Tracking the model: Data assimilation by artificial neural network

To generate reliable forecasts, we need good estimates of both the current system state and the model parameters. 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. The data assimilation process is performed by using artificial neural networks (NN) to obtain the initial condition to the atmospheric global model for the Florida State University (in USA. The NN is configured to emulate the analysis computed from the Local Ensemble Transform Kalman filter (LETKF) analysis. The method is tested employing synthetic observations. Multilayer Perceptron neural network is applied, with supervised training algorithm. An optimal configuration for the NN is obtained by solving an associated optimization problem. The data assimilation cycle is carried out at January, 2004. The results demonstrate the effectiveness of the NN technique for atmospheric data assimilation, with better computational performance and similar quality of LETKF analyses.

[1]  Takemasa Miyoshi,et al.  Local Ensemble Transform Kalman Filtering with an AGCM at a T159/L48 Resolution , 2007 .

[2]  M. B. Mathur,et al.  Florida State University's Tropical Prediction Model , 1973 .

[3]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[4]  Haroldo F. de Campos Velho,et al.  Multilayer Perceptron on data assimilation applied to FSU global model , 2015 .

[5]  Tatsuoki Takeda,et al.  Applying a Neural Network Collocation Method to an Incompletely Known Dynamical System via Weak Constraint Data Assimilation , 2003 .

[6]  Ionel Michael Navon,et al.  Performance of 4D-Var with Different Strategies for the Use of Adjoint Physics with the FSU Global Spectral Model , 2000 .

[7]  M. Ghil,et al.  Data assimilation in meteorology and oceanography , 1991 .

[8]  Haroldo Fraga de Campos,et al.  A new multi-particle collision algorithm for optimization in a high performance environment , 2008 .

[9]  Edward N. Lorenz,et al.  GENERATION OF AVAILABLE POTENTIAL ENERGY AND THE INTENSITY OF THE GENERAL CIRCULATION , 1960 .

[10]  Christopher K. Wikle,et al.  Atmospheric Modeling, Data Assimilation, and Predictability , 2005, Technometrics.

[11]  Marco Wiering,et al.  2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) , 2011, IJCNN 2011.

[12]  R. Daley.  Atmospheric Data Analysis , 1991 .

[13]  Steven Cocke,et al.  Seasonal Predictions Using a Regional Spectral Model Embedded within a Coupled Ocean–Atmosphere Model , 2000 .

[14]  Rosangela,et al.  A Local Ensemble Transform Kalman Filter Data Assimilation System for the Global FSU Atmospheric Model , 2015 .

[15]  William W. Hsieh,et al.  Applying Neural Network Models to Prediction and Data Analysis in Meteorology and Oceanography. , 1998 .

[16]  Haroldo F. de Campos Velho,et al.  GLOBAL DATA ASSIMILATION USING ARTIFICIAL NEURAL NETWORKS IN SPEEDY MODEL , 2011 .

[17]  A. Hall,et al.  Adaptive Switching Circuits , 2016 .

[18]  Haroldo F. de Campos Velho,et al.  Neural network for performance improvement in atmospheric prediction systems: Data Assimilation , 2016 .

[19]  R. E. Kalman,et al.  New Results in Linear Filtering and Prediction Theory , 1961 .

[20]  Haroldo de Campos Velho,et al.  Artificial Neural Networks emulating Representer Method at a shallow water model 2D , 2016 .

[21]  Steven Cocke,et al.  Data assimilation by artificial neural networks for the global FSU atmospheric model: Surface pressure , 2015, 2015 Latin America Congress on Computational Intelligence (LA-CCI).

[22]  Haroldo F. de Campos Velho,et al.  Data assimilation: Particle filter and artificial neural networks , 2008 .

[23]  Haroldo F. de Campos Velho,et al.  New approach to applying neural network in nonlinear dynamic model , 2008 .

[24]  Istvan Szunyogh,et al.  A local ensemble transform Kalman filter data assimilation system for the NCEP global model , 2008 .

[25]  Istvan Szunyogh,et al.  A Local Ensemble Kalman Filter for Atmospheric Data Assimilation , 2002 .

[26]  Joseph Smagorjnsky,et al.  The Beginnings of Numerical Weather Prediction and General Circulation Modeling: Early Recollections , 1983 .

[27]  Takemasa Miyoshi,et al.  ENSEMBLE KALMAN FILTER EXPERIMENTS WITH A PRIMITIVE-EQUATION GLOBAL MODEL , 2005 .

[28]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[29]  Lennart Bengtsson.  From short-range barotropic modelling to extended-range global weather prediction: a 40-year perspective , 1999 .

[30]  G. Evensen.  Sequential data assimilation with a nonlinear quasi‐geostrophic model using Monte Carlo methods to forecast error statistics , 1994 .

[31]  Istvan Szunyogh,et al.  Efficient data assimilation for spatiotemporal chaos: A local ensemble transform Kalman filter , 2005, physics/0511236.

[32]  Haroldo F. de Campos Velho,et al.  New learning strategy for supervised neural network: MPCA meta-heuristic approach , 2016 .