRMASININ MAKİNE ÖĞRENMESİ TABANLI ASKIDA SEDİMENT YÜKÜ TAHMİN PERFORMANSI ÜZERİNDEKİ ETKİSİ

Öz

Sedimentin tahmin edilmesi, su kaynakları yönetimi için hayati önem taşımaktadır. Bu çalışmada, Kızılırmak Nehri'nin Bulakbaşı istasyonundaki askıda sediment yükünün (SSL) makine öğrenmesi tabanlı tahmin performansı araştırılmıştır. Ayrıca mevsimsel ayrıştırmanın tahmin performansı üzerindeki etkisi incelenmiştir. Bu doğrultuda, Destek Vektör Makinesi (SVM), Adaptif Boosting (AdaBoost) ve Genelleştirilmiş Regresyon Sinir Ağı (GRNN) algoritmaları SSL tahmini için kullanılmıştır. Hiperparametre optimizasyonu için Grid Search (GS) algoritması tercih edilmiştir. Mevsimsel bileşen, Mevsimsel-Trend ayrıştırması LOESS (STL) yöntemi kullanılarak elde edilmiştir. Akış (Qt), akış gecikmesi (Qt-1) ve SSL'nin mevsimsel bileşeni (S-SSLt) kullanılarak altı girdi kombinasyonu oluşturulmuştur. Bulgulara göre AdaBoost (M6-NSEEğitim=0,914, M4-NSETest=0,765), SVM (M6-NSEEğitim=0,912, M6-NSETest=0,863) ve GRNN (M6-NSEEğitim=0,912, M4-NSETest=0,834) modelleri oldukça tutarlı sonuçlar üretmiştir. Test aşamasında, SVM-M6 (R2=0,893, NSE=0,863) çeşitli değerlendirme ölçütlerine göre en başarılı modeldir. SSL'nin mevsimsel bileşeninin eklendiği son üç girdi kombinasyonunun genel olarak performansı artırdığı da gözlemlenmiştir. En başarılı model olan test aşamasındaki SVM için mevsimsel bileşenin olmadığı kombinasyonda (M3) R2=0,873, NSE=0,820 ve mevsimsel bileşenin olduğu kombinasyonda (M6) R2=0,893, NSE=0,863 değerleri elde edilmiştir.

Anahtar Kelimeler

Thanks

The authors would like to thank the General Directorate of State Hydraulic Works for the data used in this study

References

Acar, A. A. (2019). Kızılırmak havzasında yapay zekâ metotları kullanarak sediment taşınımının tahmini. Yüksek Lisans Tezi. Konya Teknik Üniversitesi Lisansüstü Eğitim Enstitüsü İnşaat Mühendisliği Anabilim Dalı, Konya 89s.
Acar, R., & Saplıoğlu, K. (2022). Etkili girdi parametrelerinin çoklu regresyon ile belirlendiği su sertliğinin anfis yöntemi ile tahmin edilmesi. Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi, 22(6), 1413-1424. https://doi.org/10.35414/akufemubid.1147492
Adnan, R. M., Liang, Z., El-Shafie, A., Zounemat-Kermani, M., & Kisi, O. (2019). Prediction of Suspended Sediment Load Using Data-Driven Models. Water, 11(10), 2060. https://doi.org/10.3390/w11102060
Aghelpour, P., Graf, R., & Tomaszewski, E. (2023). Coupling ANFIS with ant colony optimization (ACO) algorithm for 1-, 2-, and 3-days ahead forecasting of daily streamflow, a case study in Poland. Environmental Science and Pollution Research, 30(19), 56440-56463. https://doi.org/10.1007/s11356-023-26239-3
AlDahoul, N., Essam, Y., Kumar, P., Ahmed, A. N., Sherif, M., Sefelnasr, A., & Elshafie, A. (2021). Suspended sediment load prediction using long short-term memory neural network. Scientific Reports, 11(1), 7826. https://doi.org/10.1038/s41598-021-87415-4
Asadi, M., Fathzadeh, A., Kerry, R., Ebrahimi-Khusfi, Z., & Taghizadeh-Mehrjardi, R. (2021). Prediction of river suspended sediment load using machine learning models and geo-morphometric parameters. Arabian Journal of Geosciences, 14(18), 1–14. https://doi.org/10.1007/s12517-021-07922-6
Buyukyildiz, M., & Kumcu, S. Y. (2017). An Estimation of the Suspended Sediment Load Using Adaptive Network Based Fuzzy Inference System, Support Vector Machine and Artificial Neural Network Models. Water Resources Management, 31(4), 1343–1359. https://doi.org/10.1007/s11269-017-1581-1
Cai, Q. C., Hsu, T. H., & Lin, J. Y. (2021). Using the General Regression Neural Network Method to Calibrate the Parameters of a Sub-Catchment. Water, 13(8), 1089. https://doi.org/10.3390/w13081089

Cigizoglu, H. K. (2005). Application of Generalized Regression Neural Networks to Intermittent Flow Forecasting and Estimation. Journal of Hydrologic Engineering, 10(4), 336–341. https://doi.org/10.1061/(ASCE)1084-0699(2005)10:4(336
Cleveland, R., Cleveland, W., McRae, J., & Terpenning, I. (1990). STL: A seasonal-trend decomposition procedure based on Loess. Journal of Official Statistics, 6(1), 3–73.
Cleveland, W. S. (1979). Robust locally weighted regression and smoothing scatterplots. Journal of the American Statistical Association, 74(368), 829–836. https://doi.org/10.1080/01621459.1979.10481038
Cleveland, W. S., & Devlin, S. J. (1988). Locally weighted regression: An approach to regression analysis by local fitting. Journal of the American Statistical Association, 83(403), 596–610. https://doi.org/10.1080/01621459.1988.10478639
Fang, K., Kifer, D., Lawson, K., Feng, D., & Shen, C. (2022). The data synergy effects of time‐series deep learning models in hydrology. Water Resources Research, 58(4), e2021WR029583. https://doi.org/10.1029/2021WR029583
Freund, Y., & Schapire, R. E. (1995). A desicion-theoretic generalization of on-line learning and an application to boosting. In European Conference on Computational Learning Theory (Vol. 904, pp. 23–37). Springer, Berlin, Heidelberg.
Freund, Y., & Schapire, R. E. (1996). Experiments with a New Boosting Algorithm. In icml. 96, 148-156.
Freund, Y., & Schapire, R. E. (1997). A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. Journal of Computer and System Sciences, 55(1), 119–139. https://doi.org/10.1006/jcss.1997.1504
Ghasempour, R., Roushangar, K., & Sihag, P. (2021). Suspended sediment load prediction in consecutive stations of river based on ensemble pre-post-processing kernel based approaches. Water Supply, 21(7), 3370–3386. https://doi.org/10.2166/ws.2021.094
Gupta, D., Hazarika, B. B., Berlin, M., Sharma, U. M., & Mishra, K. (2021). Artificial intelligence for suspended sediment load prediction: a review. Environmental Earth Sciences, 80(9), 1–39. https://doi.org/10.1007/s12665-021-09625-3
Hamida, S., Gannour, O. E, Cherradi, B., Ouajji, H., & Raihani, A. (2020). Optimization of Machine Learning Algorithms Hyper-Parameters for Improving the Prediction of Patients Infected with COVID-19. IEEE 2nd International Conference on Electronics, Control, Optimization and Computer Science (ICECOCS), Kenitra, Morocco, 1-6.
Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition. Springer New York, NY.
Himanshu, S. K., Pandey, A., & Yadav, B. (2017). Assessing the applicability of TMPA-3B42V7 precipitation dataset in wavelet-support vector machine approach for suspended sediment load prediction. Journal of Hydrology, 550, 103-117. https://doi.org/10.1016/j.jhydrol.2017.04.051
Hodson, T. O. (2022). Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not. Geoscientific Model Development, 15(14), 5481–5487. https://doi.org/10.5194/gmd-15-5481-2022
Holtschlag, D. J. (2001). Optimal estimation of suspended‐sediment concentrations in streams. Hydrological processes, 15(7), 1133-1155. https://doi.org/10.1002/hyp.207
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2021). An Introduction to Statistical Learning. Springer.
Katipoğlu, O. M., Kartal, V., & Pande, C. B. (2024). Sediment load forecasting from a biomimetic optimization perspective: Firefly and Artificial Bee Colony algorithms empowered neural network modeling in Çoruh River. Stochastic Environmental Research and Risk Assessment, 38, 3907–3927. https://doi.org/10.1007/s00477-024-02785-1
Kilinc, H. C., & Yurtsever, A. (2022). Short-term streamflow forecasting using hybrid deep learning model based on grey wolf algorithm for hydrological time series. Sustainability, 14(6), 3352. https://doi.org/10.3390/su14063352
Kisi, O., Haktanir, T., Ardiclioglu, M., Ozturk, O., Yalcin, E., & Uludag, S. (2009). Adaptive neuro-fuzzy computing technique for suspended sediment estimation. Advances in Engineering Software, 40(6), 438–444. https://doi.org/10.1016/j.advengsoft.2008.06.004
Kisi, O., & Yaseen, Z. M. (2019). The potential of hybrid evolutionary fuzzy intelligence model for suspended sediment concentration prediction. Catena, 174, 11-23. https://doi.org/10.1016/j.catena.2018.10.047
Koycegiz, C., & Buyukyildiz, M. (2019). Calibration of SWAT and two data-driven models for a data-scarce mountainous headwater in Semi-Arid Konya Closed Basin. Water, 11(1), 147. https://doi.org/10.3390/w11010147
Koycegiz, C., Buyukyildiz, M., & Kumcu, S. Y. (2021). Spatio-temporal analysis of sediment yield with a physically based model for a data-scarce headwater in Konya Closed Basin, Turkey. Water Supply, 21 (4): 1752–1763. https://doi.org/10.2166/ws.2021.016
Lafare, A. E. A., Peach, D. W., & Hughes, A. G. (2016). Use of seasonal trend decomposition to understand groundwater behaviour in the Permo-Triassic Sandstone aquifer, Eden Valley, UK. Hydrogeology Journal, 24(1), 141–158. https://doi.org/10.1007/s10040-015-1309-3
Merritt, W. S., Letcher, R. A., & Jakeman, A. J. (2003). A review of erosion and sediment transport models. Environmental modelling & software, 18(8-9), 761-799. https://doi.org/10.1016/S1364-8152(03)00078-1
Miao, J., Zhang, X., Zhang, G., Wei, T., Zhao, Y., Ma, W., Chen, Y., Li, Y., & Wang, Y. (2024). Applications and interpretations of different machine learning models in runoff and sediment discharge simulations. Catena, 238, 107848. https://doi.org/10.1016/j.catena.2024.107848
Misra, D., Oommen, T., Agarwal, A., Mishra, S. K., & Thompson, A. M. (2009). Application and analysis of support vector machine based simulation for runoff and sediment yield. Biosystems Engineering, 103(4), 527–535. https://doi.org/10.1016/j.biosystemseng.2009.04.017
Mohammadi, B., Guan, Y., Moazenzadeh, R., & Safari, M. J. S. (2021). Implementation of hybrid particle swarm optimization-differential evolution algorithms coupled with multi-layer perceptron for suspended sediment load estimation. Catena, 198, 105024. https://doi.org/10.1016/j.catena.2020.105024
Moriasi D. N., Arnold J. G., Van Liew M. W., Bingner R. L., Harmel R. D. & Veith T. L. (2007). Model evaluation guidelines for systematic quantification of accuracy in watershed simulations, Transactions of the ASABE, 50 (3), 885–900. https://doi: 10.13031/2013.23153
Naghizadeh, A., Amiri-Ramsheh, B., Atashrouz, S., Abuswer, M. A., Abedi, A., Mohaddespour, A., & Hemmati-Sarapardeh, A. (2024). Modeling thermal conductivity of hydrogen-based binary gaseous mixtures using generalized regression neural network. International Journal of Hydrogen Energy, 59, 242-250. https://doi.org/10.1016/j.ijhydene.2024.01.216
Nash, J. E., & Sutcliffe, J. V. (1970). River flow forecasting through conceptual models part I — A discussion of principles. Journal of Hydrology, 10(3), 282–290. https://doi.org/10.1016/0022-1694(70)90255-6
Noori, N., Kalin, L., 2016. Coupling SWAT and ANN models for enhanced daily streamflow prediction. Journal of Hydrology, 533, 141-151. https://doi.org/10.1016/j.jhydrol.2015.11.050
Nourani, V., Molajou, A., Tajbakhsh, A. D., & Najafi, H. (2019). A wavelet based data mining technique for suspended sediment load modeling. Water Resources Management, 33, 1769-1784. https://doi.org/10.1007/s11269-019-02216-9
NumPy. (2008). https://numpy.org/doc/2.1/ Accessed 15.04.2024.
Onüçyıldız, M., Bostancı, İ., & Yarar, A. (2014). Konya Altınapa Baraj Gölündeki Sedimantasyon Kaynaklı Kapasite Kaybının Coğrafi Bilgi Sistemleri Kullanılarak Hesaplanması. Selçuk Üniversitesi Sosyal ve Teknik Araştırmalar Dergisi, (7), 12-26.
Özger, M., & Kabataş, M. B. (2015). Sediment load prediction by combined fuzzy logic-wavelet method. Journal of Hydroinformatics, 17(6), 930–942. https://doi.org/10.2166/hydro.2015.148
Pandas. (2024). https://pandas.pydata.org/docs/ Accessed 21.04.2024.
Pandey, A., Himanshu, S. K., Mishra, S. K., & Singh, V. P. (2016). Physically based soil erosion and sediment yield models revisited. Catena, 147, 595-620. https://doi.org/10.1016/j.catena.2016.08.002
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M. & Duchesnay, E. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825-2830.
Piraei, R., Afzali, S. H., & Niazkar, M. (2023). Assessment of XGBoost to Estimate Total Sediment Loads in Rivers. Water Resources Management, 37(13), 5289–5306. https://doi.org/10.1007/s11269-023-03606-w
Samantaray, S., & Sahoo, A. (2022). Prediction of suspended sediment concentration using hybrid SVM-WOA approaches. Geocarto International, 37(19), 5609–5635. https://doi.org/10.1080/10106049.2021.1920638
Samantaray, S., Sahoo, A., & Ghose, D. K. (2020). Assessment of Sediment Load Concentration Using SVM, SVM-FFA and PSR-SVM-FFA in Arid Watershed, India: A Case Study. KSCE Journal of Civil Engineering, 24(6), 1944–1957. https://doi.org/10.1007/s12205-020-1889-x
Samantaray, S., Sahoo, A., Satapathy, D. P., Oudah, A. Y., & Yaseen, Z. M. (2024). Suspended sediment load prediction using sparrow search algorithm-based support vector machine model. Scientific Reports, 14 (1), 12889. https://doi.org/10.1038/s41598-024-63490-1
Sales, A. K., Gul, E., Safari, M. J. S., Ghodrat Gharehbagh, H., & Vaheddoost, B. (2021). Urmia lake water depth modeling using extreme learning machine-improved grey wolf optimizer hybrid algorithm. Theoretical and Applied Climatology, 146(1), 833-849. https://doi.org/10.1007/s00704-021-03771-1
Saplıoğlu, K., & Acar, R. (2020). K-means kümeleme algoritması kullanılarak oluşturulan yapay zeka modelleri ile sediment taşınımının tespiti. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 9(1), 306-322. https://doi.org/10.17798/bitlisfen.558113
Shaqiri, F. (2024). Applications of Time Series Forecasting Models, Decomposition Methods, Non-parametric Regression Methods, and Artificial Neural Networks. Fraunhofer Verlag.
Sharafati, A., Haji Seyed Asadollah, S. B., Motta, D., & Yaseen, Z. M. (2020). Application of newly developed ensemble machine learning models for daily suspended sediment load prediction and related uncertainty analysis. Hydrological Sciences Journal, 65, 2022–2042. https://doi.org/10.1080/02626667.2020.1786571
Shiri, N., Shiri, J., Nourani, V., & Karimi, S. (2022). Coupling wavelet transform with multivariate adaptive regression spline for simulating suspended sediment load: independent testing approach. ISH Journal of Hydraulic Engineering, 28(sup1), 356-365. https://doi.org/10.1080/09715010.2020.1801528
Specht, D. F. (1991). A General Regression Neural Network. IEEE Transactions on Neural Networks, 2(6), 568–576.
Vapnik, V. N. (1995). The Nature of Statistical Learning Theory. The Nature of Statistical Learning Theory. Springer New York.
Wright, S. (1921). Correlation and causation. Journal of Agricultural Research, 20(7), 557–585.
Xie, B., Bao, R., Yin, D., Zhu, L., Hu, R., Cai, W., Liu, T., Lin., C., & Lu, P. (2022). The spatio-temporal distribution and transport of suspended sediment in Laizhou Bay: Insights from hydrological and sedimentological investigations. Frontiers in Earth Science, 10, 994258. https://doi.org/10.3389/feart.2022.994258
Yang, H., & Li, W. (2023). Data decomposition, seasonal adjustment method and machine learning combined for runoff prediction: A case study. Water Resources Management, 37(1), 557-581. https://doi.org/10.1007/s11269-022-03389-6
Yılmaz, V. (2022). The use of band similarity in urban water demand forecasting as a new method. Water Supply, 22(1), 1004-1019. https://doi.org/10.2166/ws.2021.221
Yılmaz, V. (2023). Farklı performans metriklerinin buharlaşma modellemesi üzerindeki etkisinin incelenmesi. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 12(2), 472-486. https://doi.org/10.28948/ngumuh.1206278
Yilmaz, V., & Alpars, M. (2023). An Investigation of the Temporal Interaction of Urban Water Consumption in the Framework of Settlement Characteristics. Water Resources Management, 37(4), 1619-1639. https://doi.org/10.1007/s11269-023-03447-7
Yilmaz, V., Koycegiz, C., & Buyukyildiz, M. (2024a). Performance of data-driven models based on seasonal-trend decomposition for streamflow forecasting in different climate regions of Türkiye. Physics and Chemistry of the Earth, Parts A/B/C, 136, 103696. https://doi.org/10.1016/j.pce.2024.103696
Yilmaz, V., Koycegiz, C., & Buyukyildiz, M. (2024b). An approach on the estimation and temporal interaction of runoff: the band similarity method. Journal of Water and Climate Change, 15 (9): 4775–4789. https://doi.org/10.2166/wcc.2024.420
Yin, Y., Xia, R., Liu, X., Chen, Y., Song, J., & Dou, J. (2024). Spatial response of water level and quality shows more significant heterogeneity during dry seasons in large river-connected lakes. Scientific Reports, 14(1), 8373. https://doi.org/10.1038/s41598-024-59129-w
Yuan, Z., Gao, S., Wang, Y., Li, J., Hou, C., & Guo, L. (2023). Prediction of PM2. 5 time series by seasonal trend decomposition-based dendritic neuron model. Neural Computing and Applications, 35(21), 15397-15413. https://doi.org/10.1007/s00521-023-08513-0
Zhang, S., Wu, J., Jia, Y., Wang, Y. G., Zhang, Y., & Duan, Q. (2021). A temporal LASSO regression model for the emergency forecasting of the suspended sediment concentrations in coastal oceans: Accuracy and interpretability. Engineering Applications of Artificial Intelligence, 100, 104206. https://doi.org/10.1016/j.engappai.2021.104206
Zhou, T., Wang, F., Yang, Z., 2017. Comparative Analysis of ANN and SVM Models Combined with Wavelet Preprocess for Groundwater Depth Prediction. Water, 9 (10), 781. https://doi.org/10.3390/w9100781
Zounemat-Kermani, M., Batelaan, O., Fadaee, M., & Hinkelmann, R. (2021). Ensemble machine learning paradigms in hydrology: A review. Journal of Hydrology, 598, 126266. https://doi.org/10.1016/j.jhydrol.2021.126266

Details

Primary Language

English

Subjects

Water Resources Engineering

Journal Section

Research Article

Authors

Cihangir Köyceğiz ^*
0000-0002-0510-1164
Türkiye

Meral Büyükyıldız
0000-0003-1426-3314
Türkiye

Publication Date

March 3, 2025

Submission Date

June 17, 2024

Acceptance Date

December 20, 2024

Published in Issue

Year 2025 Volume: 28 Number: 1

DOI

https://doi.org/10.17780/ksujes.1502136

IZ

https://izlik.org/JA45RK33RH

Cite

RIS / Bibtex

APA

Köyceğiz, C., & Büyükyıldız, M. (2025). EFFECT OF SEASONAL-TREND DECOMPOSITION ON MACHINE LEARNING-BASED SUSPENDED SEDIMENT LOAD PREDICTION PERFORMANCE. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(1), 1-18. https://doi.org/10.17780/ksujes.1502136

Cited By

MELTBLOWN MAKİNELERİNDE ÜRETİLEN DOKUSUZ KUMAŞLARIN BASINÇ VERİMLİLİĞİNİN MAKİNE ÖĞRENMESİ YÖNTEMLERİ İLE TAHMİNLENMESİ VE PERFORMANS ANALİZİ

Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi

https://doi.org/10.17780/ksujes.1747540