Spectroscopic Modelling Using Python
Description
The Spectroscopic Modelling Using Python training is a hands-on course for building custom spectroscopic models using Python. Techniques like NIR and Raman spectroscopy are powerful tools for non-destructively evaluating chemical and physical sample properties, but proper data processing is key to unlocking their full potential.
This course will be given by experts from elegent, a spin-off company from Ghent University offering modelling services for the pharmaceutical and food industries.
This course covers essential steps for creating reliable models, introducing key Python modules and demonstrating their use through a pharmaceutical manufacturing case study. Participants will gain a thorough understanding of both theoretical concepts and their practical application in Python.
Programme
The course covers (but is not limited to) the following steps:
- Dataset preparation and visualization of the spectra
- Preprocessing evaluation:
- The evaluation of the most suitable preprocessing techniques (e.g., spectral range trimming, normalization, first derivative, …)
- Model building using Partial least square regression:
- Determination of the number of principal components
- Applying cross-validation to avoid under- and overfitting
- Outlier assessment:
- To detect and flag anomalous data points that may arise due to measurement errors, instrumental noise, or other sources
- Model analysis:
- o Various visualization to interpret the model
- o Calculation of the predictions error
Remarks
Additional information
- One week prior to the course, the registered participants will receive further information (directions, parking availabilities, course material).
- Upon completion of the training, a certificate of attendance will be made available on the platform.
- Additionally, the participant will receive an evaluation form to provide feedback on this training.
Annulation/Cancelation
Registration is possible up to one week before the day of the respective session.
Registrations can only be canceled by email, up to one week before the day of the respective course. After that, the full registration fee will still be due in case of cancellation.
A participant unable to attend can always be replaced by a colleague or can request a voucher for a similar training on a later date!
A minimum attendance of 5 participants is required to conduct the training. Otherwise the organization reserves the right to reschedule or cancel the training!
