Bayesian Optimisation in catalysis

Forschungsthema/Bereich

Machine Learning and Catalysis

Typ der Abschlussarbeit

Master

Startzeitpunkt

-

Bewerbungsschluss

01.10.2028

Dauer der Arbeit

6 months

Beschreibung

Description
​Background and Motivation
​Discovering novel catalysts remains a fundamental challenge in chemical engineering and sustainable energy. Traditional experimental screening is extraordinarily slow. It consumes massive resources and relies heavily on chemical intuition rather than data driven design. We use Bayesian optimization to fundamentally accelerate this search process.
​Our research group stands out because we do not benchmark algorithms on synthetic toy problems. You will deploy your optimization frameworks directly onto real experimental data. Your code will actively dictate the next physical evaluations. This allows you to see exactly how your mathematical models perform under genuine experimental noise and physical constraints.
​Description and Tasks
​Within the scope of this Master thesis your code will bridge the gap between computer science and the real world. The scope of your thesis is entirely flexible. The possibilities within our framework are vast. We can focus on deep algorithmic refinement or surrogate modeling or physicochemical feature engineering or thermodynamic constraint handling. We will define the specific research question together based on your background and our active experimental collaborations.
​Start of the thesis is possible continuously.

Voraussetzung

Voraussetzungen an Studierende

• - Background in Chemical Engineering or Computational Data Science or Materials Science or similar background.
• ​- High motivation to bridge the gap between abstract machine learning and applied physical chemistry
• ​Ambitious mindset and the willingness to learn across disciplines
• - ​A natural aptitude for materials science or process engineering or applied mathematics is highly advantageous
• ​
• You do not need to be a master programmer or a catalysis expert on day one.
• ​We offer excellent supervision and the opportunity to work in a highly interdisciplinary and communicative environment. You will never code in isolation because we talk constantly to ensure our algorithms respect chemical reality.
• ​-Start of the thesis is possible immediately.
• ​-Supervision is possible in English or German.
• ​If you are interested or have questions please contact Torben Tiezema at torben.tiezema@kit.edu.

Studiengangsbereiche

• Ingenieurwissenschaften
  Chemieingenieurwesen & Verfahrenstechnik
  Materialwissenschaft & Werkstofftechnik
  Computer Science
• Naturwissenschaften und Technik
  Computational and Data Sience

Betreuung

Titel, Vorname, Name

Torben, Tiezema

Organisationseinheit

Institut für Katalyseforschung und –technologie (IKFT)

E-Mail Adresse

Torben.tiezema@kit.edu

Link zur eigenen Homepage/Personenseite

Website

Bewerbung per E-Mail

Bewerbungsunterlagen

• Anschreiben
• Lebenslauf

E-Mail Adresse für die Bewerbung
Senden Sie die oben genannten Bewerbungsunterlagen bitte per Mail an Torben.tiezema@kit.edu


Zurück