A hybrid data assimilation system based on machine learning

Abstract

In the earth sciences, numerical weather prediction (NWP) is the primary method of predicting future weather conditions, and its accuracy is affected by the initial conditions. Data assimilation (DA) can provide high-precision initial conditions for NWP. The hybrid 4DVar-EnKF is currently an advanced DA method used by many operational NWP centres. However, it has two major shortcomings: The complex development and maintenance of the tangent linear and adjoint models and the empirical combination of the results of 4DVar and EnKF. In this paper, a new hybrid DA method based on machine learning (HDA-ML) is presented to overcome these drawbacks. In the new method, the tangent linear and adjoint models in the 4DVar part of the hybrid algorithm can be easily obtained by using a bilinear neural network to replace the forecast model, and a CNN model is adopted to fuse the analysis of 4DVar and EnKF to adaptively obtain the optimal coefficient of combination rather than the empirical coefficient as in the traditional hybrid DA method. The hybrid DA methods are compared with the Lorenz-96 model using the true values as labels. The experimental results show that HDA-ML improves the assimilation performance and significantly reduces the time cost. Furthermore, using observations instead of the true values as labels in the training system is more realistic. The results show comparable assimilation performance to that in the experiments with the true values used as the labels. The experimental results show that the new method has great potential for application to operational NWP systems.

Basin Scale Soil Moisture Estimation with Grid SWAT and LESTKF Based on WSN

“… Machine learning: In recent years, machine learning methods have played a significant role in advancing the field of data assimilation. For instance, a new Hybrid Data Assimilation (DA) method based on a Machine Learning (HDA-ML) method overcomes the drawbacks of the traditional hybrid 4DVar-EnKF method by using neural networks to replace the tangent linear and adjoint models, and adopting a convolutional neural network (CNN) model to adaptively combine the results of 4DVar and EnKF [ 85 ]. He et al [ 86 ] introduces a hybrid Data Assimilation and Machine Learning framework (DA-ML method) implemented in the Weather Research and Forecasting (WRF) model to optimize surface soil and vegetation conditions.…”

Assessing the Feasibility of an NWP Satellite Data Assimilation System Entirely Based on AI Techniques

“…[2,3] applied ML/DL methods to directly forecast weather patterns from periods of 6 hours to 5 to 7 days in a fraction of the time as compared to operational weather forecasts. [4], provides a framework for a 4-Dimensional variational DA system using the Lorenz96 model. [5] implemented a complete physics-inspired data driven forecast and assimilation system using an idealized system and small set of geophysical variables from the WeatherBench dataset.…”