Student, excited about her awesome thesis.

Theses

Department of Stochastic Simulation and Safety Research for Hydrosystems

Stochastics

We offer theses in different research areas.

Procedure

The theses advertised below are intended to provide pointers for topics of possible final theses at our department. Depending on the language capabilities of the supervisor, the work can usually be carried out in German or English.

Often, we can also tailor the focus specifically for project theses, bachelor theses, research modules and master theses.

If you are interested in one of our topics, but the most suitable work for you is not advertised, feel free to contact us anyway -- you will find a contact to the advertised work in the respective notice board.

Unsolicited applications are also possible at any time. 

Topics

Topic Tags Advisor
Moment Matching for Uncertainty Quantification in Process Modelling machine learning, geostatistical modelling, process modelling Stefania Scheurer
Deep-aPC-NN vs. Kolmogorov Arnold networks (KAN) deep learning, PCE Nils Wildt
Sampling with Noisy Gradients MCMC,
sampling		 Tim Brünnette

Neural Network Approaches to Climate-Driven Water Demand Modeling

neural networks, climate change

 Philipp Hofmann
Exploring Polynomial Chaos Expansion as an Extrapolative Enhancement to Gaussian Process Regression in Water Demand Modeling

PCE, extrapolation, machine learning, climate change

 Philipp Hofmann
Application of SARIMAX Models to Climate-Driven Water Demand Forecasting

hydrological modeling, time series modeling, climate change

 Philipp Hofmann
Impact of Temporal Dependencies on Predictive Models for Water Consumption in Southern Germany

machine learning, lagged variables, climate change

 Philipp Hofmann
Deep Learning of Trend Function in Non-Stationary Groundwater Process

machine learning, groundwater modelling

 Waqas Ahmed
Hydrologie, Wasser- und Umweltsystemmodellerierung hydrological modeling,
geostatistics,
precipitation modeling,
CO2 storage modeling, geothermal modeling 		 Jochen Seidel
Learning PFAS isotherms with Universal Differential Equations finite volume method,
mechanism learning, surrogates		 Nils Wildt
Stochastic Simulation of Debris Distribution after Airplane Crashes stochastics, programming, uncertainty Tim Brünnette
Predicting Fracture Path Statistics stochastics,
statistics,
machine learning,
CNNs		 Tim Brünnette

 
To the top of the page