# Integrating Feature Selection and Machine Learning for Nitrogen Assessment in Grapevine Leaves using In-Field Hyperspectral Imaging

arXiv: https://arxiv.org/abs/2507.17869 · HTML: https://mlsanity.com/paper/2507.17869/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 62 references that are in the map.
- First posted on arXiv 23 Jul 2025.

## Builds on (most cited first, 4 of 4)

- [Feature Importance in Gradient Boosting Trees with Cross-Validation Feature Selection](https://mlsanity.com/paper/2109.05468/) (2021)
- [Feature Selection for Ridge Regression with Provable Guarantees](https://mlsanity.com/paper/1506.05173/) (2015)
- [Ensemble Hyperspectral Band Selection for Detecting Nitrogen Status in Grape Leaves](https://mlsanity.com/paper/2010.04225/) (2020)
- [Machine Vision-Based Assessment of Fall Color Changes and its Relationship with Leaf Nitrogen Concentration](https://mlsanity.com/paper/2404.14653/) (2024)

## Abstract (arXiv)

Nitrogen (N) is one of the most critical nutrients in winegrape production, influencing vine vigor, fruit composition, and wine quality. Because soil N availability varies spatially and temporally, accurate estimation of leaf N concentration is essential for optimizing fertilization at the individual plant level. In this study, in-field hyperspectral images (400-1000 nm) were collected from four grapevine cultivars (Chardonnay, Pinot Noir, Concord, and Syrah) across two growth stages (bloom and veraison) during the 2022 and 2023 growing seasons at both the leaf and canopy levels. An ensemble feature selection framework was developed to identify the most informative spectral bands for N estimation within individual cultivars, effectively reducing redundancy and selecting compact, physiologically meaningful band combinations spanning the visible, red-edge, and near-infrared regions. At the leaf level, models achieved the highest predictive accuracy for Chardonnay (R^2 = 0.82, RMSE = 0.19 %DW) and Pinot Noir (R^2 = 0.69, RMSE = 0.20 %DW). Canopy-level predictions also performed well, with R^2 values of 0.65, 0.72, and 0.70 for Chardonnay, Concord, and Syrah, respectively. White cultivars exhibited balanced spectral contributions across the visible, red-edge, and near-infrared regions, whereas red cultivars relied more heavily on visible bands due to anthocyanin-chlorophyll interactions. Leaf-level N-sensitive bands selected for Chardonnay and Pinot Noir were successfully transferred to the canopy level, improving or maintaining prediction accuracy across cultivars. These results confirm that ensemble feature selection captures spectrally robust, scale-consistent bands transferable across measurement levels and cultivars, demonstrating the potential of integrating in-field hyperspectral imaging with machine learning for vineyard N status monitoring.