Abstract:
Raman spectroscopy and non-linear Raman spectroscopy techniques are increasingly being used in various disciplines, including chemical analysis, life sciences and medicine. Applications in these fields rely on artificial intelligence (AI)-based methods to transform measured data into high-level information and knowledge within the application domain. The high-level information depends on the specific task and sample characteristics, such as disease types, tissue types and other properties such as constituent concentrations. To achieve this translation, specialised data pipelines must be constructed for each measurement modality, including experimental design, sample size planning, data pre-treatment, data pre-processing, chemometric and machine learning based data modelling, model transfer methods and transfer learning. Almost every step in the data pipeline can be optimised using AI-based methods, including machine learning and deep learning. This talk will highlight common pitfalls encountered when building data pipelines for linear and non-linear Raman spectroscopy measurement techniques and discuss strategies to avoid them.

Bio:
Thomas Bocklitz studied Physics at the University of Jena and received his PhD in Physical Chemistry/Chemometrics there in 2011. In 2013 he became head of a junior research group "Statistical Modelling and Image Analysis" at the University of Jena. Since 2019 he is head of the research group "Photonic Data Science" at the Leibniz IPHT. In 2023 he was appointed as full professor for "Artificial Intelligence in Spectroscopy and Microscopy" at the University of Bayreuth and in 2024 as professor for "Photonic Data Science" at the University of Jena and the Leibniz-IPHT. His main research area is closely related to the photonic data lifecycle, which includes machine learning and chemometrics based modelling of photonic data. He has published more than 140 papers in peer-reviewed journals and has given more than 50 invited talks at conferences. Thomas Bocklitz's work has been honoured with prestigious awards, such as the Kaiser-Friedrich Research Prize in 2018 and the Bruce Kowalski Award in 2015. He also received an ERC Consolidator Grant in 2023 for the STAIN-IT project.