AI-Driven Predictive Analytics for Smart Agriculture: Crop Yield and Pest Detection Models
Download PDFAbstract
The integration of Artificial Intelligence (AI) into agriculture is revolutionizing traditional farming practices, paving the way for a more sustainable, efficient, and food-secure future. This chapter explores the application of AI-driven predictive analytics in smart agriculture, with a specific focus on two critical areas: crop yield prediction and pest detection. We delve into the foundational concepts of machine learning and deep learning models that power these applications, examining their underlying architectures and methodologies. The chapter presents a comprehensive overview of the data requirements, preprocessing techniques, and model evaluation metrics essential for developing robust predictive systems. Through a detailed literature review, we highlight recent advancements and benchmark performances, showcasing the significant improvements AI models offer over traditional methods. Furthermore, we present a proposed methodology for both crop yield and pest detection, complete with simulated results and in-depth discussions. The results demonstrate the high accuracy and practical utility of these models, with crop yield prediction achieving an R2 score of 0.789 and pest detection reaching an accuracy of 85%. The chapter concludes by discussing the implications of these technologies for agricultural decision-making, resource optimization, and the future trajectory of intelligent farming applications.
References
- Anca Parmena Olimid and Daniel Alin Olimid. “Societal challenges, population trends and human security: evidence from the public governance within the United Nations publications (2015-2019)”. In: Revista de Stiinte Politice 64 (2019), pp. 53– 64.
- Andreas Kamilaris and Francesc X Prenafeta-Bold´u. “Deep learning in agriculture: A survey”. In: Computers and electronics in agriculture 147 (2018), pp. 70–90.
- Guillermo C Hern´andez Hern´andez, Jorge G´omez G´omez, and Javier Jim´enezCabas. “Predictive Models Based on Artificial Intelligence to Estimate Crop Yield: A Literature Review”. In: Agriculture 15.23 (2025), pp. 1–31.
- Thomas Van Klompenburg, Ayalew Kassahun, and Cagatay Catal. “Crop yield prediction using machine learning: A systematic literature review”. In: Computers and electronics in agriculture 177 (2020), p. 105709.
- Hames Sherif. “Machine Learning in Agriculture: Crop Yield Prediction”. In: (2022).
- Stella Mary Venkateswara and Jayashree Padmanabhan. “Deep learning based agricultural pest monitoring and classification”. In: Scientific Reports 15.1 (2025), p. 8684.
- Xiaoping Wu et al. “Ip102: A large-scale benchmark dataset for insect pest recognition”. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019, pp. 8787–8796.
- Abderraouf Amrani et al. “Multi-task learning model for agricultural pest detection from crop-plant imagery: A Bayesian approach”. In: Computers and electronics in agriculture 218 (2024), p. 108719.
- Muhammad Bilal et al. “High-Performance Deep Learning for Instant Pest and Disease Detection in Precision Agriculture”. In: Food Science & Nutrition 13.9 (2025), e70963.
- KK Gopathoti et al. “Enhancing crop water management: A logistic regression approach integrated with iot for smart irrigation”. In: International Journal of Scientific Methods in Computational Science and Engineering 1.1 (2024), pp. 1–8.
