Katiana Kontolati

I like building models for scientific applications 🚀🤖🧬

2023 -
I am a Sr Machine Learning Researcher at Bayer Crop Science, specializing in artificial intelligence (AI) methods for crop improvement. My work involves investigating the scalable integration of multi-omics and phenotypic data using biologically-informed neural networks to drive accurate data-driven pipeline design decisions.
2019 - 2023
In my Ph.D. I specialized in high-dimensional surrogate modeling and operator learning as well as transfer learning and multi-domain learning for PDE applications including atmospheric fluid flows, brittle material fracture and modeling plasticity in amorphous solids. My research was generously supported by the U.S. Department of Energy. My adviser was Michael Shields, and I also had the pleasure to work with Michael Falk, Chris Rycroft and George Karniadakis on several exciting projects.

Along the way I squeezed 2 internships at DOE's Los Alamos National Laboratory in 2021 working on generative modeling for LIBS spectra from the ChemCam instrument onboard the NASA Curiosity rover and at GE Research in 2022 working on applcations of probabilistic machine learning on industrial gas turbines and small modular reactors.
2017 - 2019
MSc at the National Technical University of Athens where I worked on nonlinear dynamics and numerical bifurcation theory applied to biological systems.
2012 - 2017
BSc at the University of Thessaly with a major in civil engineering. My diploma thesis focused on finite element analysis for designing steel structures.
invited talks
publications
Learning nonlinear operators in latent spaces for real-time predictions of complex dynamics in physical systems
Nature Communications, 2024
Katiana Kontolati, Somdatta Goswami, George E Karniadakis, Michael D Shields
UQpy v4. 1: Uncertainty Quantification with Python
SoftwareX, 2023
Tsapetis, D., Shields, M.D., Giovanis, D.G., Olivier, A., Novak, L., Chakroborty, P., Sharma, H., Chauhan, M., Kontolati, K., Vandanapu, L., Loukrezis, D.
On the influence of over-parameterization in manifold based surrogates and deep neural operators
Journal of Computational Physics, 2023
Katiana Kontolati, Somdatta Goswami, Michael D Shields, George E Karniadakis
Deep transfer operator learning for partial differential equations under conditional shift
Nature Machine Intelligence, 2022
Somdatta Goswami, Katiana Kontolati, Michael D Shields, George E Karniadakis
Manifold learning-based polynomial chaos expansions for high-dimensional surrogate models
International Journal for Uncertainty Quantification, 2022
Katiana Kontolati, Dimitris Loukrezis, Ketson R. M. dos Santos, Dimitris D Giovanis, Michael D Shields
Neural density estimation and uncertainty quantification for laser-induced breakdown spectroscopy spectra
NeurIPS, 2021
Katiana Kontolati, Natalie Klein, Nishant Panda, Diane Oyen
Manifold learning for coarse-graining atomistic simulations: Application to amorphous solids
Acta Materialia, 2021
Katiana Kontolati, Darius Alix-Williams, Nicholas Boffi, Michael L Falk, Chris H Rycroft, Michael D Shields
Numerical analysis of mesenchymal stem cell mechanotransduction dynamics reveals homoclinic bifurcations
International Journal of Non-Linear Mechanics, 2019
Katiana Kontolati, Constantinos Siettos

Also on Google Scholar
misc unsorted