Eva Ocvirk

An application of Romberg extrapolation on quadrature method for solving linear Volterra integral equations of the second kind

The Romberg extrapolation is applied on quadrature method solution of linear Volterra integral equations (VIE) of the second kind. An algorithm for new solution calculated by Romberg method is given. The calculated solutions show more efficiency and accuracy with less computation than solution with quadrature method over more points of integration.

Calibration of supervised learning models using model parameters optimization algorithms

Searching for optimal parameters of supervised learning models for the purpose of hydrological modelling tend to be timely exhaustive. Duration of parameter searching depend of model representation, number of instances for model training and calibration, number of varied parameters, range and number of parameters in the range, number of used combinations of dataset division in training and calibration part, model nature for chosen parameters. Dependence of model precisions of parameters choice is decreased with increase of number of instances for model training, and in the case of decreased number of instances more attention has to be put on parameter searchin Results of parameter searching for three supervised models with different input variables configuration are shown in the paper. Searching is done by using two basic principles: choice of best solution for chosen ranges and number of parameters and by searching with optimization algorithm – simulated annealin.