Application of artificial neural networks (ANN) in Lake Drwęckie water level modelling

• Published in: Limnological review (Warsaw, Poland) Vol. 15; no. 1; pp. 21 - 30
• Main Authors: Piasecki, Adam, Jurasz, Jakub, Skowron, Rajmund
• Format: Journal Article
• Language: English
• Published: Torun De Gruyter Open 01-03-2015; MDPI AG
• Subjects: East Central Europe; Lake Drwęckie; Lakes; neural networks; postglacial lake; Water level fluctuations; Water levels
• ISSN: 2300-7575; 1642-5952; 2300-7575
• DOI: 10.2478/limre-2015-0003

This paper presents an attempt to model water-level fluctuations in a lake based on artificial neural networks. The subject of research was the water level in Lake Drwęckie over the period 1980-2012. For modelling purposes, meteorological data from the weather station in Olsztyn were used. As a result of the research conducted, the model M_Meteo_Lag_3 was identified as the most accurate. This artificial neural network model has seven input neurons, four neurons in the hidden layer and one neuron in the output layer. As explanatory variables meteorological parameters (minimal, maximal and mean temperature, and humidity) and values of dependent variables from three earlier months were implemented. The paper claims that artificial neural networks performed well in terms of modelling the analysed phenomenon. In most cases (55%) the modelled value differed from the real value by an average of 7.25 cm. Only in two cases did a meaningful error occur, of 33 and 38 cm.