Automated zone-specific irrigation with wireless sensor/actuator network and adaptable decision support
Introduction
Given the advancements in the field of wireless sensor networks (WSNs) as well as in the miniaturization of such sensor systems, new trends have emerged in the field of precision agriculture (Zhang et al., 2002, Srinivasan, 2006). Reviews of wireless sensor technologies and applications in agriculture and food industry have been given by Wang et al. (2006) and by Ruiz-Garcia et al. (2009).Wireless networks allow the deployment of sensing and actuation infrastructure at a much finer granularity than has been available before. Sensors and actuators can be used to precisely and autonomously control, for example, the concentration of fertilizer in the soil, based on information gathered from the soil itself, the ambient temperature, and other relevant environmental factors. Incorporating feedback into the system through the use of sensors and actuators allows for a more fine-grained analysis that can adjust flow rate and duration in a way that is informed by local conditions. Significant economic gains are expected by applying such precise information to control the growth of particularly delicate and high value crops such as wine grapes, citrus fruit and strawberries. Sensors that are able to monitor the crop itself, for example, leaf temperature in strawberries, or sugar-levels in grapes, or the photosynthetic activity of the crop plant, to provide location-specific data could also prove to be very effective.
In particular, the use of WSN technology to optimize irrigation in agriculture is of benefit to both the farmers and the environment. According to recent reports, agriculture irrigation accounts for 50–60% of freshwater usage from sources in the natural environment and up to more than 90% in some developing countries (UNESCO, 2009, pp. 106–115). Given the increasing worldwide shortage of water caused by a combination of a changing climate and pressure resulting from high demand of agricultural products, it is of primary importance to develop new irrigation control strategies that allow the minimization of water wastage while keeping associated costs at an affordable level.
In this paper we describe the design of an intelligent decision support system and its integration with a wireless sensor/actuator network (WSAN) to implement closed-loop zone specific irrigation control in greenhouses via wireless communication. Our research focuses on the provision of proactive applications by deploying sensor networks and connecting sensor data with actuators through an adaptive and able to learn decision-making layer. The system developed provides real-time monitoring and control of both agricultural inputs and outputs (irrigation control). A rule editor with a graphical user interface (GUI) is used by the domain-expert to initialize the knowledge base. The system is optimized to adapt to changes in crop development by configuring the rule parameters in the system ontology. In addition, machine learning is employed to enrich systems’ knowledge base.
The remaining of the paper is organized as follows. Section 2 gives an overall description of the developed system. The topics covered in this discussion include the layered modular architecture of the system, the WSAN platform, the supported sensors and their interfacing to the platform, the ontology-based decision making layer and the machine learning process followed to extend system knowledge. Section 3 details the technological and agronomic results. It provides an evaluation of the developed system in terms of a prototype deployment, the derivation of new rules from the machine learning experiments performed, the WSN performance analysis and the mote lifetime estimation by using analytical models, the agronomic impact of the system and also provides a discussion of related work and lessons learnt. Finally, Section 4 presents a summary of this work.
Section snippets
Materials and methods
The overall goal of the research and development work described in this paper is to design a new plant growth monitoring and control system comprising:
- •
a distributed network of sensors for accurately sensing the plant growth activity and environmental conditions, and plant growth control actuators;
- •
ontology-based decision support mechanisms that associate sensor data with actuator commands;
- •
a machine learning process for enhancing plant state diagnosis based on logged data; and
- •
a set of tools that
Experiments and results
Strawberry plants (Fragaria ananassa) have been selected for system validation and evaluation because the delivered technology can be relevant to the commercial production of this crop, while on a practical level, the size of the leaves enables easy attachment of sensors. In addition, irrigation control on strawberry plants is important as they have a shallow root system making them particularly sensitive to water stress. On the other hand, controlling excessive irrigation is significant for
Conclusions
We have been involved with a facet of precision agriculture that concentrates on plant-driven crop management. By monitoring soil, crop and climate in a field and providing a decision support system that is able to learn, it is possible to deliver treatments, such as irrigation, to specific parts of a field in real time and proactively. We have presented in this paper an integrated framework consisting of hardware and software components as well as tools that support efficiently the development
Acknowledgments
Part of the research described in this paper was conducted in the PLANTS project (IST FET Open IST-2001-38900); the authors wish to thank their fellow researchers in the PLANTS consortium for their input and support. We are grateful to professor Alan Cassells from the University College Cork for sharing his valuable insights regarding the plant science aspects of this research. The authors would also like to thank the anonymous reviewers for their helpful comments and constructive suggestions
References (38)
- et al.
Development of field programmable modular wireless sensor network nodes for ambient systems
Comput. Commun.
(2005) - et al.
Wireless sensor network with irrigation valve control
Comput. Electron. Agric.
(2013) - et al.
Wireless sensor network deployment for integrating video-surveillance and data-monitoring in precision agriculture over distributed crops
Comput. Electron. Agric.
(2011) - et al.
Expert system applications in irrigation management: an overview
Comput. Electron. Agric.
(1997) - et al.
A new relative referencing method for crop monitoring using chlorophyll fluorescence
Adv. Space Res.
(2003) - et al.
An autonomous intelligent gateway infrastructure for in-field processing in precision viticulture
Comput. Electron. Agric.
(2011) - et al.
Automatic knowledge acquisition tool for irrigation and fertilization expert systems
Expert Syst. Appl.
(2003) - et al.
Model-based irrigation management using a dynamic parameter adjustment method
Comput. Electron. Agric.
(1996) - et al.
A real-time wireless smart sensor array for scheduling irrigation
Comput. Electron. Agric.
(2008) - et al.
Wireless sensors in agriculture and food industry-recent development and future perspective
Comput. Electron. Agric.
(2006)
Automated canopy temperature estimation via infrared thermography: a first step towards automated plant water stress monitoring
Comput. Electron. Agric.
Precision agriculture – a worldwide overview
Comput. Electron. Agric.
Greenhouse monitoring with wireless sensor network
MF51E High Precision NTC Thermistors for Extremely Accurate Temperature Measurement
Applying machine learning to extract new knowledge in precision agriculture applications
An ontology-driven system architecture for precision agriculture applications
Int. J. Metadata Semant. Ontol.
Proactive agriculture: an integrated framework for developing distributed hybrid systems
Cited by (101)
Cyber-agricultural systems for crop breeding and sustainable production
2024, Trends in Plant ScienceArtificial intelligence and deep learning applications for agriculture
2023, Precision Agriculture: Evolution, Insights and Emerging TrendsMaCOnto: A robust maize crop ontology based on soils, fertilizers and irrigation knowledge
2022, Intelligent Systems with ApplicationsSmart Farming in Europe
2021, Computer Science ReviewEvolutionary layout design synthesis of an autonomous greenhouse using product-related dependencies
2021, Artificial Intelligence for Engineering Design, Analysis and Manufacturing: AIEDAM