# Multispectral Fluorescence Imaging for Fast Identification of Cold Stress in Pepper Plants

## TL;DR

This paper shows how multispectral fluorescence imaging and deep learning can quickly detect cold stress in pepper plants without damaging them.

## Contribution

A deep-learning pipeline using snapshot multispectral fluorescence imaging is proposed for nondestructive cold stress detection in plants.

## Key findings

- The deep-learning model achieved 85.7% accuracy in identifying cold stress in pepper plants.
- The model outperformed conventional classifiers like LDA, QDA, and G-SVM in classification metrics.
- Classification maps from hyperspectral cubes showed moderate misclassification, matching overall performance.

## Abstract

This paper investigated the feasibility of snapshot multispectral fluorescence imaging for nondestructive identification of cold stress in pepper plants. Fluorescence spectra were obtained by exciting the plant with a 405 nm ultraviolet LED. The plants were grown under three temperature conditions: 17 °C (control), 10 °C (moderate cold stress), and 5 °C (severe cold stress). Raw fluorescence spectra extracted from the demosaiced snapshot images were used as inputs for a deep-learning pipeline consisting of feature extraction, an encoder–decoder GRU, and a multilayer perceptron (MLP), and the results were compared with conventional machine learning classifiers, including linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and a Gaussian support vector machine (G-SVM). Tukey’s HSD test indicated that the proposed deep-learning model achieved the highest cross-validation accuracy and consistently produced superior classification metrics (accuracy of 85.7%, precision of 85.3%, recall of 85.3%, F1-score of 85.2). The trained model was further applied to hyperspectral cubes to generate classification maps; however, moderate misclassification was observed, consistent with the overall prediction performance.