APPLICATION OF MACHINE LEARNING IN THE MODELING OF PHYSICAL PROCESSES
Keywords:
modeling, artificial neural networks, lattice Boltzmann model, machine learning, computational fluid dynamicsAbstract
The article gives an overview of modern approaches to the application of machine learning in the modeling of physical processes on the example of fluid motion in space. The structure and capabilities of artificial neural networks in the modeling of complex physical processes are described.
References
Hennigh O. (2017) Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks [Електронний ресурс] // arXiv.org. URL: https://arxiv.org/abs/cond-mat/0106542 (дата звернення: 24.04.2020).
Yang C., Yang X., Data‐driven projection method in fluid simulation [Електронний ресурс] // Wiley Online Library. URL: https://onlinelibrary.wiley.com/doi/abs/10.1002/cav.1695 (дата звернення: 25.04.2020).
Guo, Xiaoxiao & Li, Wei & Iorio, Francesco (2016). Convolutional Neural Networks for Steady Flow Approximation [Електронний ресурс] //ResearchGate URL: https://www.researchgate.net/publication/305997840_Convolutional_Neural_Networks_for_Steady_Flow_Approximation (дата звернення: 25.04.2020).
G. R. McNamara and G. Zanetti, Use of the boltzmann equation to simulate lattice-gas automata. Physical review letters, vol. 61, no. 20, p. 2332, 1988.
Foster N, Fedkiw R. Practical animation of liquids. In Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques. ACM, New York, USA, 2001; 23–30
