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

Abstract

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.

3D‐Var data assimilation using a variational autoencoder

“…A full NN data assimilation in an NWP setting was recently demonstrated by de Almeida et al (2022). They employed a dense NN and trained it to emulate analysis increments in the Weather Research and Forecasting (WRF) model derived from three-dimensional variational (3D-Var) data assimilation of surface observations and atmospheric sounding data.…”

Exploring the Integration of a Global AI Model with Traditional Data Assimilation in Weather Forecasting

“…This strategy could lead to creation of hybrid systems that merge the best aspects of traditional and modern forecasting methods. Alternatively, some researchers are exploring the development of entirely new DA frameworks, leveraging AI's unique capabilities to achieve unprecedented adaptability and efficiency, which might surpass traditional methods in terms of speed and accuracy (de Almeida et al, 2022;Andrychowicz et al, 2023;Chen et al, 2023a). However, constructing a new DA system for AI forecasting models represents a formidable challenge, requiring extensive expertise, comprehensive datasets, and meticulous calibration, with mature systems often necessitating years or even decades of refinement to achieve optimal performance (Dee et al, 2011;Shao et al, 2016;Lean et al, 2021).…”