Nina Andrejevic

Assistant Computational Scientist • Argonne National Laboratory

Hi! I'm Nina, an Assistant Computational Scientist at Argonne National Laboratory working at the intersection of machine learning and materials characterization. My research focuses on developing physics-aware deep learning models to assist the analysis of X-ray scattering and spectroscopic measurements of nanoscale materials. Alongside my research, I'm also enthusiastic about science communication through teaching and scientific data visualization.

Google Scholar LinkedIn GitHub

Workshops and Interactive Tutorials

BLEND workflow.

BLEND: Building Latent Equations of Nanoscale Dynamics

Interactive tutorial illustrating how to combine neural ordinary differential equations with differentiable forward simulations of coherent scattering experiments to learn the governing equations.

View Materials
AI/ML workflow for image classification.

Introduction to AI/ML Applications for X-ray Experiments

Tutorial demonstrating the application of AI/ML tools to automate and accelerate an example X-ray experimental workflow.

View Materials
Chaotic attractor generative art.

Generative Art & Scientific Visualization

Workshop materials exploring algorithmic art, scientific visualization, and generative models through interactive notebooks, covering such topics as GANs, fractals, pattern-forming systems, and chaos theory.

E(3)NN architecture for predicting phonon DoS.

Euclidean Neural Networks for Predicting Phonon Density of States

Tutorial demonstrating how equivariant neural networks can be trained in a data efficient manner to predict the phonon density of states.

View Materials
Comparison between neural ODEs and PINNs.

Introduction to Scientific Machine Learning

A tutorial comparing the implementation and application of Neural ODEs and Physics-Informed Neural Networks.

View Materials

Data Visualization

Optical absorption palette visualization
Optical absorption palette for metal oxides. Sunburst plots of the optical absorbance spectra for representative metal oxides, grouped by constituent element and composition. Color encodes absorbance intensity across energy while angular sectors denote compositional variation. Visualization of the dataset from Stein et al., Scientific Data 6, 9 (2019). In collaboration with Jovana Andrejevic Kim.
Interstitial network radii visualization
Interstitial network bottleneck radii for Li-containing compounds. A periodic-table–based summary of the average interstitial bottleneck radius RT in Li-containing materials, where each element's annulus encodes the mean threshold radius and its variability (±1σ) across compounds; colors indicate RT, and the histogram shows the distribution stratified by interstitial network dimensionality. Visualization of the dataset from He et al., Scientific Data 7, 153 (2020). In collaboration with Jovana Andrejevic Kim.
Nobel laureates visualization
Streams of thought in Nobel laureates' scientific writing. Streamgraphs trace the temporal evolution of frequently used terms in publication titles by Nobel Prize winners across chemistry, physics, and medicine from the late 19th century to the present; stream width reflects word frequency, color denotes the time of first occurrence, and annotated branches highlight prominent concepts. Visualization of the dataset from Li et al., Scientific Data 6, 33 (2019). In collaboration with Jovana Andrejevic Kim.

Selected Publications

DynamiCXS workflow.

Data-driven discovery of dynamics from time-resolved coherent scattering

N. Andrejevic, et al. npj Computational Materials, 10(1):225, 2024.

View Publication
XAS workflow.

Machine-Learning Spectral Indicators of Topology

N. Andrejevic, J. Andrejevic, et al. Advanced Materials, 34(49):2204113, 2022.

View Publication
PNR workflow.

Elucidating proximity magnetism through polarized neutron reflectometry and machine learning

N. Andrejevic, Z. Chen, et al. Applied Physics Reviews, 9(1), 2022.

View Publication
Phonon DoS workflow.

Direct Prediction of Phonon Density of States With Euclidean Neural Networks

Z. Chen, N. Andrejevic, T. Smidt, et al. Advanced Science, 8(12):2004214, 2021.

View Publication