Artificial intelligence for enhancing supply chain management in agribusiness

Abstract

The global agribusiness industry faces increasing complexity and challenges in supply chain management (SCM). These challenges arise from volatile market demands, environmental unpredictability and the necessity to ensure sustainability. Artificial Intelligence (AI) has emerged as a transformative technology to enhance SCM through advanced analytics, real-time decision-making and optimization. This review explores recent advancements in AI applications for agribusiness SCM, highlighting their theoretical and conceptual foundations. The discussion emphasizes AI's role in demand forecasting, logistics optimization, risk mitigation and sustainability. Policy implications and recommendations for integrating AI into agribusiness SCM conclude the paper, offering pathways for maximizing its potential.

Keywords: AI, Agribusiness, Supply chain, Management

INTRODUCTION

The agribusiness sector is a cornerstone of global economic and social systems, underpinning the provision of food and raw materials essential for human sustenance and industrial applications. It encompasses a diverse range of activities, including agricultural production, processing, marketing and distribution, all of which are interlinked through supply chain management (SCM). Effective SCM is vital for ensuring that agricultural goods are delivered efficiently, cost-effectively and sustainably from producers to consumers. However, the sector faces mounting challenges driven by population growth, climate change and economic uncertainties, which necessitate innovative and adaptive solutions.

Key Challenges in Agribusiness SCM

The growing global population, projected to reach nearly 10 billion by 2050, intensifies demand for food and agricultural products. This surge places immense pressure on agribusiness supply chains to scale up production while maintaining affordability and quality (FAO, 2021). Concurrently, climate change disrupts traditional agricultural practices through erratic weather patterns, extreme events and resource constraints, such as water scarcity and land degradation. These environmental stressors introduce uncertainties that complicate supply chain operations, from production planning to logistics.

Economic volatility further compounds these challenges, as global trade dynamics, fluctuating commodity prices and geopolitical tensions impact supply chain stability (Trienekens et al., 2021). The COVID-19 pandemic underscored the vulnerability of agribusiness supply chains, revealing critical gaps in resilience and adaptability during crises. These factors collectively underscore the urgency of adopting innovative approaches to enhance supply chain performance.

The Role of AI in Transforming Agribusiness SCM

Artificial Intelligence (AI) has emerged as a transformative technology with the potential to address the multifaceted challenges facing agribusiness SCM. By leveraging advanced computational models, AI can process vast amounts of data to generate actionable insights, optimize operations and enable real-time decision-making. Several key technologies underpin AI’s applications in agribusiness SCM:

• Machine Learning (ML): ML algorithms analyze historical data to identify patterns, forecast demand and optimize resource allocation. For instance, predictive analytics powered by ML has improved yield estimation and market demand predictions, reducing mismatches between supply and demand (Choudhury et al., 2022).

• Computer Vision: Computer vision technologies are used to monitor crop health, detect pests and assess quality in agricultural products. This capability enhances precision agriculture and ensures that only high-quality produce enters the supply chain (Kamilaris and Prenafeta-Boldú, 2018).

• Natural Language Processing (NLP): NLP enables automated communication within the supply chain, facilitating seamless coordination among stakeholders. Chatbots and AI-driven platforms provide real-time updates on inventory and logistics, streamlining operations.

• Robotics and Automation: Robotics is increasingly employed in tasks such as harvesting, sorting and packaging. Automation reduces labor costs and enhances efficiency, particularly in regions facing workforce shortages.

• Internet of Things (IoT) and Sensors: IoT-enabled devices and sensors collect real-time data on environmental conditions, storage temperatures and transportation routes. Integrating this data with AI systems allows for dynamic supply chain adjustments to mitigate risks (Verdouw et al., 2021).

Potential Benefits of AI in Agribusiness SCM

The adoption of AI in agribusiness SCM offers numerous benefits that address key inefficiencies and vulnerabilities:

• Efficiency Improvement: AI optimizes resource use across the supply chain, reducing waste and minimizing costs. For example, ML-based inventory management systems predict optimal stock levels, preventing overproduction or shortages (Ghosal & Zhang, 2022).

• Risk Mitigation: Predictive models powered by AI forecast potential disruptions, such as weather-induced delays or supply bottlenecks. Early warning systems enable proactive risk management, enhancing supply chain resilience.

• Sustainability: By enabling precision agriculture, AI reduces the overuse of resources like water, fertilizers and pesticides. Furthermore, blockchain-integrated AI systems enhance traceability, promoting ethical and sustainable sourcing practices (Tian et al., 2020).

• Enhanced Decision-Making: AI systems provide supply chain managers with real-time insights and prescriptive analytics, empowering data-driven decisions that enhance overall performance.

This paper aims to provide a comprehensive review of recent advancements in AI applications for agribusiness SCM, with a focus on the theoretical and conceptual frameworks underpinning these innovations. The paper is structured as follows:

• Theoretical Framework: Discusses the academic and conceptual foundations of AI in SCM, including systems theory, decision theory and optimization models.

• Conceptual Framework: Explores the practical integration of AI technologies in key SCM functions, such as demand forecasting, inventory management and logistics optimization.

Results and Discussion: Highlights empirical evidence and case studies demonstrating the impact of AI on agribusiness SCM, including benefits, challenges and future opportunities.

• Conclusion and Policy Implications: Provides actionable recommendations for stakeholders and policymakers to maximize the potential of AI in agribusiness SCM while addressing barriers to adoption.

THEORETICAL FRAMEWORK

The theoretical underpinnings of AI applications in supply chain management (SCM) are grounded in interdisciplinary approaches, combining insights from operations research, computer science and agricultural economics. These theoretical foundations provide the structure for understanding and applying AI technologies to complex supply chain networks.

Systems Theory

Systems theory serves as a foundational framework for conceptualizing SCM as a dynamic and interconnected system. In the context of agribusiness, this theory highlights the interdependence of production, processing and distribution components. AI’s role in systems theory is to optimize the interactions between these elements, ensuring a smooth flow of information, goods and resources. For example, dynamic AI algorithms like digital twins replicate entire supply chain networks to simulate scenarios and predict bottlenecks (Ivanov and Dolgui, 2021). Such applications enable proactive adjustments to disruptions, improving resilience and agility.

Decision Theory

Decision theory underpins AI’s capacity to manage uncertainty and support optimal decision-making within agribusiness SCM. Bayesian networks are widely employed to model probabilistic dependencies among supply chain variables, allowing for robust decision-making under uncertain conditions (Zhao et al., 2022). Reinforcement learning further enhances this process by enabling AI systems to adaptively learn optimal strategies through trial and error in dynamic environments (Sutton & Barto, 2018). For instance, reinforcement learning has been applied to real-time logistics routing, significantly reducing transportation costs and delivery times (Naz et al., 2021).

Optimization Theory

Optimization theory is a cornerstone of AI’s application in SCM, enabling the design of efficient algorithms for resource allocation, logistics planning and inventory management. Techniques such as genetic algorithms and artificial neural networks are particularly effective in solving non-linear and complex optimization problems. In agribusiness SCM, these algorithms have been used to minimize transportation distances and optimize cold chain logistics for perishable goods, ensuring freshness and reducing waste (Deb et al., 2022). Moreover, metaheuristic approaches like particle swarm optimization have proven effective in handling large-scale optimization problems in agribusiness (Yang et al., 2022).

Sustainability Theory

Sustainability theory aligns AI applications with environmental and social goals, emphasizing resource efficiency, waste reduction and ethical practices. Precision agriculture, powered by AI, exemplifies sustainability in action by reducing the overuse of water, fertilizers and pesticides, while simultaneously boosting productivity (Wolfert et al., 2017). Additionally, blockchain-integrated AI systems enhance supply chain transparency, enabling traceability and accountability for sustainable sourcing practices (Kamilaris et al., 2019). Such applications address the growing demand for environmentally and socially responsible agribusiness practices.

CONCEPTUAL FRAMEWORK

The conceptual framework guiding AI integration into SCM processes comprises a synthesis of enabling technologies, core supply chain functions and desired outcomes.

AI Technologies

• Machine Learning (ML): ML has transformed demand forecasting by analyzing historical trends, market dynamics and external variables such as weather patterns. Recent studies have demonstrated that ensemble ML models improve the accuracy of yield predictions by combining diverse datasets (Choudhary et al., 2023).

• Robotics and Automation: Robotics systems in agribusiness SCM are used for tasks like automated sorting and grading of produce, enhancing efficiency and consistency. Autonomous drones equipped with computer vision have also been employed for crop monitoring and spraying, significantly reducing labor dependency (Nguyen et al., 2022).

• Computer Vision: Computer vision technologies, coupled with AI algorithms, have revolutionized quality control processes. For example, advanced image recognition systems detect defects in fruits and vegetables during packaging, ensuring high-quality products enter the supply chain (Patel et al., 2023).

• IoT and Sensors: IoT devices and sensors collect real-time data on environmental conditions, inventory levels and transportation logistics. These data streams are integrated with AI models to provide actionable insights. For instance, IoT-enabled smart bins monitor storage conditions and alert managers to potential spoilage risks (Verdouw et al., 2021).

SCM Functions

• Demand Forecasting: AI models analyze historical sales data and external factors such as socioeconomic trends to predict demand accurately. This capability is critical in agribusiness, where seasonality and perishability influence market dynamics (Alam et al., 2022).

• Production Optimization: Precision agriculture, powered by AI, optimizes resource use while maximizing yields. Farmers utilize AI-driven decision support systems to determine the optimal planting schedule, irrigation levels and fertilizer application (Jones et al., 2021).

• Inventory Management: AI algorithms predict inventory levels required to minimize stockouts and reduce carrying costs. Cloud-based AI systems dynamically adjust inventory levels based on real-time demand fluctuations, improving responsiveness (Smith and Zhang, 2023).

Logistics and Distribution: Logistics optimization is a critical area where AI has demonstrated significant benefits. AI-powered route optimization algorithms minimize transportation distances, fuel consumption and delivery delays, contributing to cost savings and sustainability (Deb et al., 2022).

Outcomes

The integration of AI technologies into agribusiness SCM yields transformative outcomes:

• Efficiency: AI-driven automation and optimization reduce processing times, improve resource utilization and streamline operations, leading to cost savings and productivity gains.

• Conceptual Framework: Step-by-Step Outline

The conceptual framework for applying Artificial Intelligence (AI) in agribusiness Supply Chain Management (SCM) is structured around three core elements: enabling technologies, SCM functions and outcomes. These components are interlinked to provide a comprehensive understanding of how AI can transform agribusiness SCM. Below is a step-by-step outline:

Enabling Technologies

AI technologies form the foundation of the conceptual framework, providing tools and methodologies to address SCM challenges.

• Machine Learning (ML)

Functionality: Analyze historical data and identify patterns for predictive and prescriptive analytics.

Applications: Demand forecasting, yield prediction and supply-demand alignment.

Example: Using ML to optimize resource allocation based on real-time data trends.

• Robotics and Automation

Functionality: Perform repetitive tasks with precision and efficiency.

Applications: Harvesting, sorting, packaging and quality control.

Example: Robotic systems automating the sorting of fruits by size and quality.

• Computer Vision

Functionality: Analyze visual data for decision-making.

Applications: Crop health monitoring, detecting defects in produce and ensuring quality control.

Example: Drones equipped with computer vision identifying pest-infested areas.

• Internet of Things (IoT) and Sensors

Functionality: Collect real-time data on environmental and logistical parameters.

Applications: Temperature monitoring, inventory tracking and logistics optimization.

Example: IoT devices monitoring the cold chain logistics of perishable goods.

• Blockchain Technology (Supporting Element)

Functionality: Enhance traceability, transparency and data security across supply chains.

Applications: Ensuring authenticity and sustainability in product sourcing.

Example: Tracking produce from farm to fork using blockchain for transparency.

SCM Functions

AI technologies are applied across key functions of SCM to address inefficiencies and optimize operations.

• Demand Forecasting

Objective: Predict consumer demand to align production and distribution.

AI Contribution: Analyze historical sales data, market trends and external factors like weather.

Example: Predicting peak demand for seasonal fruits to prevent overproduction.

• Production Optimization

Objective: Maximize yield while minimizing resource usage.

AI Contribution: Precision agriculture through AI models.

Example: Recommending optimal fertilizer usage based on soil data and crop type.

• Inventory Management

Objective: Maintain optimal stock levels to reduce costs and prevent shortages.

AI Contribution: Predict inventory needs using demand patterns and production schedules.

Example: Dynamic stock level adjustments based on real-time demand fluctuations.

• Logistics and Distribution

Objective: Optimize transportation routes and minimize delivery times.

AI Contribution: Real-time routing algorithms and fleet management systems.

Example: Dynamic re-routing of delivery trucks to avoid traffic congestion.

• Risk Mitigation

Objective: Identify and address potential risks in the supply chain.

AI Contribution: Predict weather disruptions and monitor pest outbreaks.

Example: AI models providing early warnings for extreme weather events.

Outcomes

The application of AI in SCM yields transformative outcomes that align with the goals of agribusiness stakeholders.

• Efficiency Improvement

Impact: Reduced processing times, cost savings and enhanced productivity.

Example: Automating quality checks to accelerate packaging processes.

• Sustainability

Impact: Reduced environmental footprint through optimized resource use.

Example: Minimizing water and pesticide use in farming operations.

• Risk Reduction

Impact: Enhanced supply chain resilience against disruptions.

Example: Proactive measures to mitigate the impact of droughts on crop yields.

• Improved Transparency

Impact: Greater trust among consumers and stakeholders.

Example: Blockchain technology ensuring traceability of organic produce.

Visualization of the Conceptual Framework

Below is the connection of the framework:

• Enabling Technologies → Serve as the tools for transformation.

• SCM Functions → Represent operational areas where AI is applied.

• Outcomes → Reflect the measurable benefits resulting from AI integration.

Flowchart Representation

• Step 1: Technologies → Machine Learning → Robotics and Automation → IoT and Sensors → Computer Vision

• Step 2: Functions → Demand Forecasting → Inventory Management → Logistics Optimization

Step 3: Outcomes → Efficiency → Sustainability → Risk Mitigation

RESEARCH METHODOLOGY

The present study adopted a desk review: collection of journals, textbooks, edited books, monographs, conference proceedings, newspapers, internet sources, etc. to generate valid data. Furthermore, using the collected data were systematically synthesized for the purpose of gaining insightful details on the research topic.

RESULTS AND DISCUSSION

Artificial Intelligence (AI) has revolutionized various aspects of supply chain management (SCM) in agribusiness, addressing inefficiencies, risks and environmental challenges while enhancing overall performance. This section delves into the specific outcomes and implications of AI in demand forecasting, logistics and transportation optimization, risk management and sustainability, along with an analysis of the challenges and limitations hindering its adoption.

AI in Demand Forecasting

Demand forecasting in agribusiness SCM is a critical function, directly influencing production planning, inventory management and distribution strategies. Recent advancements in AI have significantly improved the accuracy and reliability of demand predictions. Machine learning (ML) algorithms analyze historical sales data, market trends, weather patterns and consumer behavior to forecast demand with remarkable precision.

For instance, Choudhury et al. (2022) demonstrated that ensemble learning methods combining multiple ML models outperform traditional forecasting techniques in predicting crop yields. These algorithms consider external factors such as climate variability and economic conditions, enabling agribusinesses to align supply with anticipated demand. AI-driven demand forecasting has also been employed to optimize market pricing strategies, minimizing mismatches between supply and demand (Smith and Zhang, 2023).

Moreover, AI has proven effective in predicting demand for perishable goods. Deep learning models, such as recurrent neural networks (RNNs) and long short-term memory (LSTM) networks, are particularly adept at identifying temporal patterns in demand data. This capability ensures that production and distribution schedules are aligned with market requirements, reducing waste and enhancing profitability (Alam et al., 2022).

Logistics and Transportation Optimization

Efficient logistics and transportation systems are vital for agribusiness SCM, particularly given the perishable nature of many agricultural products. AI-powered solutions have emerged as game-changers, enabling dynamic routing, fleet management and real-time tracking.

Dynamic routing algorithms use data from GPS, traffic systems and weather forecasts to optimize delivery routes, reducing transit times and fuel consumption. Case studies from logistics providers reveal that implementing AI-driven fleet management systems has resulted in cost savings of up to 20% and a 15% reduction in carbon emissions (Deb et al., 2022).

AI also enhances cold chain logistics, critical for preserving the quality of temperature-sensitive goods. IoT-enabled sensors and predictive analytics monitor storage conditions and pre-emptively address potential disruptions. For example, Verdouw et al. (2021) highlighted that integrating AI with IoT systems has reduced spoilage rates in fresh produce supply chains by up to 30%. These advancements ensure timely deliveries and improve overall customer satisfaction.

Risk Management

Agribusiness supply chains are inherently exposed to risks, including weather variability, pest outbreaks and market fluctuations. AI tools are increasingly being utilized to identify, assess and mitigate these risks.

Predictive analytics models leverage historical and real-time weather data to forecast climate-related risks. These models enable farmers to adjust their planting schedules and irrigation strategies, reducing crop losses. For example, reinforcement learning algorithms have been applied to optimize water usage during droughts, improving resilience against adverse weather conditions (Jones et al., 2021).

AI is also employed to combat pest and disease outbreaks. Computer vision and ML algorithms analyze images captured by drones or field sensors to detect early signs of infestations. By identifying affected areas promptly, these tools enable targeted interventions, minimizing damage and pesticide usage (Nguyen et al., 2022).

Market risks, such as price volatility and supply chain disruptions, are addressed through AI-based simulations and scenario analysis. For instance, Monte Carlo simulations integrated with ML models provide agribusinesses with insights into potential market fluctuations, facilitating informed decision-making (Zhao et al., 2022).

Sustainability and Environmental Impact

Sustainability is a growing priority for agribusiness SCM, driven by consumer demand for environmentally responsible practices and regulatory pressures. AI-driven solutions play a pivotal role in promoting sustainable supply chain operations.

Precision agriculture, powered by AI, enhances resource efficiency by optimizing the use of water, fertilizers and pesticides. For example, ML algorithms analyze soil data, weather conditions and crop health to recommend precise application rates, reducing resource wastage and environmental harm (Kamilaris and Prenafeta-Boldú, 2018).

Blockchain-integrated AI systems have emerged as powerful tools for enhancing transparency and traceability in agribusiness supply chains. These systems track the movement of goods from farm to consumer, ensuring compliance with sustainability standards and fostering consumer trust (Tian et al., 2020). Additionally, AI-powered carbon accounting tools help agribusinesses measure and reduce their greenhouse gas emissions, contributing to global climate goals.

Challenges and Limitations

Despite its transformative potential, AI adoption in agribusiness SCM faces significant challenges that must be addressed to maximize its benefits:

• High Implementation Costs: The initial investment required for AI technologies, including hardware, software and training, is a major barrier for small and medium-sized enterprises (SMEs) in the agribusiness sector. Studies indicate that high costs deter adoption, particularly in developing regions (Trienekens et al., 2021).

• Technical Expertise: Implementing and maintaining AI systems requires specialized knowledge in data science, programming and supply chain management. The lack of skilled professionals in rural and agricultural areas limits the scalability of AI solutions (Ghosal and Zhang, 2022).

• Data Privacy and Security: The integration of AI with IoT and blockchain systems raises concerns about data privacy and cybersecurity. Ensuring secure data exchange while maintaining transparency is a complex challenge (Verdouw et al., 2021).

• Infrastructure Gaps: In many regions, particularly in developing countries, inadequate digital infrastructure hinders the deployment of AI technologies. Reliable internet connectivity, access to sensors and data storage facilities are often lacking (Alam et al., 2022).

• Resistance to Change: Cultural and organizational resistance to adopting new technologies is a common challenge. Farmers and supply chain stakeholders may be hesitant to adopt AI solutions due to perceived complexity or skepticism about their benefits (Jones et al., 2021).

CONCLUSION

The integration of Artificial Intelligence (AI) into supply chain management (SCM) in agribusiness represents a transformative opportunity to address longstanding inefficiencies, enhance sustainability and improve resilience across the sector. AI technologies, such as machine learning, robotics, IoT and blockchain, offer innovative solutions to challenges such as demand forecasting, logistics optimization and risk management. The widespread adoption of these technologies promises to revolutionize agribusiness SCM by reducing waste, optimizing resource use and enabling more sustainable practices.

However, the full potential of AI cannot be realized without addressing critical barriers such as high implementation costs, lack of technical expertise and infrastructural gaps. A collaborative effort involving policymakers, industry leaders and research institutions is essential to overcome these obstacles and drive widespread adoption. The following policy implications and recommendations provide a roadmap for maximizing AI’s impact on agribusiness SCM.

POLICY IMPLICATIONS

• Infrastructure Development: The successful deployment of AI in agribusiness SCM hinges on robust digital infrastructure. Policymakers must prioritize investments in rural broadband connectivity, data storage facilities and IoT sensor networks. For instance, enhanced internet connectivity in rural areas enables real-time data collection and communication between stakeholders. Public-private partnerships can play a pivotal role in accelerating infrastructure development, ensuring that smallholder farmers and agribusinesses in remote regions are not left behind.

• Capacity Building: The lack of technical expertise among farmers, supply chain managers and other stakeholders is a significant barrier to AI adoption. Capacity-building programs must be implemented to equip individuals with the necessary skills to deploy and manage AI technologies effectively. Governments and educational institutions should collaborate to design training modules that focus on AI applications in agribusiness SCM. For example, vocational training centers and online courses can be established to provide hands-on experience with AI tools such as predictive analytics software, automated robotics and blockchain systems.

• Incentives for Adoption: High implementation costs deter many agribusinesses, particularly small and medium-sized enterprises (SMEs), from adopting AI technologies. Policymakers can address this challenge by offering financial incentives such as subsidies, low-interest loans and tax benefits. For instance, subsidies can be provided to farmers for purchasing IoT devices and AI-powered machinery, while tax deductions can be offered to companies investing in AI-driven supply chain solutions. These incentives not only lower the financial barrier but also encourage innovation and experimentation with AI technologies in agribusiness.

• Regulatory Frameworks: The integration of AI into SCM raises concerns about data privacy, cyber-security and ethical usage. Policymakers must establish clear regulatory frameworks to address these issues and ensure the responsible deployment of AI technologies. For example, data protection laws should mandate secure storage and sharing of sensitive information, while guidelines on AI ethics should prevent misuse, such as algorithmic bias or exploitation of small-scale farmers. Additionally, certification standards for AI-powered systems can be introduced to ensure their reliability and compliance with sustainability goals.

RECOMMENDATIONS

• Promote Multi-Stakeholder Collaboration: Collaboration between governments, private sector players, research institutions and non-governmental organizations is critical for scaling AI adoption in agribusiness SCM. Public-private partnerships can facilitate the development of shared platforms for data exchange, research and innovation. For example, consortia of agribusinesses, AI developers and agricultural extension services can work together to create AI solutions tailored to local challenges.

• Encourage Open Data Platforms: The availability of high-quality data is crucial for the effective functioning of AI models. Governments and international organizations should promote open data platforms that aggregate agricultural data from diverse sources, including weather agencies, market reports and farm-level records. These platforms can serve as a valuable resource for AI-driven decision-making, enabling transparency and collaboration among stakeholders.

• Focus on Smallholder Inclusion: Smallholder farmers form the backbone of agribusiness in many developing countries but often lack access to advanced technologies. Policies should be designed to ensure that AI solutions are affordable, user-friendly and accessible to small-scale farmers. For instance, mobile-based AI applications can provide farmers with real-time insights on weather, pest outbreaks and market prices, enabling them to make informed decisions.

• Invest in Research and Development (R&D): Governments and private sector entities should increase funding for R&D in AI applications for agribusiness SCM. Research initiatives can explore innovative solutions such as AI-powered supply chain simulations, autonomous vehicles for transportation and advanced analytics for sustainability monitoring. Collaborative R&D projects involving academia, industry and policymakers can drive technological advancements while ensuring practical relevance.

• Monitor and Evaluate Implementation: Regular monitoring and evaluation of AI initiatives are essential to measure their impact and identify areas for improvement. Policymakers should establish metrics for assessing the performance of AI systems in terms of efficiency, sustainability and resilience. Periodic reviews can help refine policies and ensure alignment with evolving challenges and opportunities in agribusiness SCM.

• Leverage International Cooperation: Global challenges such as food security and climate change require coordinated efforts. International cooperation can facilitate the sharing of best practices, transfer of technology and capacity-building efforts. For example, international organizations such as the Food and Agriculture Organization (FAO) and the World Bank can support developing countries in adopting AI technologies through funding, technical assistance and policy guidance.

REFERENCES

Alam M., Uddin M.S., Hossain S. (2022). AI applications in perishable goods supply chains: Challenges and opportunities. Journal of Agricultural Economics, 55: 220-238.

Choudhary S., Joshi R., Banerjee S. (2023). Predictive analytics in agriculture: Challenges and opportunities. Journal of Agricultural Systems, 14: 245-259.

Deb A., Roy S., Basu P. (2022). Optimizing cold chain logistics with AI. International Journal of Logistics Management, 19: 55-72.

FAO (2021). The Future of Food and Agriculture: Trends and Challenges. Food and Agriculture Organization of the United Nations.

Ghosal S., Zhang A. (2022). Machine learning applications in inventory management for agribusiness. International Journal of Supply Chain Management, 10: 180-195.

Ivanov D., Dolgui A. (2021). Digital supply chain twins: Managing the ripple effect, resilience and disruption risks by data-driven optimization, simulation and visibility. Transportation Research Part E: Logistics and Transportation Review, 136: 101922.

Jones E., Wilson R., Patel K. (2021). Reinforcement learning for climate resilience in agriculture. Computers and Electronics in Agriculture, 120: 75-88.

Kamilaris A., Prenafeta-Boldú F.X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147: 70-90.

Kamilaris A., Fonts A., Prenafeta-Boldú F.X. (2019). The rise of blockchain technology in agriculture and food supply chains. Trends in Food Science & Technology, 91: 640–652.

Nguyen H., Tran P., Le D. (2022). AI and robotics in agribusiness supply chains. Journal of Food Supply Chain Research, 11: 135-150.

Patel S., Gupta V., Kumar A. (2023). Advances in AI-based quality control for agricultural products. Agricultural Engineering International: CIGR Journal, 24: 134-144.

Smith D., Zhang Q. (2023). AI in agribusiness: Bridging the supply-demand gap. Supply Chain Review, 19: 85–95.

Sutton R.S., Barto A.G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.

Tian F., Zhang J., Li W. (2020). Blockchain and AI in sustainable supply chains. Journal of Sustainable Development Studies, 14: 65-83.

Trienekens J., van der Vorst J., Bloemhof J. (2021). Challenges in global agrifood supply chains. Agricultural Economics, 52: 445-460.

Verdouw C.N., Wolfert J., Beers G., Sundmaeker H. (2021). Internet of things in smart agrifood supply chains. International Journal of Food Supply Chain Management, 5: 67-89.

Wolfert S., Ge L., Verdouw C., Bogaardt M.-J. (2017). Big data in smart farming: A review. Agricultural Systems, 153: 69–80.

Yang Y., Sun Q., Li W. (2022). A metaheuristic framework for large-scale supply chain optimization. Computers and Industrial Engineering, 162: 107746.

Zhao L., Chen X., Zhu Y. (2022). Bayesian networks for risk management in agribusiness SCM. Risk Analysis and Mitigation in Agriculture, 7: 105-122.