Advancements in Machine Learning Algorithms for Precision Crop Yield Prediction: A Comprehensive Review with focus on European Union
Carmen Anton, Anca Avram, Oliviu Matei, Laura Andreica, Bogdan Văduva

Abstract. Accurate crop yield prediction is a key enabler of precision agriculture, helping farmers, policy-makers and supply-chain actors to anticipate production and to manage resources efficiently. This paper provides a comprehensive review of recent advancements in machine learning algorithms for crop yield prediction, with a specific focus on the European Union context. The review systematises the main classes of models (classical regression, ensemble methods, deep learning, hybrid and physics-informed approaches), the most commonly used data sources (remote sensing, weather, soil and crop management records) and the typical evaluation protocols. Particular attention is given to the regulatory, agronomic and climatic specificities of the EU and to open challenges that remain to be addressed.

Keywords: crop yield prediction; machine learning; precision agriculture; European Union; literature review

Carmen Anton, Anca Avram, Oliviu Matei, Laura Andreica, Bogdan Văduva, "Advancements in Machine Learning Algorithms for Precision Crop Yield Prediction: A Comprehensive Review with focus on European Union", Proc. 19th SOCO Int. Conf. on Soft Computing Models in Industrial and Environmental Applications, Springer, 2024, 2023.

Reference: Proc. 19th SOCO Int. Conf. on Soft Computing Models in Industrial and Environmental Applications, Springer, 2024.

Other publications