This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Predicting De-Handing Point in Bananas Using Crown Morphology and Interpretable Machine Learning
by
Lei Zhao
Lei Zhao 1,2
,
Zhou Yang
Zhou Yang 2,3,*,
Chunxia Wang
Chunxia Wang 1,
Mohui Jin
Mohui Jin 2 and
Jieli Duan
Jieli Duan 2,*
1
Sichuan Academy of Agricultural Machinery Sciences, Chengdu 610066, China
2
College of Engineering, South China Agricultural University, Guangzhou 510642, China
3
School of Mechanical Engineering, Guangdong Ocean University, Zhanjiang 524088, China
*
Authors to whom correspondence should be addressed.
Agronomy 2025, 15(8), 1880; https://doi.org/10.3390/agronomy15081880 (registering DOI)
Submission received: 30 June 2025
/
Revised: 30 July 2025
/
Accepted: 1 August 2025
/
Published: 3 August 2025
Abstract
Banana de-handing is a critical yet labor-intensive step in postharvest processing, with current manual methods resulting in high costs and occupational risks. This study addresses the automation of de-handing point localization by integrating high-resolution 3D scanning and morphometric analysis of banana crowns with machine learning techniques. A total of 210 crown samples were analyzed to extract key morphological features, including inner arc length (Li), inner arc radius (Ri), outer arc radius (Ro), and the distance between inner and outer arcs (Doi), among others. Four machine learning algorithms, namely, Multi-Layer Perceptron (MLP), Gradient Boosted Decision Trees (GBDT), Extreme Gradient Boosting (XGBoost), and Random Forest (RF), were developed to predict the target radius (Rt) and target distance (Dti) of the de-handing point. The RF models achieved the optimal predictive performance on the testing set, with the following results: for Rt, R² = 0.95, MAE = 1.50, and RMSE = 1.94; for Dti, R² = 0.91, MAE = 1.33, and RMSE = 1.66. A Shapley Additive Explanations (SHAP) analysis revealed that Li, Ri, and Ro were the most influential features for Rt, while Doi was the most important for Dti. Notably, feature threshold effects were observed, with limited gains in prediction accuracy beyond specific morphological values. These results provide a quantitative foundation for vision-guided automated de-handing systems, advancing intelligent and efficient banana postharvest management.
Share and Cite
MDPI and ACS Style
Zhao, L.; Yang, Z.; Wang, C.; Jin, M.; Duan, J.
Predicting De-Handing Point in Bananas Using Crown Morphology and Interpretable Machine Learning. Agronomy 2025, 15, 1880.
https://doi.org/10.3390/agronomy15081880
AMA Style
Zhao L, Yang Z, Wang C, Jin M, Duan J.
Predicting De-Handing Point in Bananas Using Crown Morphology and Interpretable Machine Learning. Agronomy. 2025; 15(8):1880.
https://doi.org/10.3390/agronomy15081880
Chicago/Turabian Style
Zhao, Lei, Zhou Yang, Chunxia Wang, Mohui Jin, and Jieli Duan.
2025. "Predicting De-Handing Point in Bananas Using Crown Morphology and Interpretable Machine Learning" Agronomy 15, no. 8: 1880.
https://doi.org/10.3390/agronomy15081880
APA Style
Zhao, L., Yang, Z., Wang, C., Jin, M., & Duan, J.
(2025). Predicting De-Handing Point in Bananas Using Crown Morphology and Interpretable Machine Learning. Agronomy, 15(8), 1880.
https://doi.org/10.3390/agronomy15081880
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.