DBPapers

INVESTIGATION OF WATER QUALITY STATE DYNAMICS OF DANUBE RIVER IN THE EASTERN PART OF ROMANIA

G. Murariu, A. G. MURARIU, C. ITICESCU, M. TIMOFTI, L. GEORGESCU
Wednesday 19 December 2018 by Libadmin2018

ABSTRACT

The study of aquatic systems is an extremely important issue in the context of saving. natural resources. In this respect, the description of the evolution over time and the dynamics of some status parameters describing the dynamic aquarium system is a rather difficult problem. This paper presents a method of representing evolution over time and some status parameters that allow assessment of the status of an aquatic system. The method outlined in the paper is based on the use of automated automatic neural network (ANN) models. As a case study the aquatic system of the Danube river near Galati Romania is considered. The article describes the stage of training, validation and application of neural network models (ANN) for assessing pH and carbonic acid level. For a fair evaluation, a total of 20 different models were constructed and a number of 6 AN models were presented which had the best performances for assessing the HCO3 concentration and pH value in Danube waters respectively. The performance of the ANN models was evaluated by the coefficient of determination (R) (square of the correlation coefficient), the mean square error (SOS). The identified models can be used as tools for calculating water quality parameters

Keywords: Numerical approach; Statistical analysis; Interpolation method


Home | Contact | Site Map | Site statistics | Visitors : 0 / 353063

Follow site activity en  Follow site activity HYDROLOGY AND WATER RESOURCES  Follow site activity Papers SGEM2018   ?

CrossRef Member    Indexed in ISI Web Of Knowledge   Indexed in ISI Web Of Knowledge
   

© Copyright 2001 International Multidisciplinary Scientific GeoConference & EXPO SGEM. All Rights Reserved.

Creative Commons License