Deep Learning Domain Adaptation to Understand Physico-Chemical Processes from Fluorescence Spectroscopy Small Datasets: Application to Ageing of Olive Oil

TL;DR

This paper introduces a novel deep learning domain adaptation approach using pretrained vision models and interpretability algorithms to analyze fluorescence spectroscopy data, specifically for understanding olive oil ageing with small datasets.

Contribution

It presents a new method combining domain adaptation and interpretability for deep learning on spectroscopic data, enabling insights into physico-chemical processes.

Findings

Effective prediction of olive oil ageing quality indicators

Identification of spectral bands and molecules involved in oxidation

Enhanced interpretability of deep learning models in spectroscopy

Abstract

Fluorescence spectroscopy is a fundamental tool in life sciences and chemistry, widely used for applications such as environmental monitoring, food quality control, and biomedical diagnostics. However, analysis of spectroscopic data with deep learning, in particular of fluorescence excitation-emission matrices (EEMs), presents significant challenges due to the typically small and sparse datasets available. Furthermore, the analysis of EEMs is difficult due to their high dimensionality and overlapping spectral features. This study proposes a new approach that exploits domain adaptation with pretrained vision models, alongside a novel interpretability algorithm to address these challenges. Thanks to specialised feature engineering of the neural networks described in this work, we are now able to provide deeper insights into the physico-chemical processes underlying the data. The proposed approach is demonstrated through the analysis of the oxidation process in extra virgin olive oil (EVOO) during ageing, showing its effectiveness in predicting quality indicators and identifying the spectral bands, and thus the molecules involved in the process. This work describes a significantly innovative approach in the use of deep learning for spectroscopy, transforming it from a black box into a tool for understanding complex biological and chemical processes.