Research in Photonics and Food Technology

Welcome to our research hub, where the intersection of advanced photonics, AI, and food technology is leading to groundbreaking solutions for food quality and sustainability. Researchers at TOELT are pioneering methods to transform how we understand, monitor, and maintain food standards, particularly through the lens of photonics. Our team leverages spectroscopy and machine learning to analyze complex spectral data, providing critical insights into the chemical and physical changes that affect food.

One of our core pursuits is developing tools that democratize food quality assessment. With a large experience in on olive oil, wine and toxins, we have explored how spectral data can reveal signs of changes in food. Through specialized machine learning models and the identification of key wavelengths, our research has made it possible to predict these changes with high accuracy. Additionally, our research show how the development of affordable, field-ready sensors to perform real-time quality assessments without needing specialized equipment is possible.

Our research is not just about preserving food standards but also about setting new benchmarks in sustainable, data-driven food technology. By enhancing transparency in quality control and empowering producers with practical, science-backed tools, we’re reshaping the landscape of food safety and sustainability. Join us in this exciting journey as we bridge advanced technology with real-world applications to ensure the highest standards in food quality and consumer health.

Image source Michelucci, U., & Venturini, F. (2024). Deep learning domain adaptation to understand physico-chemical processes from fluorescence spectroscopy small datasets and application to the oxidation of olive oil. Scientific Reports, 14(1), 22291.

Selected Publications

Deep learning domain adaptation to understand physico-chemical processes from fluorescence spectroscopy small datasets and application to the oxidation of olive oil Nature Scientific Reports, 14(1), 22291, (2024)

Michelucci, U., & Venturini, F. (2024). Deep learning domain adaptation to understand physico-chemical processes from fluorescence spectroscopy small datasets and application to the oxidation of olive oil. Scientific Reports, 14(1), 22291.

Revolutionizing Food Quality and Sustainability through AI and Spectroscopy

At the intersection of artificial intelligence and food science, our research is transforming how we understand and maintain the quality of extra virgin olive oil (EVOO) and other food products. Using fluorescence spectroscopy data and innovative deep learning techniques, we've developed a powerful new approach to predict, interpret, and optimize food quality over time.

Our Solution: Domain Adaptation and Interpretability in AI

Fluorescence spectroscopy is widely recognized for its accuracy and detail in detecting molecular changes, making it invaluable in fields like food science, environmental monitoring, and medical diagnostics. However, traditional methods have struggled with small, sparse datasets and the complex nature of spectral data. To overcome these challenges, we apply domain adaptation—leveraging pretrained neural networks designed for image recognition to analyze spectroscopic data. By adapting the MobileNetv2 model, we've successfully trained AI to predict critical quality indicators in olive oil, even on limited datasets.

Our work goes beyond prediction. We’ve developed an Information Elimination Algorithm (IEA) that identifies the most relevant spectral bands linked to chemical changes in EVOO, like oxidation. This novel interpretability technique effectively turns our model into a tool for scientific discovery, uncovering how molecular components—such as chlorophyll and oxidation products—evolve during oil ageing. By making AI’s insights transparent, our approach enables a deeper understanding of food chemistry, supporting producers in making data-driven quality assessments.

Impact on Industry and Future Applications

The ability to accurately predict and understand food quality without large datasets opens exciting possibilities. From enhancing product shelf-life to supporting real-time quality monitoring, this research sets a new standard for AI’s role in food science. Our model can be easily adapted to other products and processes, such as tracking the freshness of perishable goods or detecting chemical changes in pharmaceuticals.

Shedding light on the ageing of extra virgin olive oil: Probing the impact of temperature with fluorescence spectroscopy and machine learning techniques, LWT, 191, 115679 (2024)

Venturini, F., Fluri, S., Mejari, M., Baumgartner, M., Piga, D., & Michelucci, U. (2024). Shedding light on the ageing of extra virgin olive oil: Probing the impact of temperature with fluorescence spectroscopy and machine learning techniques. LWT, 191, 115679.

This paper, investigates how extra virgin olive oil (EVOO) undergoes quality changes during storage, focusing on the effects of temperature. Using UV absorption and fluorescence spectroscopy, the study tracks molecular changes in olive oil exposed to accelerated ageing, aiming to capture the chemical shifts associated with oxidation. Through detailed spectral data analysis, the authors pinpoint two wavelengths, 480 nm and 300 nm, that prove sensitive to these oxidative processes, providing reliable indicators for assessing oil quality over time.

A major contribution of the research is its application of machine learning for feature extraction, which allows the model to identify specific wavelengths critical to tracking the ageing process. This approach not only enhances the precision of quality assessments but also offers a scalable solution that could be adapted across different food products. By analyzing spectral patterns, machine learning models can detect subtle changes in oil composition that traditional methods might miss, marking a significant advancement in non-destructive food quality monitoring.

Building on these findings, the paper proposes developing a low-cost fluorescence-based device, utilizing only two LEDs and a photodiode at the identified wavelengths. This portable tool could offer a practical solution for in-field quality assessments, making it easier for producers and distributors to monitor olive oil freshness in real-time without lab equipment. The broader implications suggest that similar technology could be adapted for other perishable goods, supporting enhanced food preservation, quality control, and sustainable practices in the food industry.