Weiping Wu^1,2

1 Hangzhou Yinghe Jiatian Technology Co., Ltd., Hangzhou, 310056, Zhejiang, China
2 Zhejiang Agronomist College, Hangzhou, 310021, Zhejiang, China
Author    Correspondence author
Computational Molecular Biology, 2026, Vol. 16, No. 1   
Received: 26 Dec., 2025    Accepted: 31 Jan., 2026    Published: 12 Feb., 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.

Accurate prediction of citrus yield is essential for optimizing agricultural management and ensuring food security. This study develops an integrated framework for citrus yield prediction based on soil and climate variables using multi-source data. Key soil properties and climatic factors are systematically analyzed to reveal their individual and interactive effects on yield formation. Both traditional statistical models and machine learning approaches, including Random Forest and Support Vector Machine, are employed and compared. Data preprocessing, feature selection, and model optimization strategies are implemented to improve prediction accuracy. A case study in a typical citrus-producing region demonstrates the applicability and robustness of the proposed approach. Results indicate that soil–climate coupling significantly enhances predictive performance, while key driving factors such as temperature, precipitation, and soil nutrient content play critical roles. The study provides valuable insights for precision agriculture and supports decision-making in citrus production under varying environmental conditions.

Citrus yield prediction; Soil variables; Climate factors; Machine learning; Precision agriculture