The prediction of the inside temperature and relative humidity of a greenhouse using ANN method with limited environmental and meteorological data

In this paper, the prediction of internal temperature (Tin) and relative humidity (Rhin) a greenhouse located near Agadir, Morocco using artificial neural net-work (ANN) as machine learning method. First, an analyze correlations be-tween inputs outputs is studied in order to select adequate input parameters. External temperature, solar radiations were parameters that have highest correlation coefficient with outputs. They are thus selected only The Tin Rhin previously cited gives perfect (R=0.996). aim study use one measured parameter (external temperature) eliminate two environmental (relative radiation), by introducing factor time ANN model. Results very satisfying 20 neurons was sufficient reach about 0.98.