With the abundance of data offered by modern experimental and numerical approaches, fluid dynamics is in the enviable position of bridging the gap between traditional physics-based and purely data-driven modeling. The objective is to enable predictive and sufficiently robust models at a fraction of the computational cost of the high-fidelity, first principle-based models. To be effective, these models should embed physical constraints leading to hybrid (physics-based + data-driven) modeling. These new approaches aim to increase our understanding of the fundamental mechanisms encountered in engineering, geophysical, and biomedical applications, but also to develop efficient optimization and control strategies with the extensive use of machine learning.
The problems encountered in the real world (gas turbine turbomachinery, oil reservoirs production, water resource systems, cardiovascular flow modeling, and turbulence modeling to name a few) are intrinsically multi-physical and multi-scale, making them extremely difficult to understand and to model. Knowing the first principle equations is far from being sufficient because many parameters may display a high degree of uncertainty or can even be unknown. The recent and rapid increase in the availability of data has spurred the development of many data-driven methods for modeling and predicting dynamics, leading even to the discovery of physical models. This ensemble of data-driven modeling techniques seeks to exploit underlying low-dimensionality and sparsity in data, while also dealing with corrupted or under-resolved data. If machine learning has emerged as a promising alternative to knowledge models, interpretability remains crucial to developing human trust and process safety. For this reason, physics-informed machine learning was introduced to best incorporate prior knowledge of the physical laws coming from the observational or theoretical understanding of the world. We have thus recently entered in an age where approaches based on physical modeling and machine learning can be viewed as complementary, aiming at improving our understanding of nature and even at developing optimization strategies, such as flow control.
The aim of this Research Topic is to cover promising and novel research trends in fluid dynamics, from both classical physics-based modeling and data-driven approaches. Contributors from both academia and industry are welcomed to present their work. Areas covered in this Research Topic may include, but are not limited to:
• Machine learning
• Data mining
• Artificial intelligence
• Statistical Learning
• Data-driven modeling
• Physics-based modeling
• Data assimilation
• Discovery of laws
• Symbolic regression
• Flow control and optimization
• Dimensionality reduction
• Reduced order models
• Uncertainty quantification
• Clustering
• Turbulence closure
With the abundance of data offered by modern experimental and numerical approaches, fluid dynamics is in the enviable position of bridging the gap between traditional physics-based and purely data-driven modeling. The objective is to enable predictive and sufficiently robust models at a fraction of the computational cost of the high-fidelity, first principle-based models. To be effective, these models should embed physical constraints leading to hybrid (physics-based + data-driven) modeling. These new approaches aim to increase our understanding of the fundamental mechanisms encountered in engineering, geophysical, and biomedical applications, but also to develop efficient optimization and control strategies with the extensive use of machine learning.
The problems encountered in the real world (gas turbine turbomachinery, oil reservoirs production, water resource systems, cardiovascular flow modeling, and turbulence modeling to name a few) are intrinsically multi-physical and multi-scale, making them extremely difficult to understand and to model. Knowing the first principle equations is far from being sufficient because many parameters may display a high degree of uncertainty or can even be unknown. The recent and rapid increase in the availability of data has spurred the development of many data-driven methods for modeling and predicting dynamics, leading even to the discovery of physical models. This ensemble of data-driven modeling techniques seeks to exploit underlying low-dimensionality and sparsity in data, while also dealing with corrupted or under-resolved data. If machine learning has emerged as a promising alternative to knowledge models, interpretability remains crucial to developing human trust and process safety. For this reason, physics-informed machine learning was introduced to best incorporate prior knowledge of the physical laws coming from the observational or theoretical understanding of the world. We have thus recently entered in an age where approaches based on physical modeling and machine learning can be viewed as complementary, aiming at improving our understanding of nature and even at developing optimization strategies, such as flow control.
The aim of this Research Topic is to cover promising and novel research trends in fluid dynamics, from both classical physics-based modeling and data-driven approaches. Contributors from both academia and industry are welcomed to present their work. Areas covered in this Research Topic may include, but are not limited to:
• Machine learning
• Data mining
• Artificial intelligence
• Statistical Learning
• Data-driven modeling
• Physics-based modeling
• Data assimilation
• Discovery of laws
• Symbolic regression
• Flow control and optimization
• Dimensionality reduction
• Reduced order models
• Uncertainty quantification
• Clustering
• Turbulence closure
