Phenology-Adaptive Prediction of Walnut Leaf Area Index from UAV Multispectral Data via Hybrid Feature Selection and SHAP-Enhanced Machine Learning.
Saved in:
| Title: | Phenology-Adaptive Prediction of Walnut Leaf Area Index from UAV Multispectral Data via Hybrid Feature Selection and SHAP-Enhanced Machine Learning. |
|---|---|
| Authors: | Xia, Qiuhao1,2,3 (AUTHOR), Yerzati, Yerhazi1,2,3 (AUTHOR), Li, Zihao3,4 (AUTHOR), Qi, Jiahui1,2,3,4 (AUTHOR), Chen, Jiaxing1,2,3,5 (AUTHOR), Sen, Yu1,2,3,6 (AUTHOR), Zhang, Rui1,2,3 (AUTHOR), Zhang, Yunqi2,5 (AUTHOR), Wang, Hongxia3,6 (AUTHOR), Guo, Zhongzhong1,3,4 (AUTHOR) 120230085@taru.edu.cn |
| Source: | Remote Sensing. Jun2026, Vol. 18 Issue 12, p1941. 25p. |
| Subjects: | Leaf area index, Feature selection, Remote sensing, Random forest algorithms |
| Geographic Terms: | Xinjiang Xian (China) |
| Abstract: | Highlights: What are the main findings? Predictor importance shifts with phenology: texture features dominate early growth, while red-edge indices (RENDVI and Redge_750_Mean) prevail during vigorous stages, partially alleviating the saturation effect of NDVI within the observed LAI range. Hybrid feature selection (linear + nonlinear + consensus) cuts redundancy by 69.6%; the red-edge/texture subset with random forest achieves RPD > 2.0 during oil conversion. What are the implications of the main findings? Enables phenology-adaptive UAV monitoring: tailoring feature selection (texture for early stages, red-edge for peak biomass) improves LAI accuracy across the entire growth cycle. Supports lightweight and scalable orchard systems: reducing features by 70% while achieving an RPD > 2.0 proves that high precision is possible with compact "red-edge + texture" inputs, lowering computational and sensor costs. Accurate monitoring of the leaf area index (LAI) throughout the entire growth cycle of walnut trees using UAV multispectral imagery is essential for digital orchard management. In this study, focusing on the 'Wen 185' walnut variety in Xinjiang, we simultaneously acquired UAV multispectral images and ground-measured LAI data during four critical growth stages: expansion, hard shell, oil conversion, and maturity. A total of 25 vegetation indices and 48 texture features derived from the gray-level co-occurrence matrix were extracted. Hybrid feature selection combining linear (Pearson correlation), nonlinear (maximum information coefficient and random forest importance), and multiple consensus strategies was employed to reduce redundancy. LAI prediction models were constructed using four algorithms: Random Forest (RF), Support Vector Machine (SVM), LASSO, and Ridge Regression (RR), with model interpretability enhanced by SHAP analysis. Results showed that the multiple consensus screening reduced feature redundancy by an average of 69.6%. SHAP identified five core features: Redge_750_Mean, NDVI, B_Mean, RENDVI, and G_Homogeneity. Importantly, predictor importance shifted significantly with phenology: texture features dominated during the expansion stage, while red-edge indices (RENDVI and Redge_750_Mean) became predominant during the hard shell and oil conversion stages, effectively mitigating the saturation problem commonly observed in traditional indices such as NDVI within the LAI range of 1.5–5.8 in this study. The hybrid feature subset combining "red-edge spectrum + spatial texture" with the Random Forest algorithm achieved superior performance across all stages, with the RPD value exceeding 2.0 during the oil conversion stage, indicating excellent estimation capability. This study demonstrates that a "quality over quantity" feature selection strategy not only reduces model complexity but also enables high-precision, dynamic LAI monitoring throughout the entire walnut growth cycle, providing a scientific basis for intelligent management of large-scale orchards in arid regions. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
Be the first to leave a comment!
