Forecasting surface water level fluctuations of lake Serwy (Northeastern Poland) by artificial neural networks and multiple linear regression

Abstract

The aim of this study is to assess the possibility of forecasting water level fluctuations in a relatively small (<100 km²), post-glacial lake located in a temperate climate zone by means of artificial neural networks and multiple linear regression. The area of study was Lake Serwy, located in northeastern Poland.

Two artificial neural network (ANN) multilayer perceptron (MLP) and multiple linear regression (MLR) models were built. The following explanatory variables were considered: maximal and minimal temperature (Tmax, Tmin) wind speed (WS), vertical circulation (VC) and water level from previous periods (WL). Additionally, a binary variable describing the period of the year (winter, summer) has been considered in one of the two MLP and MLR models. The forecasting models have been assessed based on selected criteria: mean absolute percentage error (MAPE), root mean squared error (RMSE), coefficient of determination (R2) and mean biased error. Considering their values and absolute deviations from observed values it was concluded that the ANN model using an additional binary variable (MLP_B+) has the best forecasting performance. Absolute deviations from observed values were the determining factor which made this model the most efficient. In the case of the MLP_B+ model, those values were about 10% lower than in other models.

The conducted analyses indicated good performance of ANN networks as a forecasting tool for relatively small lakes located in temperate climate zones. It is acknowledged that they enable water level forecasting with greater precision and lower absolute deviations than the use of multiple linear regression models.

Keywords:

• ANN
• multiple linear regression
• lake Serwy
• water level
• post-glacial lake

Additional information

Notes on contributors

Adam Piasecki

Adam PIASECKI. Mr. Adam Piasecki (MSc) is a PhD student at the Nicolaus Copernicus University in Toruń as well as at the AGH University in Cracow. Currently he is conducting research in area of hydrology and water management. He was a participant of several national and international workshops and conferences as well as author and co-author of many scientific publications.

Jakub Jurasz

Jakub JURASZ. Mr. Jakub Jurasz (PhD Eng.) is a research assistant at the AGH University in Cracow. His current research concentrates on the concept of water – energy nexus as well as integration of renewable energy sources to the national power system. Dr Jurasz is an author and co-author of several dozen papers which were published in recognized journals in field of energy.

Rajmund Skowron

Rajmund SKOWRON. Mr. Rajmund Skowron (PhD, DSc) is an expert in are of earth sciences. Lifelong research employee of the Nicolaus Copernicus University in Toruń. His research concentrates on limnology as well as the impact of human activities on the natural environment. In his publications he investigates the problem of water temperature as well as glaciation. He was author and co-author of at least 75 scientific contributions from which majority relates physical limnology. Currently he is working on lakes disappearance in Poland as well as long long-term changes in lakes thermal regime.