Machine-learning based interpretation of infrared spectroscopy in heterogenous catalysis

PhD n°4

Eligibility:

EU mobility rules apply. In principle, applicants can have any nationality and any current residence (although immigration rules apply, favoring
EU applicants). Candidates who have already been awarded a PhD degree are not eligible. In addition, candidates who have already spent more than 12 months in the Finland within the last 3 years are not eligible (unless as part of a procedure for obtaining refugee status under the Geneva Convention).

Objectives:

To develop a data-driven approach for analysing infrared spectra of in-situ catalyst characterization. Heterogeneous catalysis is an important industrial process for the production of chemical compounds and the conversion of chemicals (in e.g., car exhausts). Infrared spectroscopy is one of the characterization techniques that can provide in-situ and real-time information on catalyst operation. To facilitate spectra interpretation with the required quantum mechanical insight but without its high computational cost, we will develop a machine-learning model based on DFT data. We will adapt a recently developed global atomic structure descriptor and a regression model and parameterize it for platinum and rhodium catalysts. We will then predict the infrared spectra of chemical species (e.g., CO, CO2, NOx, H2O and their reaction intermediates) and develop a deconvolution tool with our collaborators for the analysis of in-situ and operando spectra.

  • Generate high-throughput DFT data sets for structure-spectra mapping
  • Adapt our recently developed global machine-learning model for atomic structures to infrared spectra and validate it for catalysts
  • Generate dataset of infrared spectra for reactants and reaction intermediates
  • Develop spectra analysis tool

Expected Results:

  • Large materials datasets for data driven catalysis and machine learning
  • Machine-learning model for fast infrared spectra predictions of catalyst materials
  • Spectra deconvolution tool for real-time analysis of in-situ experiments

Planned secondment(s): 7 months

  • Intersectoral: TME: H. Nguyen, M24-26; application of spectral analysis tool in R&D
  • Academic MLU: M18-20 methodological exchange and comparison of ML-based vibrational
    spectroscopy approaches

Enrolment in Doctoral degree(s):

Aalto University

Contact:

Rinke Patrick
patrick.rinke@aalto.fi

PhD n°: PhD n°4
Country: Finland
This job is no longer accepting applications.