Ing. Antonie Brožová
Ph.D. student

Biography
Publication list
EXPERIENCE
March 2021 – present: PhD student, Institute of Information Theory and Automation, CAS,
Department of Adaptive Systems
April, 2020 – February 2021: Research assistant, Institute of Information Theory and Automation,
CAS, Department of Adaptive Systems
TEACHING
Fall semester 2021, 2022, 2023: labs in Calculus 1, FNSPE CTU
EDUCATION
March, 2021 - present: CTU, Faculty of Nuclear Sciences and Physical Engineering - PhD programme:
Mathematical Engineering
2018 – Feb, 2021: CTU, Faculty of Nuclear Sciences and Physical Engineering– master programme:
Applied Mathematical Stochastic Methods
- Fall semester 2019: Kansas State University, USA – courses taken: Applied Data Mining/
Machine Learning and Predictive Analytics, Mathematics of Data and Networks, Bayesian
Inference, Experimental Design for Product Development and Quality Improvement
2015 – 2018: CTU, Faculty of Nuclear Sciences and Physical Engineering – bachelor programme:
Mathematical Engineering with focus on Applied Mathematical Stochastic Methods
LANGUAGES
English – FCE (B2, 2014), compulsory school course with an exam (C1 Academic English)
German – passive knowledge, compulsory school course (intermediate level)
SKILLS
Julia, MATLAB, R, C++
E-mail: antonie.brozova@gmail.com
Journal articles
- Spatial-temporal source term estimation using deep neural network prior and its application to Chernobyl wildfires, Journal of Hazardous Materials 448 Download Download DOI: 10.1016/j.jhazmat.2025.137510 [2025] :
Other publications
- Estimation of Spatial-temporal Source Term of Chernobyl Wildfires using Deep Neural Network Prior, EGU General Assembly 2025 Download DOI: 10.5194/egusphere-egu25-11939 [2025] :
- Bayesian methods in neural networks for inverse atmospheric modelling, Stochastic and Physical Monitoring Systems 2024 Download Download [2024] :
- Estimation of spatio-temporal source of microplastics using Bayesian Neural networks, EGU General Assembly 2024 Download DOI: 10.5194/egusphere-egu24-5960 [2024] :
- Avoiding Undesirable Solutions of Deep Blind Image Deconvolution, Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2024), p. 559-566, Eds: Radeva Petia, Furnari Antonino, Bouatouch Kadi, Sousa A. Augusto Download Download DOI: 10.5220/0012397600003660 [2024] :