Preprints
https://doi.org/10.5194/gmd-2022-50
https://doi.org/10.5194/gmd-2022-50
Submitted as: development and technical paper
09 Sep 2022
Submitted as: development and technical paper | 09 Sep 2022
Status: this preprint is currently under review for the journal GMD.

Neural networks for data assimilation of surface and upper-air data in Rio de Janeiro

Vinícius Albuquerque de Almeida1, Haroldo Fraga de Campos Velho2, Gutemberg Borges França1, and Nelson Francisco Favilla Ebecken3 Vinícius Albuquerque de Almeida et al.
  • 1Laboratory for Applied Meteorology - Federal University of Rio de Janeiro
  • 2National Institute for Space Research
  • 3Civil Engineering/COPPE - Federal University of Rio de Janeiro

Abstract. The practical feasibility of neural networks models for data assimilation using local observations data in the WRF model for the Rio de Janeiro metropolitan region in Brazil is evaluated. Surface and multi-level variables retrieved from airport meteorological stations are used: air temperature, relative humidity, and wind (speed and direction). Also, 6-hour forecast from WRF high-resolution simulations are used – domain centered in the Rio de Janeiro city with nested grids of 8 and 2.6 km. Periods of 168 h from 2015–2019 are used with 6 h and 12 h assimilation cycles for surface and upper-air data, respectively, applied to 6-hour forecast fields. The observed data (interpolated to grid points close to airport locations and influence computed in its surroundings) and short-range forecasts are used as input for training model and the 3D-Var analysis on 6-hour forecast fields for each grid point is used as target variable. The neural network models are built using two different approaches: WEKA mul- tilayer perceptron model and TensorFlow’s deep learning implementation. The year of 2019 is used as an independent dataset for forecast validation from the trained models. Results employing 6-hour forecast fields with neural network models are able to emulate the 3D-Var results for surface and multi-level variables, with better results for the NN-TensoFlow implementation. The main result refers to CPU time reduction enabled by the neural networks models, reducing the data assimilation CPU-time by 121 times and 25 times for NN-TensorFlow and NN-WEKA, respectively, in comparison to the 3D-Var method under the same hardware configurations.

Vinícius Albuquerque de Almeida et al.

Status: open (until 04 Nov 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Vinícius Albuquerque de Almeida et al.

Vinícius Albuquerque de Almeida et al.

Metrics will be available soon.
Latest update: 09 Sep 2022
Download
Short summary
The paper focuses on data assimilation for the WRF model by employing neural network. The applied supervised ML technique was designed to emulate the 3D-Var in a regional atmospheric model. The proposed technique has the potential to significantly reduce the computational effort of data assimilation. Indeed, in the worked example the neural network scheme was more 70 times faster than 3D-Var method, with similar quality for the analysis.