Postdoc in Chemometrics & Machine Learning for Fluorescence Imaging

To advance our microplastics research, we are looking for a highly motivated Postdoctoral Researcher with strong expertise in fluorescence microscopy data analysis, chemometrics, and machine learning. This position is ideal for a researcher who enjoys working at the interface of imaging, data science, and environmental monitoring.

The project focuses on building scalable, accreditation-ready analysis workflows to detect and classify microplastics in complex sample types such as drinking water, plant-based beverages, and biological fluids.

As a key team member, you will:

Develop advanced pipelines for analyzing fluorescence microscopy datasets, integrating spectral, morphological, and lifetime features. Apply chemometric and machine learning methods (e.g., PCA, PLS-DA, clustering, neural networks) to enable automated, polymer-specific classification. Optimize workflows for high-throughput imaging and real-world sample variability, minimizing false positives and maximizing robustness. Validate the pipeline using diverse and regulatory-relevant samples, supporting future accreditation. You will work closely with a multidisciplinary team of chemists, materials scientists, and environmental engineers, as well as industrial and governmental stakeholders. The position includes access to state-of-the-art imaging infrastructure, including high-end fluorescence and Raman microscopes, hyperspectral and lifetime systems, and custom-built hardware.

If you are passionate about applying advanced data analysis to real-world environmental challenges, and you are eager to bring fluorescence microscopy and machine learning together to advance microplastic detection, we strongly encourage you to apply., * Design and implement chemometric and machine learning models (e.g., PCA, PLS-DA, clustering, CNNs) to classify microplastic particles based on spectral and morphological fluorescence data.

• Develop and maintain modular analysis pipelines in Python or MATLAB, integrating data preprocessing, feature extraction, and classification for hyperspectral and fluorescence lifetime datasets.
• Optimize algorithms for batch processing and scalability, enabling high-throughput, automated analysis of large image datasets from fluorescence microscopy.
• Integrate analysis pipelines with imaging hardware workflows, contributing to software automation for tile stitching, autofocus, and multichannel detection.
• Validate models and workflows using diverse, real-world sample matrices (e.g., drinking water, milk, blood), benchmarking against regulatory and ISO guidelines.
• Collaborate with a multidisciplinary team of microscopists, materials scientists, and environmental researchers to align data analysis with imaging protocols and sample preparation.
• Document, publish, and communicate your work, contributing to scientific publications, stakeholder presentations, and potential valorization or IP development.

• A PhD in data science, applied physics, chemistry, materials science, bioengineering, or a related field, with a strong focus on data-driven analysis.
• Proven expertise in processing and analyzing fluorescence microscopy data, with hands-on experience in spectral imaging, lifetime data, or multi-channel image datasets.
• Solid background in chemometrics, machine learning, or deep learning, particularly for classification, clustering, or pattern recognition in large datasets.
• Proficiency in Python, MATLAB, or similar platforms used for image analysis, data modeling, and algorithm development.
• Experience with environmental analysis or microplastic research is a plus but not required.
• Strong analytical and problem-solving skills, ability to translate data into insights, and motivation to contribute to a multidisciplinary research and innovation environment.
• A publication track record in relevant areas, and a proactive, solution-oriented mindset with an interest in technology valorization and applied research.

The Roeffaers Lab at KU Leuven develops cutting-edge microscopy techniques to address key challenges in environmental science, catalysis, and biomedical research. Our team specializes in fluorescence and Raman-based approaches, integrating advanced microscopic analysis to gain molecular-level insights into complex materials and systems. The lab is internationally recognized for its expertise in correlative imaging and materials science., A dynamic research environment with state-of-the-art facilities and close collaborations with industry and governmental stakeholders.An opportunity to contribute to high-impact environmental and public health innovations, shaping the future of microplastics detection methodologies.Support for professional development, networking, and career advancement.