Funded under the European Commission's FET (Future and Emerging Technologies) initiative of the IST programme, the PLANTS project sought to develop a unique system that linked plants, technology and people to continuously assess the state of crop health. Using sensors, transmitters and specialist software, the system monitors the state of the crop on a plant-by-plant basis, in near real-time.

Dr Anthony Morrissey at Tyndall National Institute (Ireland) led the project which included partners from University College Cork (Ireland), Computer Technology Institute (CTI, Greece) and Eden Project Ltd (UK).

"You could almost walk away from the crop and let it grow on its own," says Dr Fiona Tooke of the Eden Project, a unique public education facility in the UK's Cornwall region that gathers all the planet's major agricultural systems under a series of spectacular, and immense, plastic domes that function as high tech glasshouses. Eden joined the PLANTS project to help promote, and disseminate the ideas and philosophy behind the project.

The combined presence of plants and artefacts in an environment inhabited by humans set a new computing environment, where the complexity of the interactions between many possibly heterogeneous artefacts and their environment, including plants and humans, could be overcome by developing a technological framework (i.e., system architecture, models and tools) for composing the so-called ubiquitous computing applications.

PLANTS adhered to a broader vision where the virtual (computing) space was seamlessly integrated with the physical environment. One of its main objectives was to develop the necessary software modules, tools and methodologies that enable the efficient and flexible integration of �augmented' plants and artefacts into ubiquitous computing applications which may range from domestic plant care to precision agriculture.

To bring this vision closer to reality several issues were addressed and resolved:

software infrastructure for pervasive computing that can support the integration between our physical space and virtual computing space; sensors and sensor network that can capture and disseminate context information; context-aware applications that use context information to create intelligent artefacts and applications; � embedding computing into physical entities; user interfaces for supporting ubiquitous computing. Optimising resources "The system picks up on the plants' signals that indicate when plants need help, such as more water, more nutrients or more or less light. Essentially, the plants are controlling the system," says Tooke.

"The main idea behind PLANTS is to develop a system that produces the optimal growing conditions for a crop, so that crops are kept in the best possible health with the minimum of inputs,� she continues. �It promotes sustainability, because there isn't excessive use of inputs like fertilizer and water. It makes crop management more economic too, as well as less damaging to the environment."

The system uses an infrared camera to scan the entire crop canopy. It can automatically detect when individual or groups of plants are getting too hot. Another sensor detects chlorophyll fluorescence, which tells the system the rate at which the plant is absorbing energy. That reflects the current state of photosynthesis, itself a reflection of the plant's health. The team at University College Cork is evaluating other sensors in a future project.

These sensors communicate their data through specially developed wireless transmitters. The transmitters started out as a Field Programmable Gate Array (FPGA), a sort of universal microchip that can be set to carry out many different functions. Over the life of the project, however, scientists at project partner the Tyndall National Institute in Cork managed to reduce the essential technology from 100mm FPGAs, to a specialised 25mm module. They believe it will be possible to reduce it to a mere 10mm cube utilising the latest system integration technologies under development at Tyndall.

This system incorporates a wireless transceiver capability with embedded protocol software to minimise power consumption and maximise data throughput. This can work in conjunction with high specification FPGA technology for signal processing tasks. Additional input capability for sensor and actuator integration can be incorporated seamlessly due to the modular nature of the system. This gives it the ability to interface to a broad range of physical and chemical transducers. The total system is packaged in a modular 25mm cubed form factor developed at Tyndall. This enables the module to be utilised in a wide variety of projects incorporating a multitude of actuators/sensors in miniaturised, mobile, autonomous systems.

What's more, these chips work wirelessly and contain their own batteries. They can communicate over large distances for their size, with a current range of about 10m, but again the Tyndall team hope to push their range further. "Finally, they are also looking at the potential of 'Power Harvesting' for the chip, where it would supply its own energy needs through solar energy or ground vibrations, making the chip completely independent,'' says Tooke.

She believes these could have many applications outside of the PLANTS project. "We were speculating, for example, that they might have an application in hostile environments, like growing plants in space or soil-less systems. Potentially, these are situations where our system could prove very useful."

The sensors and transmitters are two key elements of the system, but its heart is the management software, designed by Computer Technology Institute, Greece, that gathers, and then acts, on the data operating as a plant/environmental context management system. Called ePlantOS, it can control the deployment of water, nutrients or pesticides, as necessary.

ePlantOS provides an interface with sensors and actuators, maintains a plant-specific ontology and supports distributed resource management with local and/or global decision-making according to criteria. ePlantOS is a middleware system operating according to a peer-to-peer interaction model in which plants being monitored and devices of the system are universally modelled. A modular design allows the replacement of a module without affecting the functionality of the rest provided that the interfaces between them remain consistent. The system incorporates a mechanism for learning rules or parameters to be used in the decision making process, according to historical/logged data.

A set of graphical tools provide the user with a set of useful operations like creating/composing/ reconfiguring applications which may range from domestic plant care to precision agriculture, viewing knowledge represented into the PLANTS ontology, monitoring the plant and environmental parameters and finally managing dynamically the rules taking part in the decision-making process.

PLANTS on show PLANTS developed two demonstrators, one at the beginning of the project in 2003 to prove the concept. The second demonstrator went live at the Eden Project end March 2006 and was the centre point of a special workshop to introduce the technology to experts in the fields of plant science, crop management, microelectronics and software engineering. A temporary exhibit will now show PLANTS results from mid-April to end June 2006 at the Eden Project.

The team designed the current system to track high-value, glasshouse crops like strawberries and other soft fruits, but a commercial version could be tractor mounted to survey field crops and, as the costs of production come down, it may be possible to deploy in it in comparatively low-value crops, too.

As well as improving the system, as it exists now, by further miniaturising the equipment, the team also hopes to develop other sensors in a future project. These could look at the levels of volatiles, gases that plants emit when they are under stress. For example, the presence of methyl jasmonate shows the plant suffered a wound, typically from a pest, while plants release methyl salicylate in response to disease, such as a fungal attack. Tracking these gases would allow farmers to deploy pesticides or other remedies when necessary.

"Unfortunately plants emit such small doses of these gases that they are difficult to detect with current sensor technology, but scientists at University College Cork are looking at this area and it may be a part of some future system," says Tooke.

Three partners lodged a patent for the technology developed during the PLANTS project. "They certainly hope to carry the work further, by initially developing a prototype, and then possibly commercialising the system,� says Tooke. �That work will go beyond the life of this project, however. PLANTS ended in March 2006."

�Moving our research effort even further, towards to a more autonomous system in the long-term with self-adaptation and self-learning characteristics, we aim to explore ways of incorporating AI [Artificial Intelligence]/Machine Learning aspects in the system," she says.

However, none of those system improvements will make the plants totally stress free, but if the project's crop management system takes off, at least their complaints will be heard and listened to.

Related Links
Tyndall National Institute
University College Cork
Computer Technology Institute
Eden Project
European Commission Future and Emerging Technologies Initiative