🔬 Research

My current postgraduate research explores the application of high performance computing (HPC) and machine learning (ML) methodologies to scientific problems, with a focus on areas like radiation schemes in climate prediction models.

Updates¶

• Dez 2025: Renewal of the AMPEMI project at SDumont.
• Oct 2025: Paper accepted at CIACA.
• Aug 2024: Approved in the Exam Proposal at INPE.
• May 2024: Approved in the Qualification Proposal at INPE.
• Feb 2023: I started my PhD at INPE.
• Mar 2022: I graduated from my MSc.
• Jul 2021: Paper accepted at BreSci.
• Jun 2021: Paper accepted at Revista Cereus.
• Feb 2019: I started my MSc at INPE.

Research interests¶

• New technologies and methods applied in HPC.
• Solution of scientific and engineering problems using HPC.

Projects¶

• PIML - application of physics-based machine learning in solving scientific problems.
• MPI-based HPC Approaches - use of recent high-performance computing resources in solving scientific problems.

I maintain a repository on Github with my open source projects that I have been developing over time for various purposes: https://github.com/efurlanm/ . The current main research repository is: https://github.com/efurlanm/ml/. The research also uses the LNCC supercomputer Santos Dumont under the project AMPEMI.

Publications¶

Publications related to my postgraduate course.

• MIRANDA, E. F.; SOUTO, R. P.; STEPHANY, S. Descoberta de parâmetro na equação 2D de burgers por rede neural informada pela física. Dec. 2025. CIACA CIAWI 2025 Proceedings. Lisboa: IADIS, Dec. 2025. pp. 87–94. Available at: https://www.iadisportal.org/ciaca-ciawi-2025-proceedings.
• MIRANDA, E. F. Common MPI-based HPC Approaches in Python Evaluated for Selected Test Cases. 2022. Master’s Thesis (Applied Computing) - National Institute for Space Research (INPE), São José dos Campos, 2022. Available at: http://urlib.net/ibi/QABCDSTQQW/46C4U9H.
• MIRANDA, E. F.; STEPHANY, S. Common MPI-Based Solutions for High-Performance Processing in Python Evaluated on Selected Test Cases. [Presentation]. 2022. DOI: https://doi.org/10.5281/zenodo.10676832.
• MIRANDA, E. F.; STEPHANY, S. Comparison of High-performance Computing Approaches in the Python Environment for a Five-point Stencil Test Problem. In: XV Brazilian E-Science Workshop (CSBC), 2021, Online. Proceedings [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021. pp. 33–40. DOI: https://doi.org/10.5753/bresci.2021.15786.
• MIRANDA, E. F.; STEPHANY, S. Common HPC Approaches in Python Evaluated for a Scientific Computing Test Case. Revista Cereus, vol. 13, no. 2, pp. 84–98, 2021. DOI: https://doi.org/10.18605/2175-7275/cereus.v13n2p84-98.
• MIRANDA, E. F.; STEPHANY, S. Comparison of high-performance computing approaches in the Python environment for a five-point stencil case study. In: XV Brazilian e-Science Workshop (BreSci), 2021, Online. [Presentation]. DOI: https://doi.org/10.5281/zenodo.10672456.

Manuscripts¶

Manuscripts related to my postgraduate course.

• MIRANDA, E. F.; SANTOS, L. B. L.; STEPHANY, S. Data-Driven Parameter Discovery of a One-Dimensional Burgers’ Equation Using a Physics-Informed Neural Network. [Manuscript]. 2023. DOI: https://doi.org/10.5281/zenodo.10676770. Available at: https://efurlanm.github.io/425/.
• MIRANDA, E. F. Solution of a One-Dimensional Viscous Burgers' Equation Using a Physics-Informed Neural Network and a Gaussian Quadrature Method. [Manuscript]. 2022. DOI: https://doi.org/10.5281/zenodo.10676900. Available at: https://efurlanm.github.io/421/.
• MIRANDA, E. F. Comparison of CNN and MLP Artificial Neural Network Models for an Optical Character Recognition Test Case. [Manuscript]. 2022. DOI: https://doi.org/10.5281/zenodo.10676917.

Address¶

National Institute for Space Research (INPE)
1758 Astronautas Avenue
São José dos Campos, SP 12210-000

Contact¶

✉ mailto:efurlanm@gmail.com

Last edited: 2026-08-15