Andreja Stojić

Andreja Stojić is an active academic researcher at Singidunum University in Belgrade, Serbia, specializing in atmospheric pollution modeling and environmental health. Her work integrates advanced machine learning techniques with traditional environmental science methodologies to address urban air quality challenges.

• Born January 3, 1976 in Jagodina, Serbia
• Doctoral studies (2007-2015) in Theoretical Physics/Atomic and Molecular Physics at University of Belgrade
• Bachelor studies (1998-2007) in Applied Physics and Informatics at University of Belgrade

Her primary research focuses on atmospheric pollution dynamics, particularly PM2.5-bound polycyclic aromatic hydrocarbons (PAHs), volatile organic compounds (VOCs), and their health implications. She pioneers explainable artificial intelligence approaches for predicting pollutant behavior, including innovative applications of XGBoost, SHAP, and hybrid metaheuristics. Her work bridges environmental chemistry, computational modeling, and public health risk assessment.

Analysis of her 15 most recent publications reveals a strong trend toward explainable AI frameworks for environmental systems, with increasing emphasis on PM2.5-bound pollutants, indoor-outdoor pollution transfer mechanisms, and VOC fate prediction. Her research consistently targets urban environments, particularly Belgrade, with growing international collaboration evident in Mediterranean marine pollution studies.

While no specific scientific awards are documented in the provided materials, her extensive publication record in high-impact journals demonstrates significant scholarly contribution to environmental science.

Dr. Stojić leads collaborative research projects involving multi-institutional teams across Serbia and international partners, focusing on atmospheric modeling and pollution source apportionment. Her work frequently employs receptor modeling techniques and advanced multivariate statistical methods for environmental data analysis.

Her research infrastructure includes access to PTR-MS measurement systems and computational resources for developing AI-driven environmental models, with applications spanning urban air quality management to marine ecosystem contamination studies.