Back to publications

Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation

Mack, Julian and Arcucci, Rossella and Molina-Solana, Miguel and Guo, Yike
Computer Methods in Applied Mechanics and Engineering 372, 113291 (2020)

Abstract:

We propose a new ‘Bi-Reduced Space’ approach to solving 3D Variational Data Assimilation using Convolutional Autoencoders. We prove that our approach has the same solution as previous methods but has significantly lower computational complexity; in other words, we reduce the computational cost without affecting the data assimilation accuracy. We tested the new method with data from a real-world application: a pollution model of a site in Elephant and Castle, London and found that we could reduce the size of the background covariance matrix representation by \mathcalO(10^3) and, at the same time, increase our data assimilation accuracy with respect to existing reduced space methods.

Links:

DOI: 10.1016/j.cma.2020.113291
PDF: https://authors.elsevier.com/c/1bdjR_12dr5W8C

Bibtex:

@article{Mack2020,
  author = {Mack, Julian and Arcucci, Rossella and Molina-Solana, Miguel and Guo, Yike},
  title = {Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation},
  journal = {Computer Methods in Applied Mechanics and Engineering},
  year = {2020},
  volume = {372},
  articleno = {113291},
  doi = {10.1016/j.cma.2020.113291},
  comment = {https://authors.elsevier.com/c/1bdjR_12dr5W8C},
  timestamp = {28}
}