Prof. Dr. rer. nat. Stephan Doerfel
Data Science - especially Machine and Deep Learning
24149 Kiel
Room: C12-1.31
Prof. Dr. Doerfel holds a professorship in data science. At the Institute for Data Science (IfDS) at the Faculty of Media, he is responsible for the English-language modules "Mathematics and Multivariate Statistics," "Machine Learning," "Deep Learning," and "Advanced Topics in Data Mining." He is also one of the organizers of the "Application Project" module.
Information on the individual courses is available in the module database.
Stephan Doerfel studied mathematics (Diplom degree) with a minor in economics at the Technical University of Dresden and at Lund University (Sweden). He earned his Ph.D. from the University of Kassel in the field of knowledge discovery, where, as a research assistant, he focused on topics including the application of machine learning to metadata from scientific literature, recommender systems, scientometrics, and network analysis.
From 2016 to 2022, Stephan Doerfel worked for Micromata GmbH, where he served as a software engineer and data scientist on various projects. He also coordinated the company’s Tech Guild, promoting technical exchange and innovation.
Since 2021, he has been a professor of data science at Kiel University of Applied Sciences (HAW Kiel).
Stephan Doerfel is originally from Cottbus, where he attended the Max-Steenbeck-Gymnasium (graduated in 2002). Come rain or shine, he occasionally heads out into nature to go geocaching.
Stephan Doerfel’s research contributes to the field of applied data science. He focuses on applying machine learning and data analysis methods to address complex problems across a wide range of disciplines.
He also regularly serves as a member of program committees for international conferences (including ECML/PKDD and WebSci) and as a reviewer for academic journals (including Knowledge-Based Systems).
Research Areas:
Recommender Systems | Meta data and Altmetrics | Machine Learning | AI-Applications
Recent Publications
Predicting Part Quality Early during an Injection Molding Cycle.
International Polymer Processing, 39(2):210-219, 2024.
Lucas Bogedale, Stephan Doerfel, Alexander Schrodt and Hans-Peter Heim.
DOI: 10.1515/ipp-2023-4457
Exploring AI for Interpolation of Combine Harvester Yield Data.
In: C. Hoffmann, A. Stein, E. Gallmann, J. Dörr, C. Krupitzer und H. Floto (Herausgeber): Informatik in der Land-, Forst- und Ernährungswirtschaft, Band 344, Reihe Lecture Notes in Informatics, Seiten 107-118. 2024.
Lucas Johannsen, Sebastian Ramm, Yves Reckleben and Stephan Doerfel.
DOI: 10.18420/giljt2024_17
Online Prediction of Molded Part Quality in the Injection Molding Process Using High-Resolution Time Series.
Polymers, 15(4), 2023.
Lucas Bogedale, Stephan Doerfel, Alexander Schrodt and Hans-Peter Heim.
DOI: 10.3390/polym15040978
A complete list of his publications can be found on his ORCID-Profil.
Transfer & Collaborations
Stephan Doerfel has successfully supervised over 100 student projects and master’s theses. Almost all of these projects take the form of applied research and transfer projects carried out in direct collaboration with external partners - including companies, research institutions, medical facilities, and stakeholders from the public sector. The goal is always to tap into existing data potential, develop practical solutions, and demonstrate and scientifically validate their value.
Application Domains:
Agriculture | Education | Energy | Food | Human Resources | Maritime Logistics & Navigation | Media | Medicine (Imaging & Data Analysis) | Mobility & Transportation | Sports | Tourism | Utilities
Range of Methods:
- Data Engineering: ETL pipelines, data lakes, data architecture & design
- Data Analytics & BI: Monitoring, KPI systems, interactive dashboards
- Machine Learning: Clustering, classification, forecasting, time series analysis, deep learning, computer vision, recommender systems
- Advanced AI: Retrieval-Augmented Generation (RAG), foundation models