Optimization and interpretation of
Machine Learning models for spectral data
We invite you to our next webinar on Machine Learning methods and the interpretation of ML models developed on spectral databases on March 10, 2026 at 4 p.m. (CET).
Would you like to learn more about how to make your
Machine Learning models built on spectroscopic data more reliable?
This webinar is focusing on:
- Why and when use Machine Learning methods to analyze spetra
- How optimize the model understanding using interpretability methods to avoid the black-box effect of some methods (explainable Machine Learning)
- Use cases developed on spectral data
📆March 10, 2026
🕚 4.00pm (CET)
Webinar program:
- Why use Machine Learning (ML) models?
- The interest of ML models interpretability
- Overview of ML methods
- Principles and applications of kernel methods and neural networks
- Overview of interpretability methods of ML models
- Principles and applications of interpretability methods (SHAP, etc.) to spectroscopic data
- Q&A session

Dr. Astrid Maléchaux, Data Scientist at Ondalys for several years and expert in Machine Learning and model interpretability, will present this webinar. With her, you will discover how to avoid the black box effect of some Machine Learning models on spectral data and ensure the reliability of these models.
Experts in spectral calibration and in developing Machine Learning methods adapted to spectral data (NIR, MIR, Raman, …), Ondalys team supports you in analyzing your spectroscopic data and developing spectral calibrations.



