cv
General Information
Full Name | Miguel Angel Corrales |
Date of Birth | 11 August 1994 |
Languages | English, Spanish |
Education
- 2022 - Present
PhD
King Abdullah University of Science and Technology (KAUST), Kingdom of Saudi Arabia
- Earth Sciences and Engineering Program (ErSE)
- Machine Learning Track
- Deep Reservoir characterization and Uncertainty Quantification from macro scale rock imaging to reservoir scale characterization using Deep Learning framework and Deep Generative Models
- 2019-2021
Master of Science
King Abdullah University of Science and Technology (KAUST), Kingdom of Saudi Arabia
- Energy Resources and Petroleum Engineering Program (ERPE)
- Assessment of CO2 storage in saline aquifers in the Unayzah Reservoir, Central Arabia, Kingdom of Saudi Arabia.
- 2012-2017
Bachelor's degree
Universidad Central del Ecuador (UCE), Ecuador
- Strong Fundamentals about the different of Oil and Gas Supply Chain.
- Waterflooding study for reservoir development in Coca-Payamino field.
Honors and Awards
- 2022
- Hackathon KAUST NVIDIA 2022 Winner, Accelerating Scientific applications using GPUs.
- 2022
- Petrobowl Team (KAUST) - Top 3 MENA Qualifiers.
- 2022
- BEST IN SHOW, Hackathon - Explainable A.I., EAGE ANNUAL 2022, Madrid-Spain.
- 2021
- Third Place e-Poster competition. KAUST Research Conference - Enabling CO2 Geological Storage Within a Low-Carbon Economy
- 2020
- Petrobowl Team (KAUST) - Top 3 MENA Qualifiers.
- 2016
- Academic Exchange Recognition, Universidad Central del Ecuador.
- 2012-2017
- Academic Excellence Scholarship, Universidad Central del Ecuador.
Academic Interests
-
Seismic Reservoir Characterization.
- Elastic properties from pre-stack seismic data.
- Petrophysical properties from pre-stack seismic data.
- Cascade inversion, joint inversion, data-driven inversion.
- CO2 monitoring.
-
Fluid Flow in Porous media.
- Fluid flow in oil and gas reservoirs at darcy-scale.
- Fluid flow in porous media.
- Fluid flow in naturally fractured reservoirs.
- Compositional fluid flow for CO2 sequestration in geological formations.
-
Deep Learning and Generative models.
- Supervised Learning, Unsupervised Learning.
- Generative adversarial networks and diffusion models.
- Explainable Artificial intelligence.