Deep-Learning Investigation of Vibrational Raman Spectra for Plant-Stress Analysis

TL;DR

This paper presents DIVA, a deep learning workflow using variational autoencoders to analyze native Raman spectra for plant stress detection, eliminating manual preprocessing and enabling unbiased, automated plant health assessment.

Contribution

Introduction of DIVA, a fully automated deep learning method that processes native Raman spectra for plant-stress analysis without manual background removal.

Findings

Successfully detected various abiotic stresses

Identified bacterial infections in plants

Processed spectra with fluorescence backgrounds

Abstract

Detecting stress in plants is crucial for both open-farm and controlled-environment agriculture. Biomolecules within plants serve as key stress indicators, offering vital markers for continuous health monitoring and early disease detection. Raman spectroscopy provides a powerful, non-invasive means to quantify these biomolecules through their molecular vibrational signatures. However, traditional Raman analysis relies on customized data-processing workflows that require fluorescence background removal and prior identification of Raman peaks of interest-introducing potential biases and inconsistencies. Here, we introduce DIVA (Deep-learning-based Investigation of Vibrational Raman spectra for plant-stress Analysis), a fully automated workflow based on a variational autoencoder. Unlike conventional approaches, DIVA processes native Raman spectra-including fluorescence backgrounds-without manual preprocessing, identifying and quantifying significant spectral features in an unbiased manner. We applied DIVA to detect a range of plant stresses, including abiotic (shading, high light intensity, high temperature) and biotic stressors (bacterial infections). By integrating deep learning with vibrational spectroscopy, DIVA paves the way for AI-driven plant health assessment, fostering more resilient and sustainable agricultural practices.