Integration of ANFIS with PCA and DWT for daily suspended sediment concentration prediction

• Published in: Water S. A. Vol. 47; no. 2; pp. 200 - 209
• Main Authors: Dang, Nguyen Mai, Anh, Duong Tran
• Format: Journal Article
• Language: English
• Published: Gezina Water Research Commission (WRC) 01.04.2021; Water Research Commission
• Subjects: Adaptive systems; Agricultural production; Analysis; Aquatic biota; Aquatic resources; Artificial neural networks; Biota; Canada; Case studies; Discrete Wavelet Transform; Ecosystem integrity; Environmental impact; Environmental studies; Flow rates; Flow velocity; Fluvial morphology; Fuzzy logic; Iowa River; Machine learning; Morphology; Neural networks; Predictions; Principal components analysis; River discharge; River flow; Rivers; Schuylkill River; Sediment; Sediment concentration; Sediment load; Sediment transport; Sediment, Suspended; Statistical methods; Suspended load; Suspended sediment; Suspended sediments; Water resources; Water shortages; Wavelet transforms; Canada; United States > US; Iowa River; Schuylkill River
• ISSN: 0378-4738; 1816-7950
• DOI: 10.17159/wsa/2021.v47.i2.10916

Quantifying sediment load is vital for aquatic and riverine biota and has been the subject of various environmental studies since sediment plays a key role in maintaining ecological integrity, river morphology and agricultural productivity. However, predicting sediment concentration in rivers is dificult because of the non-linear relationships of flow rates, geophysical characteristics and sediment loads. It is thus very important to propose suitable statistical methods which can provide fast, accurate and robust prediction of suspended sediment concentration (SSC) for management guidance. In this study, we developed coupled models of discrete wavelet transform (DWT) with adaptive neuro-fuzzy inference system (ANFIS), named DWT-ANFIS, and principal component analysis (PCA) with ANFIS, named PCA-ANFIS, for SSC time-series modeling. The coupled models and single ANFIS model were trained and tested using long-term daily SSC and river discharge which were measured on the Schuylkill and Iowa Rivers in the United States. The findings showed that the PCA-ANFIS performed better than the single ANFIS and the coupled DWT-ANFIS. Further applications of the PCA-ANFIS should be considered for simulation and prediction of other indicators relating to weather, water resources, and the environment.