A review of deep learning for super-resolution in fluid flows DOI
Filippos Sofos, Dimitris Drikakis

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(4)

Published: April 1, 2025

Integrating deep learning with fluid dynamics presents a promising path for advancing the comprehension of complex flow phenomena within both theoretical and practical engineering domains. Despite this potential, considerable challenges persist, particularly regarding calibration training models. This paper conducts an extensive review analysis recent developments in architectures that aim to enhance accuracy data interpretation. It investigates various applications, architectural designs, performance evaluation metrics. The covers several models, including convolutional neural networks, generative adversarial physics-informed transformer diffusion reinforcement frameworks, emphasizing components improving reconstruction capabilities. Standard metrics are employed rigorously evaluate models' reliability efficacy producing high-performance results applicable across spatiotemporal data. findings emphasize essential role representing flows address ongoing related systems' high degrees freedom, precision demands, resilience error.

Language: Английский

Artificial intelligence forecasting and uncertainty analysis of meteorological data in atmospheric flows DOI
Nicholas Christakis, Dimitris Drikakis, Panagiotis Tirchas

et al.

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(3)

Published: March 1, 2025

This study investigates using the long short-term memory model, a recurrent neural network, for forecasting time series data in atmospheric flows. The model is specifically employed to handle intrinsic temporal dependencies and nonlinear patterns related wind, temperature, relative humidity. research incorporates preprocessing methodologies such as normalization sequence generation enhance model's learning process alignment with fluid dynamics characteristics. further examines strategies optimizing performance, including hyperparameter tuning feature selection, while considering various compositions that capture complexities of behavior. Key factors are analyzed evaluate their impact on ability predict dynamic flow patterns. effectiveness evaluated statistical visual methods, highlighting its capabilities accurately trends variations within meteorological datasets. findings indicate can significantly improve predictive accuracy applications, offering valuable insights into nature flows importance inputs modeling techniques.

Language: Английский

Citations

0
A review of deep learning for super-resolution in fluid flows DOI
Filippos Sofos, Dimitris Drikakis

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(4)

Published: April 1, 2025

Integrating deep learning with fluid dynamics presents a promising path for advancing the comprehension of complex flow phenomena within both theoretical and practical engineering domains. Despite this potential, considerable challenges persist, particularly regarding calibration training models. This paper conducts an extensive review analysis recent developments in architectures that aim to enhance accuracy data interpretation. It investigates various applications, architectural designs, performance evaluation metrics. The covers several models, including convolutional neural networks, generative adversarial physics-informed transformer diffusion reinforcement frameworks, emphasizing components improving reconstruction capabilities. Standard metrics are employed rigorously evaluate models' reliability efficacy producing high-performance results applicable across spatiotemporal data. findings emphasize essential role representing flows address ongoing related systems' high degrees freedom, precision demands, resilience error.

Language: Английский

Citations

0