Trees classification based on Fourier coefficients of the sapflow density flux

In this paper we study the possibility to use artificial neural networks for trees classification based on real and approximated values of sap flow density flux describing water transport in trees. The data sets were generated by means a new tree monitoring system TreeTalker. Fourier series-based model is used fitting with periodic patterns. multivariate regression defines functional dependencies between temperature time series. shows that coefficients can be successfully as elements feature vectors required solve different problems. Here train multilayer classify according types classes. quality developed prediction verified numerous numerical examples.