Conducting research on the hydrological data objects is an important step in monitoring their condition. Changes in the quality and quantity of surface waters has social, environmental and economic consequences and require careful monitoring and, if necessary, quick response to adverse changes. This article discusses the computational scheme for the allocation of components in the time series, as well as the implementation and analysis of the above scheme using the example of hydrological monitoring data.The developed computational scheme processes the data presented in the form of time series.The first step in the analysis of hydrological data is the determination of the primary statistical characteristics of the object under study. Among these characteristics: average, minimum and maximum values of the time series; median, variance, coefficient of variation, kurtosis and asymmetry of the time series. The preliminary assumptions about the presence of deterministic components in the time series are made on the basis of a correlogram analysis based on the initial data.To test the hypothesis of the presence in the time series of the trend component, the Fosters-Stewarts method is used. When confirming the hypothesis that a trend in the time series is present, the trend component is removed by the described linear regression model, the parameters of which are calculated by the least squares method. Identification of periodic component of a time series is carried out using the methods of the Fourier analysis. The dynamics of the series are determined with using the methods of linear and nonlinear regression, in particular: polynomial (3 degrees), power, exponential, Phillips curve and Engel curve, whose parameters are calculated by the least squares method; modified exponential, the parameters of which are calculated by the method of three points. The analysis of the adequacy of the regression models is checked using the coefficient of determination and the adjusted coefficient of determination, also as the average approximation error. The Akaike information criterion and Bayesian information criterion Schwartz are used to determine the best model. The results of the study are accompanied by appropriate graphs and tables.