Daily discharge forecasting using least square support vector regression and regression tree

Prediction of river ow is one of the main issues in the eld of water resourcesmanagement. because of the complexity of the rainfall-runo process, data-driven methodshave gained increased importance. in the current study, two newly developed models calledleast square support vector regression (lssvr) and regression tree (rt) are used. thelssvr model is based on the constrained optimization method and applies structural riskminimization in order to yield a general optimized result. also, in the rt, data movementis based on laws discovered in the tree. both models have been applied to the data in thekashkan watershed. variables include (a) recorded precipitation values in the kashkanwatershed stations, and (b) outlet discharge values of one and two previous days. presentdischarge is considered as output of the two models. following that, a sensitivity analysishas been carried out on the input features and less important features have been diminished,so that both models have provided better prediction on the data. the nal results of bothmodels have been compared. it was found that the lssvr model has better performance.finally, the results present these models as suitable models in river ow forecasting.