Jinhua Cheng , Wei Wang

Institute of Life Sciences, Jiyang College of Zhejiang A&F University, Zhuji, 311800, Zhejiang, China
Author    Correspondence author
Computational Molecular Biology, 2026, Vol. 16, No. 2   
Received: 02 Feb., 2026    Accepted: 08 Mar., 2026    Published: 21 Mar., 2026

This is an open access article published under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Maize yield prediction plays an essential role in ensuring food security and promoting sustainable agricultural management. This study explores a prediction framework based on soil nutrient characteristics and climate variables to improve the accuracy and reliability of maize yield estimation. Key soil indicators, including nitrogen, phosphorus, potassium, organic matter, and pH value, were combined with climate factors such as temperature, precipitation, and accumulated growing degree days. Multiple prediction models, including traditional statistical approaches, machine learning algorithms, and deep learning methods, were constructed and compared. The study further analyzed the interaction effects between soil and climate variables and evaluated model performance using indicators such as RMSE, MAE, and R². A regional case study was conducted to verify the applicability and robustness of the proposed framework. The results demonstrate that integrating soil nutrient and climate data can significantly enhance maize yield prediction accuracy and provide valuable support for precision agriculture, crop management, and agricultural decision-making.

Maize yield prediction; Soil nutrients; Climate variables; Machine learning; Precision agriculture