Sediment-carrying capacity prediction using extreme learning machine

Abstract

Sediment-carrying capacity prediction is an important part in the river sediments movement simulation. In this paper, a novel machine learning approach was proposed to predict the sediment-carrying capacity by using the Extreme Learning Machine (ELM). The evaluation indexes and the average errors of these prediction models were analysed in detail. The result shows that the ELM model has a good generalization performance for the sediment-carrying capacity prediction, and the ELM approach could be an effective tool for the sediment movement simulation.