Preprints
https://doi.org/10.5194/egusphere-2022-1167
https://doi.org/10.5194/egusphere-2022-1167
 
10 Nov 2022
10 Nov 2022
Status: this preprint is open for discussion.

Reduced order digital twin and latent data assimilation for global wildfire prediction

Caili Zhang1, Sibo Cheng2, Matthew Kasoar3, and Rossella Arcucci1 Caili Zhang et al.
  • 1Department of Earth Science and Engineering, Imperial College London, London, United Kingdom
  • 2Data Science Institute, Imperial College London, London, United Kingdom
  • 3Department of Physics, Imperial College London, London, United Kingdom

Abstract. The occurrence of forest fires can impact vegetation in the ecosystem, property, and human health, but also indirectly affect the climate. JULES-INFERNO is a global land surface model, which simulates vegetation, soils, and fire occurrence driven by environmental factors. However, this model incurs substantial computational costs due to the high data dimensionality and the complexity of differential equations. Deep learning-based digital twins have an advantage in handling large amounts of data. They can reduce the computational cost of subsequent predictive models by extracting data features through Reduced Order Modelling (ROM) and then compressing the data to a low-dimensional latent space. This study proposes a JULES-INFERNO-based digital twin fire model using ROM techniques and deep learning prediction networks to improve the efficiency of global wildfire predictions. The iterative prediction implemented in the proposed model can use current-year data to predict fires in subsequent years. To avoid the accumulation of errors from the iterative prediction, Latent data Assimilation (LA) is applied to the prediction process. LA manages to efficiently adjust the prediction results to ensure the stability and sustainability of the prediction. Numerical results show that the proposed model can effectively encode the original data and achieve accurate surrogate predictions. Furthermore, the application of LA can also effectively adjust the bias of the prediction results. The proposed digital twin also runs 500 times faster for online predictions than the original JULES-INFERNO model without requiring High-Performance Computing (HPC) clusters. The implementation code of this study and the developed models are available at https://github.com/DL-WG/Digital-twin-LA-global-wildfire.

Caili Zhang et al.

Status: open (until 22 Dec 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2022-1167', Anonymous Referee #1, 11 Nov 2022 reply
    • AC2: 'Reply on RC1', Sibo Cheng, 19 Nov 2022 reply
  • RC2: 'Comment on egusphere-2022-1167', Anonymous Referee #2, 17 Nov 2022 reply
    • AC1: 'Reply on RC2', Sibo Cheng, 19 Nov 2022 reply

Caili Zhang et al.

Caili Zhang et al.

Viewed

Total article views: 219 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
161 45 13 219 3 2
  • HTML: 161
  • PDF: 45
  • XML: 13
  • Total: 219
  • BibTeX: 3
  • EndNote: 2
Views and downloads (calculated since 10 Nov 2022)
Cumulative views and downloads (calculated since 10 Nov 2022)

Viewed (geographical distribution)

Total article views: 217 (including HTML, PDF, and XML) Thereof 217 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Dec 2022
Download
Short summary
This paper introduces a digital twin fire model using machine learning techniques to improve the efficiency of global wildfire predictions. The proposed model also manages to efficiently adjust the prediction results thanks to data assimilation techniques. The proposed digital twin runs 500 times faster than the current state-of-the-art physics-based model.