Artificial Intelligence for climate-smart agriculture: A systematic review of applications, sustainability impacts, and future directions

Introduction

Agriculture is confronting unprecedented challenges due to climate change, population growth, natural resource degradation, and increasing food demand. The global population is expected to approach 10 billion by 2050, significantly intensifying pressure on food production systems and natural resources (FAO, 2023) [3] . Simultaneously, agriculture remains highly vulnerable to rising temperatures, irregular precipitation patterns, droughts, floods, and emerging pest and disease outbreaks (Challinor et al., 2014) [1] . These climatic disturbances threaten crop productivity, soil fertility, water availability, and overall food security, particularly in developing countries where farming systems are highly climate-sensitive. In addition, agriculture contributes substantially to greenhouse gas emissions and freshwater consumption, emphasizing the urgent need for sustainable and resilient production systems (IPCC, 2022; Zhao et al., 2017) [4,8] . Climate-Smart Agriculture (CSA) has emerged as an integrated approach to address these interconnected challenges by enhancing productivity, strengthening climate resilience, and reducing environmental impacts (FAO, 2010) [2] . Practices such as precision irrigation, conservation agriculture, integrated nutrient management, and climate-resilient cropping systems have demonstrated considerable potential for sustainable agricultural development (Smith et al., 2008) [7] . However, the effective implementation of CSA requires accurate monitoring, predictive analysis, and data-driven decision-making systems. Recent advancements in Artificial Intelligence (AI) have created transformative opportunities [1] ; IPCC (2022) [4] Mitigation Conservation [17,20] . These technologies enable data-driven decision-making for irrigation management, disease detection, crop monitoring, yield prediction, and supply chain optimization.

Machine Learning algorithms are widely used for predictive analysis, crop yield forecasting, soil fertility assessment, and pest detection. Techniques such as Random Forest, Support Vector Machines, and Artificial Neural Networks help optimize agricultural inputs and improve farm management practices (Liakos et al., 2018) [6] . Deep Learning models, particularly Convolutional Neural Networks (CNNs), have shown high accuracy in image-based disease detection, weed identification, and crop monitoring using drone and satellite imagery (Mohanty et al., 2016) [21] . The Internet of Things (IoT) enables real-time monitoring of soil moisture, temperature, humidity, and crop health through interconnected sensors and smart devices (Ayaz et al., 2019) [16] . Similarly, robotics and automation technologies, including autonomous tractors, drones, and robotic harvesters, reduce labor dependency and enhance operational precision in farming systems (Duckett et al., 2018) [19] . Big data analytics and cloud computing further strengthen smart agriculture by integrating large agricultural datasets for predictive modeling, climate forecasting, and decision support systems (Coble et al., 2018) [18] . Overall, AI-driven technologies are significantly improving agricultural efficiency, sustainability, and resilience, making them essential components of future climate-smart food systems.

[6] ; Russell & Norvig (2020)

Deep Learning (DL)

A subset of ML using multi-layered neural networks for complex image recognition, pattern detection, and time-series forecasting in crop systems.

CNN, RNN, LSTM LeCun et al. (2015); Kamilaris

& Prenafeta-Boldú (2018) [5] Internet of Things (IoT) Network of interconnected sensors and smart devices that collect and exchange real-time agricultural data through internet-based communication systems.

Soil sensors, wearable devices, smart meters Ayaz et al. (2019) [16] ; Wolfert et al. (2017) [24] Remote [25] Big Data Analytics

Processing and analysis of large, heterogeneous agricultural datasets from sensors, satellites, and machinery to extract actionable management insights.

Predictive analytics, cloud storage, data mining Coble et al. (2018) [18] ; Bhat & Huang (2021) [17] Robotics & Automation AI-guided autonomous machines that perform precise, repetitive farm tasks including planting, weeding, spraying, and harvesting without human intervention.

Agribots, autonomous tractors, robotic harvesters Duckett et al. (2018) [19] ; Bechar & Vigneault (2016) [21] ; Liakos et al.

(2018) [6] Rice LSTM, IoT sensors Irrigation scheduling, growth monitoring

Water savings of 15-30%, reduced CH₄ emissions Namin et al. (2018) [22] ; Talaviya et al.

(2020) [23] Maize [21] ; Kamilaris & Prenafeta-Boldú (2018) [5] [19] ; Bechar & Vigneault (2016) [6] ; Javaid et al. (2022) [20] Resource Efficiency Optimized water, fertilizer, and pesticide use reduces input waste and environmental pollution High equipment and software costs; variable ROI across farm scales Talaviya et al. (2020) [23] ; Ayaz et al. (2019) [16] Climate Adaptation AI forecasting improves response to weather variability, drought, and extreme events Model accuracy depends on data quality and regional calibration; poor internet limits real-time use Namin et al. (2018) [22] ; [25] ; Bhat & Huang (2021) [17] ~ [20,24] .

AI-Based Precision Irrigation

Water scarcity and irregular rainfall patterns caused by climate change have increased the importance of precision irrigation technologies in agriculture. AI-driven smart irrigation systems use sensors, machine learning algorithms, weather forecasts, and real-time soil moisture data to regulate water application according to crop requirements. These systems improve wateruse efficiency and reduce water wastage by delivering precise quantities of irrigation at the appropriate time (Talaviya et al., 2020) [23] . AI-assisted irrigation scheduling helps farmers manage drought conditions more effectively by predicting crop water stress and evapotranspiration rates. Smart irrigation technologies integrated with IoT devices can automatically control irrigation pumps and valves, reducing labor requirements and operational costs. Such technologies are particularly valuable in arid and semi-arid regions where water conservation is essential for sustainable crop production (Ayaz et al., 2019) [16] . [20,24] . These technologies support efficient decision-making related to irrigation, nutrient management, disease detection, and crop monitoring. One of the major advantages of AI in agriculture is enhanced productivity and resource-use efficiency. AI-based predictive models optimize irrigation scheduling, fertilizer application, and pest management, leading to higher crop yields and reduced input wastage (Liakos et al., 2018) [6] . Precision irrigation systems integrated with IoT sensors improve water-use efficiency, while site-specific nutrient management reduces excessive fertilizer use and environmental pollution (Talaviya et al., 2020) [23] . AI technologies also strengthen climate resilience by providing accurate weather forecasting and early warning systems for droughts, floods, and pest outbreaks. Predictive analytics help farmers adopt timely adaptation strategies, improving farm resilience against climate variability (Namin et al., 2018) [22] . In addition, AI-supported conservation practices contribute to greenhouse gas mitigation through optimized input use, reduced energy consumption, and improved soil carbon sequestration (Coble et al., 2018) [18] . Economically, AI-driven systems reduce labor dependency, lower production costs, and improve operational efficiency through automation and smart advisory services. These benefits collectively enhance farm profitability, food security, and longterm agricultural sustainability (Kamilaris & Prenafeta-Boldú, 2018) [5] .

Challenges and Limitations of AI-Driven Climate-Smart Agriculture

Despite its significant potential, the adoption of AI-driven climate-smart agriculture faces several economic, technical, and social challenges. One of the primary limitations is the high initial investment required for AI technologies such as sensors, drones, robotics, and automated irrigation systems, which restricts adoption among smallholder and resource-poor farmers (Pathak et al., 2019) [25] . In addition, inadequate digital infrastructure, including poor internet connectivity and unreliable electricity supply in rural areas, limits the effective implementation of IoT and cloud-based agricultural systems (Ayaz et al., 2019) [16] . Data-related challenges also hinder AI applications in agriculture. AI models require large volumes of accurate and real-time data; however, agricultural datasets are often fragmented, inconsistent, and region-specific, affecting prediction accuracy and decision-making efficiency (Wolfert et al., 2017) [24] . Limited digital literacy, lack of technical expertise, and insufficient training opportunities among farmers further constrain technology adoption, particularly in developing countries (Javaid et al., 2022) [20] . Ethical concerns related to data privacy, cybersecurity, and ownership of agricultural information have also emerged as critical issues in AI-based farming systems. Furthermore, excessive dependence on automated technologies may reduce human participation in agricultural decision-making processes. [6,20] . These innovations strengthen agricultural resilience against climate variability while reducing environmental impacts and greenhouse gas emissions. AI-driven systems also enhance decision-making through predictive analytics and real-time monitoring, supporting sustainable and climate-resilient agricultural production.

Emerging technologies including explainable AI, blockchain integration, and digital twins are expected to further improve transparency, efficiency, and adaptability in future farming systems (Verdouw et al., 2021) [27] . However, several barriers continue to limit large-scale adoption, particularly in developing countries. High implementation costs, inadequate digital infrastructure, limited technical expertise, and data privacy concerns remain major challenges (Arrieta et al., 2020) [26] . Addressing these limitations will require strong policy support, investment in rural digital infrastructure, farmer training programs, and affordable technological solutions. Overall, AI-driven climate-smart agriculture offers a promising pathway toward resilient, sustainable, and intelligent food production systems. Continued innovation, interdisciplinary research, and collaborative institutional efforts will be essential for ensuring global food security and sustainable agricultural development under changing climatic conditions.

References

1. Challinor AJ, Watson J, Lobell DB, Howden SM, Smith DR, Chhetri N. A meta-analysis of crop yield under climate change and adaptation. Nat Clim Chang. 2014;4(4):287291.
2. FAO. Climate-smart agriculture: Policies, practices and financing for food security, adaptation and mitigation. Rome: Food and Agriculture Organization of the United Nations; 2010.
3. FAO. The state of food security and nutrition in the world 2023. Rome: Food and Agriculture Organization of the United Nations; 2023.
4. IPCC. Climate change 2022: Impacts, adaptation and vulnerability. Geneva: Intergovernmental Panel on Climate Change; 2022.
5. Kamilaris A, Prenafeta-Boldú FX. Deep learning in agriculture: A survey. Comput Electron Agric. 2018;147:70-90.
6. Liakos KG, Busato P, Moshou D, Pearson S, Bochtis D. Machine learning in agriculture: A review. Sensors. 2018;18(8):2674.
7. Smith P, Martino D, Cai Z, Gwary D, Janzen H, Kumar P, et al. Greenhouse gas mitigation in agriculture. Philos Trans R Soc B Biol Sci. 2008;363(1492):789-813.
8. C, Liu B, Piao S, Wang X, Lobell DB, Huang Y, et al. Temperature increase reduces global yields of major crops in four independent estimates. Proc Natl Acad Sci U S A. 2017;114(35):9326-9331.
9. Garnett T, Appleby MC, Balmford A, et al. Sustainable intensification in agriculture. Science. 2013;341(6141):3334.
10. Lipper L, Thornton P, Campbell BM, et al. Climate-smart agriculture for food security. Nat Clim Chang. 2014;4(12):1068-1072.
11. Smith P, Martino D, Cai Z, et al. Agriculture and greenhouse gas mitigation. Philos Trans R Soc B Biol Sci. 2020;363(1492):789-813.
12. Thornton PK, Herrero M. Adapting to climate change in agricultural systems. Nat Clim Chang. 2015;5(9):830-836.
13. Tilman D, Balzer C, Hill J, Befort BL. Global food demand and sustainable intensification. Proc Natl Acad Sci U S A. 2011;108(50):20260-20264.
14. Vermeulen SJ, Campbell BM, Ingram JSI. Climate change and food systems. Annu Rev Environ Resour. 2012;37:195222.
15. Wezel A, Soboksa G, McClelland S, et al. Agroecological practices for climate-smart agriculture. Agron Sustain Dev. 2020;40(2):1-18.
16. Ayaz M, Ammad-Uddin M, Sharif Z, Mansour A, Aggoune EHM. Internet-of-Things (IoT)-based smart agriculture: Toward making the fields talk. IEEE Access. 2019;7:129551-129583.
17. Bhat SA, Huang NF. Big data and AI revolution in precision agriculture: Survey and challenges. IEEE Access. 2021;9:110209-110222.
18. Coble KH, Mishra AK, Ferrell S, Griffin T. Big data in agriculture: A challenge for the future. Appl Econ Perspect Policy. 2018;40(1):79-96.
19. Duckett T, Pearson S, Blackmore S, Grieve B. Agricultural robotics: The future of robotic agriculture. UK-RAS White Papers. 2018;1-32.
20. Javaid M, Haleem A, Singh RP, Suman R. Artificial intelligence applications for Industry 4.0 in agriculture. Sustain Oper Comput. 2022;3:15-28.
21. Mohanty SP, Hughes DP, Salathé M. Using deep learning for image-based plant disease detection. Front Plant Sci. 2016;7:1419.
22. Namin ST, Esmaeilzadeh M, Najafi M, Brown TB, Borevitz JO. Deep learning for time-series crop yield prediction. Front Plant Sci. 2018;9:1-12.
23. Talaviya T, Shah D, Patel N, Yagnik H, Shah M. Artificial intelligence in agriculture for optimization of irrigation and pesticides. Artif Intell Agric. 2020;4:58-73.
24. Wolfert S, Ge L, Verdouw C, Bogaardt MJ. Big data in smart farming: A review. Agric Syst. 2017;153:69-80.
25. Pathak HS, Brown P, Best T. A systematic literature review of the factors affecting the precision agriculture adoption process. Precis Agric. 2019;20(6):1292-1316.
26. Arrieta AB, Díaz-Rodríguez N, Del Ser J, et al. Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges. Inf Fusion. 2020;58:82-115.
27. Verdouw C, Tekinerdogan B, Beulens A, Wolfert S. Digital twins in smart farming. Agric Syst. 2021;189:103046.