Transforming Agri-Food Sustainability with AI and IoT

By Muhammad OsamaReviewed by Susha Cheriyedath, M.Sc.Nov 26 2024

This study, published in Sensors, takes a detailed look at how artificial intelligence (AI)-enabled data infrastructures can support sustainability efforts in the agri-food sector.

Focusing on two use cases—soft-fruit production and brewery operations—the research highlights how AI and the Internet of Things (IoT) can transform the industry by optimizing resource use, improving food quality, and reducing carbon footprints. At the same time, the study sheds light on the challenges of implementing these technologies effectively.

Agri-Food Sector's Transition Towards Net Zero

The global food system is responsible for about one-third of all human-caused greenhouse gas (GHG) emissions, creating a pressing need for the agri-food sector to transition toward net-zero emissions.

In the UK alone, the food and drink industry is a cornerstone of the economy, employing over 430,000 people and contributing approximately £35 billion to the national Gross Value Added (GVA) each year. Achieving net-zero goals in this sector requires sweeping changes across the supply chain, from production to delivery.

Recent advancements in data collection and monitoring have introduced new tools for environmental management in supply chains. Transparency has become a critical element for identifying risks, tracking progress, and addressing sustainability challenges. However, existing tools like sustainability scorecards, self-disclosure systems, and carbon calculators often fall short—they can lack accuracy, require extensive data input, or demand specialized skills to use effectively. Optimizing food production to maximize yields while minimizing resource use and environmental damage remains a priority.

Emerging technologies like AI and IoT show great promise in addressing these challenges, though further research is needed to fully understand their potential and overcome implementation barriers.

Using AI and IoT in Agri-Food Sustainability

This study investigated the feasibility of using AI and IoT to reduce carbon emissions in the agri-food sector through two real-world use cases: strawberry production and brewery operations.

In the strawberry production case, IoT sensors monitored environmental factors both inside and outside polytunnels. This included data on temperature, humidity, light levels, and soil moisture. AI algorithms analyzed these data streams to optimize growing conditions and predict yields, resulting in improved resource efficiency and enhanced food quality.

For brewery operations, sensors tracked parameters such as fermentation temperature, pressure, and dissolved oxygen. These metrics were used to refine brewing processes, improve product consistency, and calculate carbon footprints more accurately. Both use cases demonstrated how real-time data from IoT devices, combined with AI-driven analysis, can significantly enhance efficiency and sustainability.

A user-centered design approach was integral to the study. The researchers collaborated closely with stakeholders, organizing workshops and interactive sessions with soft-fruit growers and brewery operators. This ensured the developed solutions were practical, user-friendly, and aligned with industry needs.

Challenges and Insights from Real-world Deployments

The study identified several challenges in deploying AI and IoT solutions for sustainability in the agri-food sector:

• User Engagement: Active participation from stakeholders was essential for successful implementation. Engaging users early in the process helped ensure practicality and fostered acceptance of new technologies.
• Data Quality: Variability in environmental conditions, inconsistencies in sensor reliability, and differences across production facilities created challenges for data integrity and model performance. For example, in the strawberry use case, variations in soil types, polytunnel setups, and plant varieties significantly impacted model accuracy.
• Model Generalizability: AI models trained on data from one site often performed poorly when applied to others, underscoring the difficulty of creating adaptable solutions for diverse environments.
• Socio-Technical Barriers: High capital costs, the lack of standardization and regulations, and the need for domain-specific expertise were significant obstacles, especially for small and medium-sized enterprises (SMEs), which dominate the agri-food sector.
• Economic Feasibility: SMEs faced particular challenges in adopting these technologies due to resource limitations.
• Ethical Concerns: Issues around data ownership and privacy added complexity. Federated learning was suggested as a way to address these concerns by enabling collaborative model training without compromising sensitive data.

Despite these challenges, the study highlighted the potential of AI-enabled systems to improve sustainability. For example, optimizing resources and processes could not only reduce environmental impacts but also enhance food quality and consistency. The findings underscore the importance of building solutions that address both technical and socio-economic challenges to maximize impact.

Practical Applications

The research provides significant insights for the agri-food sector. AI-enabled decision support systems offer a way to optimize resource use, reduce carbon emissions, and improve food quality. IoT sensors enable real-time monitoring of key metrics, helping producers identify areas for improvement and boost operational efficiency. Additionally, transparent carbon footprint calculators can help businesses track and minimize their environmental impacts. However, to achieve widespread adoption, overcoming barriers such as inconsistent data quality, limited user engagement, and economic feasibility will be essential.

Conclusion and Future Directions

The study concluded that while AI-based data infrastructures have the potential to transform sustainability efforts in the agri-food sector, several challenges remain. These include improving data quality, ensuring stakeholder engagement, addressing model generalizability, and overcoming socio-technical and economic barriers. Ethical issues surrounding data ownership and privacy also need careful consideration.

Looking ahead, the researchers recommend focusing on advanced AI applications, such as semantic data integration, synthetic data generation, and multi-objective optimization systems. Bridging the gap between researchers and industry professionals, raising awareness of AI and IoT technologies, and fostering stronger collaboration among stakeholders will be key to overcoming these challenges. By addressing these issues, the agri-food sector can fully harness the potential of AI and IoT to achieve its sustainability goals.

Journal Reference

Markovic, M.; &.; et al. Embedding AI-Enabled Data Infrastructures for Sustainability in Agri-Food: Soft-Fruit and Brewery Use Case Perspectives. Sensors 2024, 24, 7327. DOI: 10.3390/s24227327, https://www.mdpi.com/1424-8220/24/22/7327

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.