Prediction of Apple Canopy Leaf Area Index Based on Near-Infrared Spectroscopy and Machine Learning
Agronomy · 25.04.2026 · 16 (9) · 875
DOI: 10.3390/agronomy16090875 ↗Kurz gefasst
Fachartikel in der Zeitschrift Agronomy, online erschienen am 25.04.2026. Verfasst von Junkai Zeng und 5 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Study on Light Physiology Characteristics and Mechanisation-Compatible Cultivation Model Establishment in Dwarf Rootstock Dense-Planting Apple Orchards in Sout…, Nanjing Agricultural University–Tarim University Joint Research Fund.
Abstract (Originalsprache)
Traditional leaf area index (LAI) measurement methods are destructive, time-consuming, and labor-intensive. In this study, 282 four-year-old central-leader apple trees were used as research subjects. Canopy reflectance spectra in the range of 4000–10,000 cm−1 were collected, and the corresponding true LAI values were measured destructively by harvesting all leaves from a representative branch of each tree using a leaf area meter. The dataset was randomly divided into training (70%) and testing (30%) sets. Eight spectral pretreatment methods were compared. The Competitive Adaptive Reweighted Sampling (CARS) algorithm was employed to extract characteristic wavelengths. Subsequently, both a BP neural network and a Support Vector Machine (SVM) model for LAI prediction were constructed. The optimal model was selected based on evaluation metrics including the coefficient of determination (R2), mean absolute error (MAE), mean bias error (MBE), and mean absolute percentage error (MAPE). The combined preprocessing of MSC and SD yielded the optimal results, screening out 26 characteristic wavelengths. The SVM linear kernel model (c = 5, g = 0.3) constructed based on MSC + SD preprocessing performed best, achieving a validation set R2 of 0.90, MAE of 0.2117, MBE of −0.1214, and MAPE of 16.09%. The performance on the training set and validation set was comparable, with no overfitting observed. The MSC + SD preprocessing combined with CARS feature screening and SVM linear kernel modeling enables rapid, non-destructive estimation of apple canopy LAI, providing an effective technical tool for precision orchard management.
Förderung
- Study on Light Physiology Characteristics and Mechanisation-Compatible Cultivation Model Establishment in Dwarf Rootstock Dense-Planting Apple Orchards in Sout…
- Nanjing Agricultural University–Tarim University Joint Research Fund
Zitieren
APA
Zeng, J., Cao, W., Chen, Y., Yu, M., Jiang, J., & Bao, J. (2026). Prediction of Apple Canopy Leaf Area Index Based on Near-Infrared Spectroscopy and Machine Learning. Agronomy, 16(9), 875. https://doi.org/10.3390/agronomy16090875
Vancouver
Zeng J, Cao W, Chen Y, Yu M, Jiang J, Bao J. Prediction of Apple Canopy Leaf Area Index Based on Near-Infrared Spectroscopy and Machine Learning. Agronomy. 2026;16(9):875. doi:10.3390/agronomy16090875
BibTeX
@article{Zeng2026,
author = {Zeng, Junkai and Cao, Wei and Chen, Yan and Yu, Mingyang and Jiang, Jiyuan and Bao, Jianping},
title = {Prediction of Apple Canopy Leaf Area Index Based on Near-Infrared Spectroscopy and Machine Learning},
journal = {Agronomy},
year = {2026},
volume = {16},
number = {9},
pages = {875},
doi = {10.3390/agronomy16090875}
}
EUVIMED