Prediction of river suspended sediment load using machine learning models and geo-morphometric parameters

Abstract Estimating sediment load of rivers is one the major problems in river engineering that has been using various data mining algorithms and variables. It desirable to obtain accurate estimates while techniques limit computational intensity when datasets are large. This study investigates usefulness geo-morphometric factors machine learning (ML) models for predicting suspended (SSL) several basins Lorestan Gilan, Iran. Six ML models, namely, multiple linear regression (MLR), artificial neural networks (ANN), K-nearest neighbor (KNN), Gaussian processes (GP), support vector machines (SVM), evolutionary (ESVM), were evaluated estimating minimum average SSL regions. Geo-morphometric parameters discharge utilized as main predictors modeling process. In addition, an attribute reduction technique was applied decrease algorithm complexity resources used. The results showed all estimated both target variables well. However, optimal GP ESVM respectively.