Intelligent forecasting of growth and development of fruit trees by deep learning recurrent neural networks

Abstract The questions of intellectual forecasting of dynamic processes of growth and development of fruit trees are considered. The average growth rate of shoots of apple trees of the «Renet Simirenko» variety was predicted. Forecasting was carried out using a deep learning recurrent neural network LSTM in relation to a one-dimensional time series, with which the specified parameter was described. The implementation of the recurrent neural network LSTM was carried out in the MATLAB 2021 environment. When defining the architecture and training of the LSTM recurrent neural network, the Deep Network Designer application was used, which is included in the MATLAB 2021 extensions and allows you to create, visualize, edit and train deep learning networks. The recurrent neural network LSTM was trained using the Adam method. The results obtained in the course of predicting the average growth rate of apple shoots using a trained LSTM recurrent neural network were evaluated by the root-mean-square error RMSE and the loss function LOSS.

Ҳали таржима қилинмаган