The purpose of greenhouse crop systems is to generate a high quality product at high production rates, consistently, economically, efficiently and in a sustainable way. To achieve this level of productivity, accurate monitoring and control of some processes of the entire biophysical system must be implemented. In addition, the proper selection of actions at the strategic, tactical and operational management levels must be implemented.Greenhouse management relies largely on human expertise to adjust the appropriate optimum values for each of the production and environmental parameters, and most importantly, to verify by observation the desired crop responses. The subjective nature of observing the plant responses, directly affects the decision-making process (DMP) for selecting these `optimums'. Therefore, in this study several decision support systems (DSS) were developed to enhance the DMP at each of the greenhouse managerial levels.A dynamic greenhouse environment model was implemented in a Web-based interactive application which allowed for the selection of the greenhouse design, weather conditions, and operational strategies. The model produced realistic approximations of the dynamic behavior of greenhouse environments for 28-hour simulation periods and proved to be a valuable tool at the strategic and operational level by evaluating different design configurations and control strategies.A Web-based crop monitoring system was developed for enhancing remote diagnosis. This DSS automatically gathered and presented graphically environmental data and crop-oriented parameters from several research greenhouses. Furthermore, it allowed for real-time visual inspection of the crop.An intelligent DSS (i-DSS) based on crop records and greenhouse environment data from experimental trials and from commercial operations was developed to characterize the growth-mode of tomato plants with fuzzy modeling. This i-DSS allowed the discrimination of "reproductive", "vegetative" and "balanced" growth-modes in the experimental systems, and the seasonal growth-mode variation on the commercial application.An i-DSS based on commercial operation data was developed to predict the weekly fluctuations of harvest rates, fruit size and fruit developing time with dynamic neural networks (NN). The NN models accurately predicted weekly and seasonal fluctuations of each variable, having correlation coefficients (R) of 0.96, 0.87 and 0.94 respectively, when compared with a dataset used for independent validation.