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

2025-07-23

AI Summary

To address the need for precise nitrogen management in vineyards, this study proposes a non-destructive leaf nitrogen content estimation method integrating field-based hyperspectral imaging (400–1000 nm) with machine learning. Using multi-cultivar, multi-growth-stage, and multi-field experimental data, four stable nitrogen-sensitive spectral bands—500–525 nm, 650–690 nm, 750–800 nm, and 900–950 nm—were identified. Two feature selection strategies were combined with gradient-boosting models (e.g., XGBoost) to enhance model generalizability. The approach achieved R² values of 0.57 at the leaf scale and 0.49 at the canopy scale, demonstrating robust performance under complex field conditions. This work provides a practical, scalable solution for site-specific variable-rate nitrogen fertilization in viticulture.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Learning & Optimization for CV
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Machine learning and data science for the Web
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Nitrogen (N) is one of the most crucial nutrients in vineyards, affecting plant growth and subsequent products such as wine and juice. Because soil N has high spatial and temporal variability, it is desirable to accurately estimate the N concentration of grapevine leaves and manage fertilization at the individual plant level to optimally meet plant needs. In this study, we used in-field hyperspectral images with wavelengths ranging from $400 to 1000nm of four different grapevine cultivars collected from distinct vineyards and over two growth stages during two growing seasons to develop models for predicting N concentration at the leaf-level and canopy-level. After image processing, two feature selection methods were employed to identify the optimal set of spectral bands that were responsive to leaf N concentrations. The selected spectral bands were used to train and test two different Machine Learning (ML) models, Gradient Boosting and XGBoost, for predicting nitrogen concentrations. The comparison of selected bands for both leaf-level and canopy-level datasets showed that most of the spectral regions identified by the feature selection methods were across both methods and the dataset types (leaf- and canopy-level datasets), particularly in the key regions, 500-525nm, 650-690nm, 750-800nm, and 900-950nm. These findings indicated the robustness of these spectral regions for predicting nitrogen content. The results for N prediction demonstrated that the ML model achieved an R square of 0.49 for canopy-level data and an R square of 0.57 for leaf-level data, despite using different sets of selected spectral bands for each analysis level. The study demonstrated the potential of using in-field hyperspectral imaging and the use of spectral data in integrated feature selection and ML techniques to monitor N status in vineyards.

Problem

• Estimating grapevine leaf nitrogen concentration using hyperspectral imaging
• Identifying optimal spectral bands for nitrogen assessment in vineyards
• Developing machine learning models for vineyard nitrogen management

Innovation

• In-field hyperspectral imaging for nitrogen assessment
• Feature selection to identify optimal spectral bands
• Machine Learning models for nitrogen concentration prediction