Professor Adjunto III · UFRJ
Adriano M. A. Côrtes
Professor and Interdisciplinary Researcher working between Computational Science & Engineering and AI/ML. I came up through Computational Mechanics and HPC, and over time machine learning became impossible to separate from the work. Most of what I do now lives at that boundary: building physically grounded surrogate models using Scientific Machine Learning and deep generative models (mainly flow-based), applied across domains like CO₂ sequestration, complex flows, and systems biology. I supervise graduate research and collaborate with industry partners, which keeps the work tied to problems that actually need solving.
Professor at the Department of Applied Mathematics (Mathematics Institute) and PESC/COPPE (Systems and Computer Engineering Program) at the Federal University of Rio de Janeiro (UFRJ).
Research Areas
Scientific Machine Learning (SciML)
Surrogate Models based on modern neural network architectures — PINNs, Neural Operators, GNNs, etc, and hybrid SciML approaches incorporating physical laws and conservation principles.
High-Performance Computing
Scalable finite element solvers, parallel algorithms, and isogeometric analysis frameworks. Co-developer of PetIGA and EdgeCFD.
Systems Biology and AI for Healthcare
Applying computational methods to single-cell RNA sequencing (scRNA-seq) data for cancer research, including glioblastoma multiforme dynamics and epigenetic landscape modeling. Recently applying LLM+RAG in breast cancer guideline assistance OncoGuIA.
News
2025
New paper — “Data-Driven Diffusion-Based Super-Resolution for Improvement of Reduced-Order Model Predictions in Fluid Dynamics” accepted at FUSION 2025, Rio de Janeiro.
2025
New paper in Finite Elements in Analysis and Design — “Advances in data-driven reduced order models using two-stage dimension reduction for coupled viscous flow and transport.”
2024
Workshop co-organizer — “Artificial Intelligence and High-Performance Computing for Advanced Simulations” at ICCS 2024.
2024
Two papers published on glioblastoma multiforme modeling using scRNA-seq data in Int. J. Molecular Sciences and Scientific Reports.
Affiliations
Universidade Federal do Rio de Janeiro
Instituto de Matemática Departamento de Matemática Aplicada
PESC/COPPE Programa de Engenharia de Sistemas e Computação