Abstract
Numerical weather prediction (NWP) uses atmospheric general circulation models (AGCMs) to predict weather based on current weather conditions. The process of entering observation data into mathematical model to generate the accurate initial conditions is called data assimilation (DA). It combines observations, forecasting, and filtering step. This paper presents an approach for employing artificial neural networks (NNs) to emulate the local ensemble transform Kalman filter (LETKF) as a method of data assimilation. This assimilation experiment tests the Simplified Parameterizations PrimitivE-Equation Dynamics (SPEEDY) model, an atmospheric general circulation model (AGCM), using synthetic observational data simulating localizations of meteorological balloons. For the data assimilation scheme, the supervised NN, the multilayer perceptrons (MLPs) networks are applied. After the training process, the method, forehead-calling MLP-DA, is seen as a function of data assimilation. The NNs were trained with data from first 3 months of 1982, 1983, and 1984. The experiment is performed for January 1985, one data assimilation cycle using MLP-DA with synthetic observations. The numerical results demonstrate the effectiveness of the NN technique for atmospheric data assimilation. The results of the NN analyses are very close to the results from the LETKF analyses, the differences of the monthly average of absolute temperature analyses are of order 10–2. The simulations show that the major advantage of using the MLP-DA is better computational performance, since the analyses have similar quality. The CPU-time cycle assimilation with MLP-DA analyses is 90 times faster than LETKF cycle assimilation with the mean analyses used to run the forecast experiment.
Highlights
For operating systems in weather forecasting, one of the challenges is to obtain the most appropriate initial conditions to ensure the best prediction from a physical mathematical266 Advanced Applications for Artificial Neural Networks model that represents the evolution of the atmospheric dynamics
The results show the comparison of analysis fields, generated by the multilayer perceptrons (MLPs)-data assimilation (DA), the local ensemble transform Kalman filter (LETKF), and the true model fields
These results show that the application of MLP-DA, as an assimilation system, generates analyses similar to those calculated by the LETKF system
Summary
For operating systems in weather forecasting, one of the challenges is to obtain the most appropriate initial conditions to ensure the best prediction from a physical mathematical266 Advanced Applications for Artificial Neural Networks model that represents the evolution of the atmospheric dynamics. Performing a smooth melding of data from observations and model predictions, the assimilation process carries out a set of procedures to determine the best initial condition. The approach of Bayesian scheme [31] uses ensembles of integrations of prediction models, where added perturbations to initial conditions and model formulation; the mean of ensemble forecasts can be interpreted as a probabilistic prediction. The ensemble Kalman filter (EnKF) [11, 23] uses a probability density function associated with the initial condition, characterizing the Bayesian approaches [9], and represents the model errors by an ensemble of estimates in state space. A useful overview of most common data assimilation methods used in meteorology and oceanography and detailed mathematical formulations can be found in texts such as Daley [9] and Kalnay [29]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.