Answers are grounded in this paper and cite their sources.
: Leaf Area Index (LAI) is a key parameter representing canopy structure and photosynthetic capacity in fruit trees, playing a critical role in growth monitoring, precision water and nutrient management, and yield prediction. Considering that the canopy is most developed during the fruit expansion stage and that accurate LAI estimation is particularly needed at this stage, this study focused on pear orchards in the Seventh Regiment of southern Xinjiang and conducted precise LAI retrieval by integrating UAV-based multispectral and RGB imagery. Vegetation indices, color indices, texture features, and RGB wavelet features were extracted as multi-source variables to construct multispectral models, RGB models, and fused models, which were evaluated using multiple machine learning algorithms. The results demonstrated that: (1) multi-source features showed significant correlations with measured LAI, indicating strong potential for accurate retrieval; (2) the fusion of multispectral and RGB features substantially improved LAI estimation accuracy, exhibiting higher stability and generalization compared to single-source models; and (3) among all tested models, the optimized integrated algorithm (OIA) achieved the best performance. This approach constructs a performance-adaptive weighted fusion mechanism based on the prediction errors and stability of base learners including SVM, ELM, and XGBoost, enabling complementary advantages among multiple models through optimized weight allocation. Overall, the combination of vegetation indices, multispectral texture features, and RGB wavelet features in the OIA model achieved the highest accuracy, with a testing set R² of 0.744 and RMSE of 0.141 m²/m². This study innovatively establishes a UAV-based multi-source and adaptive weighted ensemble framework for LAI estimation, significantly enhancing spatial estimation accuracy during the fruit expansion stage and providing a scalable technical approach for precise monitoring, water and nutrient management, and yield assessment in fruit trees.
No takes yet. Share an insight, caveat, or question.
A 2025 study studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: