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. 4   
Received: 22 Jun., 2026    Accepted: 30 Jul., 2026    Published: 15 Aug., 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.

Bayberry (Myrica rubra) is an economically important fruit crop, and its commercial value is largely determined by quality attributes such as soluble solids content, acidity, firmness, color, and bioactive compounds. However, fruit quality formation is strongly influenced by complex interactions between environmental conditions and cultivation practices, making accurate prediction challenging under variable production environments. This review focuses on the construction of prediction models for bayberry fruit quality based on environmental and cultivation data. The mechanisms underlying quality formation are first summarized, including the regulation of temperature, precipitation, solar radiation, soil conditions, irrigation, and nutrient management on fruit development and biochemical accumulation. Subsequently, approaches for data acquisition, feature engineering, and integration of multi-source agricultural information are discussed. Various prediction methods, including statistical models, machine learning algorithms, and deep learning approaches, are evaluated with emphasis on model optimization, validation strategies, and interpretability analysis. A case study framework is presented to demonstrate the application of predictive models in orchard monitoring, quality forecasting, and precision management. Furthermore, the integration of prediction models with digital agriculture technologies, such as IoT sensors, remote sensing, and intelligent decision-support systems, is explored. Future research should emphasize multi-dimensional data integration, explainable artificial intelligence, and region-specific model adaptation to improve prediction accuracy and practical applicability. These advances will provide theoretical foundations and technical support for intelligent management and sustainable development of high-quality bayberry production.

Bayberry; Fruit quality prediction; Environmental factors; Machine learning; Precision horticulture