Beatriz Moya
Papers
2
Total Citations
47
H-Index
2
About
Beatriz Moya is a researcher working at the intersection of computational mechanics, machine learning, and physics-informed modeling, with a particular focus on fluid dynamics and digital twin technologies. Her work addresses one of the most challenging frontiers in modern engineering: enabling machines to learn, reason about, and predict complex physical phenomena in real time. Her most notable contribution, "Physically sound, self-learning digital twins for sloshing fluids" (2020, 29 citations), introduced a groundbreaking framework for developing digital twins capable of autonomously learning fluid sloshing behavior — a problem with direct applications in robotic manipulation and simulation-assisted decision making. Building on this foundation, her 2023 work on thermodynamics-informed active learning (18 citations) advanced the field further by embedding physical laws into perception and reasoning systems for fluid analysis, pushing the boundaries of what robots and computational models can infer about their physical environment. A defining characteristic of Moya's research is her commitment to physically consistent learning — ensuring that data-driven models respect fundamental laws such as thermodynamics. This philosophy positions her as an important voice in the growing field of scientific machine learning, offering rigorous, interpretable approaches that bridge theoretical physics and practical artificial intelligence applications.
Research Focus
Key Achievements
Top Papers
- 1Physically sound, self-learning digital twins for sloshing fluids29 citations · 2020
- 2