EUVIMEDObjevte EUVIMED
Evaluationsstudie

Coupling machine learning with a biophysical model for maturity date prediction of apple fruit across China's apple planting regions

Renwei Chen iD, Jing Wang, Zhihong Gong, Jianshuo Zhou, Yang Li, Rui Bai, Zhenjiang Qu, Zhangyan Le

Journal of the Science of Food and Agriculture · 2026-12 · 106 (15) · 9693-9704

DOI: 10.1002/jsfa.70943 ↗

At a glance

Evaluationsstudie in Journal of the Science of Food and Agriculture, published online on 2026-08-01. Written by Renwei Chen and 7 co-authors. Institution: Tianjin Climate Center, Tianjin, China. Major MEDLINE topics: Malus, Fruit, Machine Learning. 78 references. Funded by: The work was supported by China's National Climatic Zoning Project for Apple, Natural Science Basic Research Program of Shaanxi [2024JC-YBMS-238], Open Research Fund Project of the Key Laboratory of Eco-Environmental Meteorology in Qinling Mountains and Loess Plateau, China Meteorological Administration [….

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

BACKGROUND Accurate prediction of apple fruit maturity date is essential for optimizing harvest timing, fruit quality and market value under climate change. However, process‐based crop models often show limited performance when extrapolated across large spatial scales, whereas machine learning models lack physiological interpretability. To address these limitations, this study has developed a hybrid framework integrating the process‐based STICS model with machine learning approaches across China's apple planting regions. RESULTS Phenological observations from 24 sites and meteorological data from 250 stations during 1991–2020 were used to calibrate and evaluate six machine learning models. Among them, the random forest (RF) model achieved the best performance [coefficient of determination ( R 2 ) > 0.65, root mean square error (RMSE) < 8.1 days]. A hybrid approach was implemented by incorporating STICS‐simulated maturity dates as input features into the machine learning models, enabling the capture of residual non‐linear relationships between maturity dates of apple fruit and climatic and geographic variables. This integration further improved prediction accuracy ( R 2 > 0.71, RMSE < 7.5 days), reducing errors by over 50% compared to the standalone STICS model. Spatially, the average maturity date was 282.5 ± 7.0 DOY (i.e. day of year), with the latest maturity in the Yellow River region and the earliest in the Southwest highlands. Temporally, maturity dates advanced slightly at 0.1 days decade −1 , with substantial regional variability. SHAP (i.e. Shapley Additive exPlanations) analysis identified chilling requirement, elevation and STICS‐simulated maturity date as dominant drivers. CONCLUSION The hybrid STICS+RF framework effectively combines mechanistic understanding with data‐driven learning, improving prediction accuracy and interpretability of apple fruit maturity date at regional scales. This approach provides a robust tool for optimizing harvest management and adapting apple production systems to climate change. © 2026 Society of Chemical Industry.

Subjects

MeSH terms (MEDLINE)

MalusFruitMachine LearningChinaPredictive Learning ModelsRandom ForestSeasonsClimate ChangePrediction Algorithms

Author keywords

SHAPSTICSautumn phenologyclimate changemeteorological factors

Authors and institutions

  • Tianjin Climate Center, Tianjin, China.
  • College of Resources and Environmental Sciences, China Agricultural University, Beijing, China.
  • Jizhou Meteorological Service of Tianjin Municipality, Jizhou, China.
  • State Key Laboratory of Severe Weather Meteorological Science and Technology, Shenyang Institute of Agricultural and Ecological Meteorology, Chinese Academy of Meteorological Sciences, Beijing, China.
  • Hainan Climate Center, Key Laboratory of South China Sea Meteorological Disaster Prevention and Mitigation of Hainan Province, Haikou, China.
  • Shaanxi Meteorological Information Center, Shaanxi Meteorological Service, Xi'an, China.

ORCID profiles: Renwei Chen

Funding

  • The work was supported by China's National Climatic Zoning Project for Apple
  • Natural Science Basic Research Program of Shaanxi [2024JC-YBMS-238]
  • Open Research Fund Project of the Key Laboratory of Eco-Environmental Meteorology in Qinling Mountains and Loess Plateau, China Meteorological Administration […

Cite

APA

Chen, R., Wang, J., Gong, Z., Zhou, J., Li, Y., Bai, R., Qu, Z., & Le, Z. (2026). Coupling machine learning with a biophysical model for maturity date prediction of apple fruit across China's apple planting regions. Journal of the Science of Food and Agriculture, 106(15), 9693-9704. https://doi.org/10.1002/jsfa.70943

Vancouver

Chen R, Wang J, Gong Z, Zhou J, Li Y, Bai R, et al. Coupling machine learning with a biophysical model for maturity date prediction of apple fruit across China's apple planting regions. Journal of the Science of Food and Agriculture. 2026;106(15):9693-9704. doi:10.1002/jsfa.70943

BibTeX
@article{Chen2026,
  author = {Chen, Renwei and Wang, Jing and Gong, Zhihong and Zhou, Jianshuo and Li, Yang and Bai, Rui and Qu, Zhenjiang and Le, Zhangyan},
  title = {Coupling machine learning with a biophysical model for maturity date prediction of apple fruit across China's apple planting regions},
  journal = {Journal of the Science of Food and Agriculture},
  year = {2026},
  volume = {106},
  number = {15},
  pages = {9693--9704},
  doi = {10.1002/jsfa.70943}
}
Start for free →