Sai Karthikeya Vemuri, M.Sc.
Sai Karthikeya Vemuri
Address: Computer Vision Group
Department of Mathematics and Computer Science
Friedrich Schiller University of Jena
Ernst-Abbe-Platz 2
07743 Jena
Germany
Phone: +49 (0) 3641 9 46416
E-mail: sai (dot) karthikeya (dot) vemuri (at) uni-jena (dot) de
Room: 1212
Links:
Curriculum Vitae
since 2022 PhD Student
Computer Vision Group, Friedrich Schiller University Jena
Data Analysis and Intelligence Group, German Aerospace Center (DLR), Institute for Data Science, Jena
Research topic: “MELODI: Machine-learning-based analysis of fan noise source dependencies on aerodynamic
inlet disturbances”
2019 – 2022 Masters in Computational Materials Sciences
TU Bergakademie Freiberg
Master Thesis: “Machine Learning assisted understanding of RVE size dependent uncertainties and
corresponding hierarchy of properties”
2015 – 2019 Bachelors in Mechanical Engineering
Osmania University, Hyderabad, India
Research Interests
  • Applied DL/ML in Physics and Engineering
  • Knowledge Integration
  • Causality
Projects
MELODI: Machine-learning-based Analysis of Fan Noise Source Dependencies on Aerodynamic Inlet Disturbances

Development and testing of machine learning methods to investigate dependencies of fan noise sources on aerodynamic inflow disturbances. These physical relationships have not yet been investigated using the modern methods that have been developed in the field of artificial intelligence and machine learning. Existing methods for the integration of prior knowledge into machine learning procedures, as well as causality investigations are tested and extended for this specific application domain.

Publications
2024
Gideon Stein, Sai Karthikeya Vemuri, Yuanyuan Huang, Anne Ebeling, Nico Eisenhauer, Maha Shadaydeh, Joachim Denzler:
Investigating the Effects of Plant Diversity on Soil Thermal Diffusivity Using Physics- Informed Neural Networks.
ICLR Workshop on AI4DifferentialEquations In Science (ICLR-WS). 2024.
[bibtex] [pdf] [web]
Sai Karthikeya Vemuri, Tim Büchner, Joachim Denzler:
Estimating Soil Hydraulic Parameters for Unsaturated Flow using Physics-Informed Neural Networks.
International Conference on Computational Science (ICCS). Pages 338-351. 2024.
[bibtex] [doi] [abstract]
Sai Karthikeya Vemuri, Tim Büchner, Julia Niebling, Joachim Denzler:
Functional Tensor Decompositions for Physics-Informed Neural Networks.
International Conference on Pattern Recognition (ICPR). 2024. (accepted at ICPR)
[bibtex] [web] [doi] [code] [abstract]
2023
Sai Karthikeya Vemuri, Joachim Denzler:
Gradient Statistics-Based Multi-Objective Optimization in Physics-Informed Neural Networks.
Sensors. 23 (21) : 2023.
[bibtex] [pdf] [web] [doi] [abstract]
Sai Karthikeya Vemuri, Joachim Denzler:
Physics Informed Neural Networks for Aeroacoustic Source Estimation.
IACM Mechanistic Machine Learning and Digital Engineering for Computational Science Engineering and Technology. 2023.
[bibtex] [web] [doi] [abstract]