SUSPENDED SEDIMENT ESTIMATION USING MACHINE LEARNING METHODS

• Published in: Aerul si Apa. Componente ale Mediului Vol. 2024; no. 1; pp. 105 - 114
• Main Authors: Taşar, Bestami, üneş, Fatih, Demirci, Mustafa, Güzel, Hasan, Varçin, Hakan
• Format: Journal Article
• Language: English
• Published: Cluj-Napoca Babes Bolyai University Faculty of Geography 01.03.2024; Cluj University Press
• Subjects: Artificial intelligence; Decision trees; Genetic algorithms; Hydraulic loading; Hydraulic structures; Learning algorithms; linear regression; m5 tree; Machine learning; Neural networks; prediction; River sediments; Rivers; Root-mean-square errors; Sediment; Sediment concentration; Sediment discharge; Sediment load; Statistical analysis; Statistical methods; Statistical models; Stream discharge; Stream flow; Support vector machines; Suspended load; Suspended sediments; Water discharge; Water resources; Water temperature; United States > US; Ohio; Cuyahoga River
• ISSN: 2067-743X; 2344-4401
• DOI: 10.24193/AWC2024_10

Suspended sediment in rivers is important for efficiently using water resources and hydraulic structures. In this study, the suspended sediment load of rivers was estimated using traditional multi-linear regression (MLR), machine learning methods such as the support vector machines (SVM) and M5 decision tree (M5T). Data on daily stream flow, daily maximum and minimum water temperature and suspended sediment concentration in the river were used as input data in all models to predict daily suspended sediment discharge. The performance of all methods is evaluated based on a statistical approach. Determination coefficient (R2), root mean square error (RMSE) and mean absolute error (MAE) are used as comparison criteria. Overall, the machine learning approaches better predict suspended sediment discharge.