Abstract
In this paper, deterministic and Artificial Neural Networks (ANNs) based techniques are applied to generate solar radiation forecasts with the purpose of being incorporated within a greenhouse predictive control strategy. These predictions are essential to estimate heat load fluctuations in the greenhouse caused by high frequency solar radiation changes, and so to improve ventilation and heating computation requirements for the greenhouse.

Abstract
This work presents an on-chip silicon bulk-micromachined Soil Moisture Sensor (SMS) suited for irrigation control and management applications. The same basic fabrication concepts and materials, which made microelectronics successful, are now being adapted to making low-cost, small, high-performance sensor systems with integrated electronics on the same chip. As a result, this system-on-a-chip includes the SMS, readout electronics, self-test, calibration facilities and a digital bus interface for external data transmission, Moreover, since this sensor has low-cost, it could be employed several sensors networked together with the 1-wire bus, to achieve an accurate measure of the soil moisture at the plant root level. A heat-pulse technique is used (for measuring the maximum temperature on a distant point) to determine the volumetric heat capacity and hence the water content of a porous media, such as soil. This method is based on the Joule effect (heater probe shank) and in Seebeck effect (thermopile - temperature probe shank). The heater and the thermopile are suspended on a dielectric window to reduce undesired heat conduction to the substrate (silicon is a good heat conductor). Thermal simulations of the bulk-micromachined SMS are performed to test sensor performance. In order to validate the method, simulations are made and experimental results were achieved with a macrosensor based on this technique. The results were compared with the measurements performed by the conventional thermo-gravimetric method.

Abstract
This paper reports the design, modelling, fabrication and assembly of a silicon bulk-micromachined soil moisture microsensor using the Dual-Probe Heat-Pulse (DPHP) method. Soil humidity measurement is essential to study soil preservation and control the development of plants, namely in closed ecosystem. The DPHP method uses a heater (Peltier effect) and a temperature probe (Seebeck effect) to determine the volumetric heat capacity of the soil and hence water content (theta (v)). This is the first time that the DPHP method is implemented in a microdevice and the first integrated sensor for soil moisture. This microdevice is more suited to measure at different soil depths in a non-destructive and automated manner.

Abstract
Greenhouse control computers are an essential part of modern greenhouse operation. Climate, irrigation and nutrient supply must be controlled, in an economical way, to produce the best crop conditions. Current research on CO2 enrichment and optimal growth strategies implies the use of powerful tools, either based on hardware or software. This paper describes the design and implementation of a distributed data acquisition and control system for computerised agricultural management systems that is being developed at Universidade of Tras-os-Montes and Alto Douro, Vila Real. Different communications platform concepts, such as Controller Area Network (CAN), Wireless Technologies, Ethernet and Internet tools supported by Transfer Control Protocol/Internet Protocol (TCP/IP) and e-mail tools supported by Simple Mail Transfer Protocol (SMTP) were used to achieve a network with a low-cost, flexible, and functional characteristics. The system management and maintenance tasks are divided into two types of performance levels. At a lower supervision level, a Local Controller placed in the greenhouses performs the monitoring/control and communications actions. The management decisions are performed at the higher level. The techniques and tools, which provide to the user a transparent, friendly and intuitive Graphical User Interface (GUI) will be presented.

Abstract
Crop models are useful to improve the management and control of the greenhouse climate. In fact, they are essential if it is intended to optimize the climate control according to a defined production plan. In this paper are reviewed simulation models developed for horticultural crops with emphasis on leaf area and dry matter production. The dynamic crop models are based on the description of the crop photosynthesis and respiration processes. Various models were tested for a tomato crop grown in a greenhouse with a soil medium. The environmental factors such as air temperature and humidity, photosynthetic flux density, carbon dioxide concentration, among others, were measured, with a sampling rate of 1 minute and the mean values were stored with a 30min time interval. Plant leaf area and fresh and dry weights were measured by conducing periodic destructive tests. The results achieved with the different models employed are discussed and their applicability addressed.

Abstract
This paper describes the 5dpo team. The paper will be divided into three main sections, corresponding to three main blocks: the Global Level, the Local Level and the Interface Level. These Levels, their subsystems and some implementation details will be described next.