Data-driven study of flow & sediment in circular channels using GPR & ANFIS
Abstract
This study investigates sediment transport in circular pipes using Gaussian Process Regression (GPR) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS). The models evaluate how hydraulic parameters and sediment characteristics influence sediment discharge. Among various input combinations, the model with λs, Fd, Dgr, and d50/R achieved the highest accuracy under both smooth and rough pipe conditions. Sensitivity analysis identified the particle Froude number (Fd) as the most influential factor. Predictions were more accurate for smoother pipe beds, as increased roughness reduced sediment transport efficiency. These findings provide a reliable, data-driven approach for estimating sediment transport in water and wastewater systems.
Fields of Study & Subjects
Hydrology and Sediment Transport Processes
Hydrological Forecasting Using AI
Coastal wetland ecosystem dynamics
Publication details
- Journal / source
- Multiscale and Multidisciplinary Modeling Experiments and Design
- Publisher
- Springer Science and Business Media LLC
- Volume
- 9
- Issue
- 1
- Publication date
- 12 February 2026
- Language
- EN