Encyclopedia
Please note this is an old version of this entry, which may differ significantly from the current revision.
Subjects:
Computer Science, Information Systems
The Internet of Things (IoT) has the potential to revolutionize agriculture by providing real-time data on crop and livestock conditions. As the network becomes denser with a decrease in the network area, there is an increase in network connectivity and a decrease in hop count. In terms of future improvements, incorporating advanced technologies such as machine learning algorithms and edge computing can enhance the performance and scalability of the proposed framework. Additionally, integrating more sophisticated sensor technologies such as drones and cameras can provide a more comprehensive understanding of the farm environment.
- Internet of Things (IoT)
- precision agriculture
- wireless sensor networks (WSNs)
1. Introduction
The integration of the Internet of Things (IoT) within the agriculture sector has advanced significantly, as evidenced by its incorporation into various commercial applications such as monitoring weather conditions, soil moisture, temperature, fertility, and crop growth, as well as weed and pest detection, animal intrusion, irrigation control, and supply chain and food waste management. By deploying IoT sensors, farmers can reduce human effort and increase operational efficiency in monitoring their farms. Furthermore, sensors use communication channels to transmit the obtained status information into consolidated, scalable data repositories [1].
The application of data-processing algorithms on collected data can create opportunities for the development of further innovations and data-driven services, such as decision-making applications that can be combined with IoT actuators to act on physical objects (e.g., turning on a water pump) with minimal or no farmer intervention. However, sensor integration into industrial-scale frameworks requires a large volume of constrained sensor devices, resulting in a self-contained network known as a wireless sensor network (WSN) [2,3,4,5,6,7]. Despite the existence of these technologies and services, they are not always deployed.
2. loT in Agriculture
There has been a growing interest in understanding the best approaches for integrating IoT solutions within the agricultural sector. This interest can be broadly categorized into three stages: (1) Vertical studies that examine the best practices and technical guidelines for using IoT-enabling technologies such as wireless sensor networks (WSNs), gateways, communication platforms, and middleware in production farms [3,11,12]. (2) Horizontal studies that investigate approaches to bridge gaps among the vertical studies by discussing standardization, interoperability issues, large-scale prototyping, and system of systems approach [1]. (3) Business-driven studies that focus on integrating the entire chain of agriculture, wherein social and technical guidelines and frameworks are considered, such as farm-to-fork and traceability for food-chain-related studies [13].
IoT and AI state-of-the-art solutions in agriculture have been discussed in [14,15]. The RPL protocol has been widely investigated in vertical studies focusing on several IoT sectors and applications (e.g., home and building automation, urban environments, and industrial applications). However, few research studies have examined how RPL behaves in other application domains, such as agriculture. For example, the authors in [16] examined the behavior of RPL for precision agriculture using a methodology similar to that used in this work; they proposed an extension model and presented preliminary network performance measurements of RPL. This study further investigates and demonstrates how the RPL behaves in two precision agriculture use cases (i.e., stationary and mobile).
Many attempts have been made to build functional architectures for IoT applications suitable for plant and crop field monitoring and management [13,17,18]. Sensors for collecting information about the environment, soil, and water level are combined with geographical information systems (GISs). The captured parameters are stored in centralized databases using data management software. Web and mobile applications provide farmers with easy access to these databases.
Several studies have proposed using IoT applications for monitoring animals, such as using sensor readings to track their health, behavior, and nutrition. These readings can be transferred to a centralized server for storage and further processing, providing valuable insights to farmers and animal trainers. They can then use this information to optimize their cost and time investments and achieve more value-added products [19,20,21,22,23,24,25,26].
Similarly, various proposed IoT systems have been proposed for monitoring peat forests, such as environmental conditions and potentially managing disasters. These systems often use solar power and communicate with monitoring centers through LoRa networks. Additionally, some studies have proposed using high-resolution satellite imagery to identify changes in forest viability and detect foliar diseases. These systems aim to provide early warning systems for fires, pest control, or deforestation [25,27,28,29].
In livestock farming, a wide range of factors to consider, such as wool and skin, depending on the type and number of farm animals. Studies have proposed solutions such as support systems for disease diagnosis and treatment, non-contact temperature measurement for early disease detection, and IoT monitoring systems for tracking animal behavior and health in large-scale pig farms. These systems can provide animal health recommendations to farmers in rural areas where veterinary access is difficult [30,31,32,33].
This study examined the performance of wireless sensor networks (WSN) in two different agricultural scenarios: olive tree farms with fixed-position sensor nodes and a horse training stable with mobile sensor nodes. The sensors were used to monitor the physical condition of the horses, aiming to improve their health and well-being while also collecting high-precision measurements. The experiments adopted a random waypoint model to simulate the movement of the horses in the second scenario. Our evaluation measures included average power consumption, radio duty cycle, and sensor network connectivity levels. The paper proposed a new approach for simulating moving animals using the COOJA simulator.
Despite the limitations imposed by the constrained nature of WSNs, extending their lifespan remains a critical challenge. Various techniques, such as power optimization algorithms, low-power communications, and reactive sensor networks, have been proposed to address this issue [34,35,36,37]. However, studies that compare the performance of WSNs in fixed and mobile deployment scenarios in the agriculture sector are limited. Furthermore, the implementation of IoT technologies such as WSNs in the agriculture industry has been slower compared to other domains, indicating a need for further research in this area to promote wider and faster diffusion of IoT in the sector [38,39,40,41,42].
IoT integration within the agriculture sector has matured, as evidenced by its extension into several commercial applications. There has been a growing interest in understanding the best approaches for integrating IoT solutions within the agricultural sector, which can be broadly categorized into three stages: (1) vertical studies that examine the best practices and technical guidelines for using IoT-enabling technologies such as wireless sensor networks (WSNs); (2) horizontal studies that investigate approaches to bridge gaps among the vertical studies; and (3) business-driven studies that focus on integrating the entire chain of agriculture. This study examined the performance of wireless sensor networks (WSN) in two different agricultural scenarios: olive tree farms with fixed-position sensor nodes and a horse training stable with mobile sensor nodes.
The state-of-the-art precision agriculture systems involve the use of advanced technologies such as sensors, GPS, robotics, and data analytics to optimize crop production and reduce costs. Remote sensing and ground-based sensor systems are commonly used to monitor crop health, soil moisture, and other environmental factors. Variable rate application systems use this data to adjust inputs such as fertilizers, pesticides, and water according to the specific needs of different parts of a field. Autonomous agricultural equipment, such as drones and robots, are also being developed and used to automate planting, harvesting, and other tasks. In addition to these technologies, precision agriculture systems are also integrating machine learning and AI algorithms to analyze large volumes of data and make predictions about crop health and yield. This allows farmers to make data-driven decisions and optimize their operations for maximum efficiency and profitability. The research problems in precision agriculture systems primarily involve developing more accurate and reliable sensors, improving data analytics and modeling techniques, and addressing issues related to data privacy and security. Additionally, there is ongoing research in developing more advanced autonomous equipment and integrating multiple systems for a more comprehensive approach to precision agriculture. Overall, precision agriculture is a rapidly evolving field, with new technologies and techniques constantly emerging. The state-of-the-art is driven by a focus on improving efficiency, reducing waste, and increasing yields through the use of advanced technologies and data-driven decision making.
3. Precision Agriculture Applications
For example, an application such as horse monitoring is essential for several reasons, such as horses being prone to sudden illnesses such as colic, which can be fatal. Therefore, monitoring horses remotely and constantly is essential to be aware of their condition and function as quickly as possible in an emergency. For this task, WSNs play a decisive role, allowing owners and/or breeders to monitor the vital signs and anxiety of the horses or the stable environmental conditions that can influence the horses’ comfort.
The utilization of WSN technology for farm animal monitoring has received considerable research attention. Research has focused on monitoring the behavioral preferences of cattle using a combination of GPS, satellite imagery, and WSNs. Wireless sensor technology has been used for horses to analyze gait (to identify lameness) and detect foaling time. Monitoring cows and pasture time on a new grass strip using Zigbee technology has already been addressed [47].
IoT systems for horse management, which is a WSN-based system that provides a solution for equine real-time monitoring, allows farmers to access and evaluate vital health signs and behavioral and environmental measurements remotely while being connected to the Internet. In addition to monitoring, the system comprises additional functionalities (i.e., registering and alerting and remote video streaming). Many sensors have been developed in recent years for such horse stables; these sensors can be used to monitor various conditions. The following are some mobility-support sensors that can be used for horse monitoring: (1) motion sensors; (2) blood pressure sensors; (3) heartbeat sensors; (4) colic sensors [48,49].
A commercially available sensor board can be used to use these sensors. For example, some boards support up to 16 sensor plugs on the same board, which can help create a single node that can measure many physical parameters [50,51,52,53].
A second practical example is IoT for olive trees, which integrates IoT devices to manage irrigation, fertilization, and pest control on plant structures. This system helps to detect the disease in its early stages and the risk of the disease spreading in the field by determining the right amount and time of additional olive tree irrigation and tree changes caused by agricultural pests. The system relies on temperature and humidity sensors on the ground and cameras that take pictures of the trees. The data generated by these devices are sent to a database server through web services and analyzed. This system sends instructions to decide, such as the amount of irrigation and fertilization, the time to water, and the precise infection treatment.
For example, Libelium’s Waspmote Plug & Sense! Sensor Platform is a commercially available sensor board used for best control in an olive tree farm. For Example, Libelium’s boards support up to 16 sensor branches on a single board so that a node can measure multiple parameters [29].
This entry is adapted from the peer-reviewed paper 10.3390/info14040205
This entry is offline, you can click here to edit this entry!
