A Novel Method for Virtual Real-Time Cumuliform Fluid Dynamics Simulation Using Deep Recurrent Neural Networks

Guardado en:
Detalles Bibliográficos
Publicado en:Mathematics vol. 13, no. 17 (2025), p. 2746-2777
Autor principal: Jiménez de Parga Carlos
Otros Autores: Calo, Sergio, Cuadra, José Manuel, García-Vico, Ángel M, Pastor Vargas Rafael
Publicado:
MDPI AG
Materias:
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 3249691798
003 UK-CbPIL
022 |a 2227-7390 
024 7 |a 10.3390/math13172746  |2 doi 
035 |a 3249691798 
045 2 |b d20250101  |b d20251231 
084 |a 231533  |2 nlm 
100 1 |a Jiménez de Parga Carlos  |u National Distance Education University (UNED), 30203 Cartagena, Spain 
245 1 |a A Novel Method for Virtual Real-Time Cumuliform Fluid Dynamics Simulation Using Deep Recurrent Neural Networks 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a The real-time simulation of atmospheric clouds for the visualisation of outdoor scenarios has been a computer graphics research challenge since the emergence of the natural phenomena rendering field in the 1980s. In this work, we present an innovative method for real-time cumuli movement and transition based on a Recurrent Neural Network (RNN). Specifically, an LSTM, a GRU and an Elman RNN network are trained on time-series data generated by a parallel Navier–Stokes fluid solver. The training process optimizes the network to predict the velocity of cloud particles for the subsequent time step, allowing the model to act as a computationally efficient surrogate for the full physics simulation. In the experiments, we obtained natural-looking behaviour for cumuli evolution and dissipation with excellent performance by the RNN fluid algorithm compared with that of classical finite-element computational solvers. These experiments prove the suitability of our ontogenetic computational model in terms of achieving an optimum balance between natural-looking realism and performance in opposition to computationally expensive hyper-realistic fluid dynamics simulations which are usually in non-real time. Therefore, the core contributions of our research to the state of the art in cloud dynamics are the following: a progressively improved real-time step of the RNN-LSTM fluid algorithm compared to the previous literature to date by outperforming the inference times during the runtime cumuli animation in the analysed hardware, the absence of spatial grid bounds and the replacement of fluid dynamics equation solving with the RNN. As a consequence, this method is applicable in flight simulation systems, climate awareness educational tools, atmospheric simulations, nature-based video games and architectural software. 
653 |a Software 
653 |a Accuracy 
653 |a Computer & video games 
653 |a Physics 
653 |a Deep learning 
653 |a Flight simulation 
653 |a Fluid dynamics 
653 |a Neural networks 
653 |a Recurrent neural networks 
653 |a Computer simulation 
653 |a Numerical analysis 
653 |a Solvers 
653 |a Algorithms 
653 |a Methods 
653 |a Animation 
653 |a Real time 
653 |a Energy consumption 
653 |a Computer graphics 
653 |a Clouds 
653 |a Cultural heritage 
653 |a Run time (computers) 
700 1 |a Calo, Sergio  |u Faculty of Physics, University of Santiago de Compostela (USC), 15705 Santiago de Compostela, Spain; sergio.calo@upf.edu 
700 1 |a Cuadra, José Manuel  |u Department of Artificial Intelligence, National Distance Education University (UNED), 28040 Madrid, Spain; jmcuadra@dia.uned.es 
700 1 |a García-Vico, Ángel M  |u Department of Computer Science, Research Institute in Data Science and Computational Intelligence, University of Jaén, 23071 Jaén, Spain; agvico@ujaen.es 
700 1 |a Pastor Vargas Rafael  |u Department of Communication Systems and Control, National Distance Education University (UNED), 28040 Madrid, Spain; rpastor@scc.uned.es 
773 0 |t Mathematics  |g vol. 13, no. 17 (2025), p. 2746-2777 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3249691798/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3249691798/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3249691798/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch