The techniques of task analysis and task allocation were applied to the problem of decision support system development in tree fruit production. The task of midwinter freeze protection of peach and nectarine [Prunus persica (L.) Batsch] flower buds was chosen as the model system. Sixty-five tasks and subtasks were identified as necessary components of the freeze-protection activity at the testing and subsequent management activity levels. Of these, 45 were done exclusively in the orchard where we wished to focus our efforts to benefit the broadest group of growers. Of these 45 tasks or subtasks, 13 were judged suitable for computerization. These 13 tasks were prioritized in order of importance to growers through a self-administered mail survey that asked how often they would use a computer to perform each task. Based on a 77% rate of return, peach and nectarine growers indicated that they were most likely to use a computer to monitor weather forecasts for general weather and freeze alerts, monitor real-time orchard temperatures, and estimate critical temperature ranges for flower-bud damage. This close interaction also produced additional design and use information for the proposed knowledge-based system, such as data presentation requirements, the presence of a variety of farming styles that often determined how the critical temperature data were produced and used, and the challenges of developing suitable validation data for the users.
Michael J. Willett, Preston K. Andrews, and Edward L. Proebsting
Kuanglin Chao, Richard S. Gates, and Robert G. Anderson
Knowledge engineering offers substantial opportunities for integrating and managing conflicting demands in greenhouse crop production. A fuzzy inference system was developed to balance conflicting requirements of producing a high-quality, single-stem rose crop while simultaneously controlling production costs of heating and ventilation. An adaptive neuro-fuzzy inference system was built to predict the rose status of `Lady Diana' single-stem roses from nondestructive measurements. The fuzzy inference system was capable of making a critical decision based on the principle of economic optimization. Temperature set points for two greenhouses with similar rose status were treated significantly different by the fuzzy inference system due to differences in greenhouse energy consumption. Moderate reduction in heating energy costs could be realized with the fuzzy inference system.
Paul R. Fisher and Royal D. Heins
A methodology based on process-control approaches used in industrial production is introduced to control the height of poinsettia (Euphorbia pulcherrima L.). Graphical control charts of actual vs. target process data are intuitive and easy to use, rapidly identify trends, and provide a guideline to growers. Target reference values in the poinsettia height control chart accommodate the biological and industrial constraints of a stemelongation model and market specifications, respectively. A control algorithm (proportional-derivative control) provides a link between the control chart and a knowledge-based or expert computer system. A knowledge-based system can be used to encapsulate research information and production expertise and provide management recommendations to growers.
Paul R. Fisher, Royal D. Heins, Niels Ehler, Poul Karlsen, Michael Brogaard, and J. Heinrich Lieth
Commercial production of Easter lily (Lilium longiflorum Thunb.) requires precise temperature control to ensure that the crop flowers in time for Easter sales. The objective of this project was to develop and validate a greenhouse decision-support system (DSS) for producing Easter lily to predetermined height and flower date specifications. Existing developmental models were integrated with a knowledge-based system in a DSS to provide temperature recommendations optimized for Easter lily scheduling and height control. Climate data are automatically recorded in real time by linking the DSS to a greenhouse climate control computer. Set point recommendations from the DSS can be manually set or automatically implemented in real time. Potential benefits of the project include improved crop quality and the transfer, validation, and integration of research-based models. The DSS was implemented at several research and commercial locations during the 1994 Easter lily season. DSS recommendations were compared with the strategies of experienced growers. The system design, implementation, production results, quality of recommendations, and potential are discussed.