Enhancing Agriculture through IoT: Advancements, Applications and Opportunities

Introduction

With Industry 4.0 providing a paradigm shift toward industrial manufacturing practices, focus needs to be applied to advancing outdated commercial procedures to accommodate a rapidly expanding global population. Agriculture is at a critical standpoint, with climate change affecting the seasons causing unpredictability in precipitation, higher temperatures (Abbass et al., 2022, pp. 42539-42559), and decades of negligent overuse of harmful chemicals destroying topsoil (Tripathi et al., 2020 pp. 25-54). It is also to be considered that not all surfaces are suitable for agriculture with restrictions such as soil quality, climate and homogenous locations already utilised for living (Dhanaraju et al., 2022, pp. 1745). With the global population expected to be 9.75 billion by 2050 (Sands et al., 2022, pp. 2034-2048) and research by Sands et al. (2022) projects that food production, compared to a 2011 baseline, will need to provide a greater nutrient density of 47% from crops by 2050, now more than ever, with the current advancement of communication technologies, such as 5G, and wireless sensor technologies (Kim et al., 2020, pp. 385-400), the need to advance agricultural procedures is necessary to ensure a growing population remains fed.

Commercial systems offered to manage agricultural tasks have previously come at a high price point, with smaller farmers and hobbyists unable to afford the solutions (Garcia et al., 2020, pp. 1042). Due to this, manufacturers have been looking to emerging sensor technologies to implement low-cost irrigation management and smart agriculture monitoring systems. The Internet of Things (IoT) offers a range of benefits to agriculture, primarily due to the ability of IoT's monitoring, controlling & tracking capabilities (Farooq et al., 2020, pp. 319).

The purpose of this literature review is to document the wide array of IoT technologies that are implemented in agriculture to promote productivity and efficiency, increase crop yields to accommodate a rapidly expanding population, and provide examples of current implementations of IoT applications and a discussion of the future opportunities within the domain.

Categorical Review of IoT Applications

For IoT to sufficiently supply the agricultural sector it needs to be scalable, interoperable, distributive, secure and operate with minimal resources to integrate seamlessly throughout a wide range of pre-existing systems (Lombardi et al., 2021), securely providing real-time data to supplement decision-making. Furthermore, a device needs to be robust, to work in harsh environmental conditions, and most importantly affordable (Dhanaraju et al., 2022, pp. 1745) to promote integration into the industry.

IoT provides a framework for capturing data in real-time providing farmers, or automated machinery, assistance regarding agricultural decision-making (Morchid et al., 2024). IoT applications in smart agriculture utilise edge computing to perform real-time calculations, minimising the need to transmit data to a central database.

Based on the needs of a device, uses of IoT in agriculture can be classed into three primary application domains. Research has shown that the primary application domains for IoT in agriculture pertain to Monitoring (70%), Controlling (25%) and Tracking (5%) (Farooq et al., 2020, pp. 319) requiring to monitor and control air, temperature, humidity, illumination, soil, water, fertilisation, disease, pests, stress, location & emissions to maximise plant growth and asset management (Morchid et al., 2024). Each application domain can be utilised to create an overarching management information system to efficiently monitor, control and track an entire agricultural sector.

Application Domains

Monitoring

Monitoring provides real-time data that farmers can use to detect problems early, forecast growth and make informed decisions to completely optimise their operations and resources. This application domain can be split into three sub-domains that each contain IoT applications, applying focus to a general agricultural procedure.

Yield Monitoring

Yield monitoring pertains to maximising the quantifiable amount of crop produced per unit of land, allowing a farmer to optimally allocate resources and enhance overall productivity. Through yield monitoring, farmers can be more agile in their farming approach, addressing any issues early and making necessary rectifications (Farooq et al., 2020, pp. 319).

Through environmental sensors monitoring soil, nutrients, irrigation, and physical factors of the plant themselves (such as colour and size) a farmer can forecast yields prior to harvest at certain development stages of a crop (Dhanaraju et al., 2022, pp. 1745). This predictive approach allows farmers to anticipate harvests, maximising crop production & efficiency. This also assists farmers in being able to make informed management decisions on tasks such as marketing and logistics. Farmers can also determine underperforming units of land and adjust accordingly to supplement production (Morchid et al., 2024).

Climate Monitoring

Climate plays an essential role in crop growth and development, and monitoring the climate can provide valuable data to supplement efficient growing procedures. IoT can be applied to analyse and determine air condition to predict, monitor and react to detrimental effects (Farooq et al., 2020, pp. 319). By measuring humidity, temperature & light exposure through remote sensing technology (Dhanaraju et al., 2022, pp. 1745) a farmer can provide an optimum environment for plant health. This procedure can be controlled more precisely in a greenhouse environment where ideal factors can be more effectively mimicked.

Condition Monitoring

When maintaining crop conditions for effective cultivation, data needs to be monitored that influences the growth, health, nutrient density, and performance of a particular crop. Dhanaraju et al. (2022) explain the framework of an IoT-based monitoring system developed to maintain optimal crop cultivation through environmental monitoring data, with sensors used to monitor soil properties such as texture, absorption rate and water holding capacity. Monitoring systems can also predict conditions that may lead to an outbreak of disease (Kim et al., 2020, pp. 385-400). Current research is focused on image-based deep learning systems using convolutional neural networks for detection and classification (Qazi et al., 2022, pp. 21219-21235).

For livestock, drone technology has been implemented to monitor animal behaviours to determine their welfare, as well as infrared thermal imaging to detect stress and edemas (Akhigbe et al., 2021, pp. 10). Motion sensors have been developed to monitor the condition of pregnant cows, designed to send a SMS to farmers two hours before a cow is calving with over a 95% accuracy rate, reducing calf mortality rate during birth by 7% (Kim et al., 2020, pp. 385-400).

Controlling

Controlling plays an important role in modern agriculture, where precision and accuracy increase efficiency and reduce cost. A major benefit of IoT in controlling agricultural procedures is its ability to track in real-time. Utilised with edge computing, systems can make calculations at the edge rather than having to transfer data to a central hub.

Framework has been developed using reasonably inexpensive devices, such as a Raspberry Pi-3, as an edge computing vision processing unit to detect codling moths in real-time (Qazi et al., 2022, pp. 21219-21235) with a detection rate greater than 90%. This framework can set the foundations for future developments that can control a broader range of pests specific to each farmer's needs.

Fertilisers provide nutrients to supplement crop growth, but under or oversupply can be harmful to soil, plant health and the overall environment (Dhanaraju et al., 2022, pp. 1745). Research has proven fertigation, the process of delivering fertiliser through irrigation systems, in greenhouse environments, where external factors such as climate and soil diversification can be ignored, can not only reduce operating costs and environmental impact by allocating limited resources across crops but also control resources to particular crops during growth periods, with the framework provided by Lin et al. (2020) providing a 3.59% more economical approach compared to hierarchal models tested under the same environment. Further systems have been developed to monitor the growth of fruits and vegetables grown in greenhouses by controlling the internal temperature, humidity & ambient light (Farooq et al., 2020, pp. 319).

Tracking

Tracking in agriculture is achieved with IoT by analysing data in real-time to pass on to the farmer or an autonomous machine. For example, unwanted livestock movements can be tracked, with a farmer receiving a SMS notification. Ilyas & Ahmad (2020) developed a framework that utilises Geofencing and General Packet Radio Service (GPRS) using an ultrasonic sensor network to determine when livestock have moved out of a determined boundary. Additional researchers have put focus towards RFID chips inserted into cattle, to track their movement in real-time as they graze (Farooq et al., 2020, pp. 319).

For autonomous vehicles, John Deere, an industry leader in agricultural machinery, have integrated IoT systems into their equipment that can track and share data with other machinery (Garcia et al., 2020, pp. 1042) such as machine speed and steering angles for simultaneous tractor operation, increasing the efficiency of harvesting, and ensuring full coverage of fertiliser application.

Future Research Opportunities & Emerging Trends

Currently, no researchers have put effort into developing a low-cost, all-encapsulating process, such as a one-size-fits-all solution for farmers of any demographic (Kim et al., 2020, pp. 385-400). Such developments would provide civilians the opportunity to invest in smart agriculture to grow and sustain their own food, adapting to the estimated food crisis (Sands et al., 2022, pp. 2034-2048).

Research suggests there is an opportunity in machine learning using AI implemented to perform predictive analytics to support automated real-time decision-making on a more interoperable solution for pest and disease management. With the development of communication technologies such as 5G (Kim et al., 2020, pp. 385-400), research should point towards creating high-speed edge computing devices.

Conclusion

The applications IoT provide in agriculture consist of three domains: monitoring, controlling, and tracking. Monitoring is the most applied, used to monitor yields, climate and the condition of crops and livestock. Controlling applications are used to optimise agricultural procedures and reduce operational costs. Tracking is generally used for asset management; however recent developments have seen a focus on autonomous machinery.

With the agricultural industry at a critical standpoint, the implementation of IoT into agriculture provides humanity with the opportunity to advance the sector so that the world can remain sustainably fed. With technological advancements in IoT, such as advanced, low-cost, WSNs and 5G increasing the speeds that edge devices can operate, farmers should be looking toward shifting towards Industry 4.0 solutions to increase their crop density and reduce operational costs.

Further research needs to be applied to developing a one-size-fits-all solution that could be incorporated by farmers of any demographic, as well as machine learning using AI to further support real-time decision-making, to help humankind sustainably increase food production.

Reference List

Abbass, K., Qasim, M. Z., Song, H., Murshed, M., Mahmood, H., Younis, I. (2022) A review of the global climate change impacts, adaption, and sustainable mitigation measures. Environmental Science and Pollution Research, 29, 42539-42559. https://link.springer.com/article/10.1007/s11356-022-19718-6

Tripathi, S., Srivastava, P., Devi, R. S., Bhadouria, R. (2020) Chapter 2 – Influence of synthetic fertilizers and pesticides on soil health and soil microbiology. Agrochemicals Detection, Treatment and Remediation, 25-54. https://www.sciencedirect.com/science/article/abs/pii/B9780081030172000027

Dhanaraju, M., Chenniappan, P., Ramalingam, K., Pazhanivelan, S., Kaliaperumal, R. (2022). Smart Farming: Internet of Things (IoT)-Based Sustainable Agriculture. Agriculture 2022, 12(10), 1745. https://www.mdpi.com/2077-0472/12/10/1745

Sands, R. D., Suttles, S. A. (2022). World agricultural baseline scenarios through 2050. Applied Economic Perspectives and Policy, 44(4), 2034-2048. https://onlinelibrary.wiley.com/doi/10.1002/aepp.13309

Garcia, L., Parra, L., Jimenez, J. M., Lloret, J., Lorenz, P. (2020). IoT-Based Smart Irrigation Systems: An Overview on the Recent Trends on Sensors and IoT Systems for Irrigation in Precision Agriculture. Sensors 2020, 20(4), 1042. https://www.mdpi.com/1424-8220/20/4/1042

Farooq, M. S., Riaz, R., Abid, A., Umer, T., Zikira, Y. B. (2020). Role of IoT Technology in Agriculture: A Systematic Literature Review. Electronics 2020, 9(2), 319. https://www.mdpi.com/2079-9292/9/2/319

Morchid, A., Alami, R. E., Raezah, A. A., Sabbar, Y. (2024). Applications of Internet of Things (IoT) and sensors technology to increase food security and agricultural Sustainability: Benefits and challenges. Ain Shams Engineering Journal, 15(3). https://sciencedirect.com/science/article/pii/S2090447923003982

Qazi, S., Khawaja, B. A., Farooq, Q. U., (2022). IoT-Equipped and AI-Enabled Next Generation Smart Agriculture: A Critical Review, Current Challenges and Future Trends. IEEE Access, 10, 21219-21235. https://ieeexplore.ieee.org/abstract/document/9716089

Akhigbe, B. I., Munir, K., Akinade, O., Akabni, L., Oyedele, L. O. (2021). IoT Technologies for Livestock Management: A Review of Present Status, Opportunities, and Future Trends. Big Data and Cognitive Computing, 5(1), 10. https://www.mdpi.com/2504-2289/5/1/10

Kim, W. S., Lee, W. S., Kim, Y. J. (2020). A Review of the Applications of the Internet of Things (IoT) for Agricultural Automation. Journal of Biosystems Engineering, 45, 385-400. https://link.springer.com/article/10.1007/s42853-020-00078-3#Sec6

Lin, N., Wang, X., Zhang, Y., Hu, X., Ruan, J. (2020). Fertigation management for sustainable precision agriculture based on Internet of Things. Journal of Cleaner Production, 277, 124119. https://www.sciencedirect.com/science/article/pii/S0959652620341640?casa_token=5x1kW3o44ksAAAAA:P73TNOG38xc1iZgogD4Czp17wcGHZuJxfb1wZa5hlin3u9XWVDvvMiYWuCt3L_cbQmONyBIQpw

Ilyas, Q. M., Ahmad, M. (2020). Smart Farming: An Enhanced Pursuit of Sustainable Remote Livestock Tracking and Geofencing using IoT and GPRS. Data Collection in Resource-Limited Networks (WSNs, IoT, Sensor Cloud), 2020, Article 6660733. https://www.hindawi.com/journals/wcmc/2020/6660733/

Lombardi, M., Pascale, F., Santaniello, D. (2021) Internet of Things: A General Overview between Architectures, Protocols and Applications. Information 2021, 12(2), 87. https://www.mdpi.com/2078-2489/12/2/87