This work is a continuation of a previous survey related to a new sensor tree monitoring system TreeTalker© (TT). This system has been used to create a database, which is expected to be published shortly and which includes, among other things, a large amount of information on the sap density flux describing water transport process in different tree varieties that also differ in age, health status, metric characteristics, etc. Recall that in the previous paper we presented a method for predicting the density flux during the day based on data on air temperature during the observed cycle. For this purpose, Fourier series and a multivariate regression model were used, establishing the functional relationship between the respective Fourier coefficients for temperature data sets and density flux values. Here we report our first experiments carried out on data sets extracted by the TT monitoring system as well as on the estimated values of the density flux and dedicated to trees classification. Classification is a very common use case of a machine learning. Artificial neural networks is a part of a supervised machine learning which is most popular in different problems of data classification, pattern recognition, regression, clustering, time series forecasting.