Abstract
Accurate regulation of modern greenhouse requires fast and accurate acquisition of various key physiological indexes of greenhouse crops. Greenhouse environmental data and crop physiological data were used as input and output, and the Deep&Wide Neural Network (WDNN) model was established to predict the tomato net photosynthetic rate in greenhouse. Through the adoption of ADAM algorithm, the accuracy of WDNN has been improved. At the same time, compared with the traditional Deep Neural Network(DNN), WDNN has a better prediction effect. Mean Absolute Error (MAE), Mean Squard Error (MSE), Root Mean Squard Error (RMSE) of WDNN predicted value and real value were 0.7498, 1.7617, 1.3272, respectively, and determination coefficient of the model was 0.9764.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have