An LSTM based Kalman Filter for Spatio-temporal Ocean Currents Assimilation

In this paper, we present a Long Short-Term Memory (LSTM)-based Kalman Filter for data assimilation of a 2D spatio-temporally varying depth-averaged ocean flow field for underwater glider path planning. The data source to the filter combines both the Eulerian flow map with the Lagrangian mobile sensor data stream. The depth-averaged flow is modeled as two components, the tidal and the non-tidal flow component. The tidal flow is modeled with ADCIRC (Advanced Three-Dimensional Circulation Model), while the non-tidal flow field is modeled by a set of spatial basis functions and their time series coefficients. The spatial basis functions are the principal modes derived by performing EOF (Empirical Orthogonal Functions) analysis on the historical surface flow field measured by high frequency radar (HFR), and the temporal coefficients of the spatial basis function are modeled by an LSTM neural network. The Kalman Filter is performed to combine the dynamics derived from the LSTM network, and the observations from the glider flow estimation data. Simulation results demonstrate that the proposed data assimilation method can give flow field prediction of reasonable accuracy.

[1]  R. Mehra.  Approaches to adaptive filtering , 1972 .

[2]  G. Evensen,et al.  Sequential Data Assimilation Techniques in Oceanography , 2003 .

[3]  Randy A. Freeman,et al.  Decentralized Environmental Modeling by Mobile Sensor Networks , 2008, IEEE Transactions on Robotics.

[4]  Fumin Zhang,et al.  Trend and Bounds for Error Growth in Controlled Lagrangian Particle Tracking , 2014, IEEE Journal of Oceanic Engineering.

[5]  Gaurav S. Sukhatme,et al.  Planning and Implementing Trajectories for Autonomous Underwater Vehicles to Track Evolving Ocean Processes Based on Predictions from a Regional Ocean Model , 2010, Int. J. Robotics Res..

[6]  Remy Baraille,et al.  The HYCOM (HYbrid Coordinate Ocean Model) data assimilative system , 2007 .

[7]  R. Davis,et al.  The autonomous underwater glider "Spray" , 2001 .

[8]  K. Ide,et al.  A Three-Dimensional Variational Data Assimilation Scheme for the Regional Ocean Modeling System , 2008 .

[9]  S. M. García,et al.  2014: , 2020, A Party for Lazarus.

[10]  Raman K. Mehra,et al.  Approaches to adaptive filtering , 1970 .

[11]  H. Stommel.  The Slocum Mission , 1989 .

[12]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[13]  T. Overton.  1972 , 1972, Parables of Sun Light.

[14]  Luigi di Stefano,et al.  On-line Support Vector Regression of the transition model for the Kalman filter , 2013, Image Vis. Comput..

[15]  Hernan G. Arango,et al.  Weak and strong constraint data assimilation in the inverse Regional Ocean Modeling System (ROMS): Development and application for a baroclinic coastal upwelling system , 2007 .

[16]  Annalisa Griffa,et al.  Predictability of Lagrangian particle trajectories: Effects of smoothing of the underlying Eulerian flow , 2004 .

[17]  Sharon L. Wolchik.  1989 , 2009 .

[18]  D. C. Webb,et al.  SLOCUM: an underwater glider propelled by environmental energy , 2001 .

[19]  Dietmar Rempfer,et al.  Predictive flow-field estimation , 2009 .

[20]  Alexander F. Shchepetkin,et al.  The regional oceanic modeling system (ROMS): a split-explicit, free-surface, topography-following-coordinate oceanic model , 2005 .

[21]  Nassir Navab,et al.  Long Short-Term Memory Kalman Filters: Recurrent Neural Estimators for Pose Regularization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[22]  Alexey Kaplan,et al.  Mapping tropical Pacific sea level : Data assimilation via a reduced state space Kalman filter , 1996 .

[23]  John C. Warner,et al.  Ocean forecasting in terrain-following coordinates: Formulation and skill assessment of the Regional Ocean Modeling System , 2008, J. Comput. Phys..

[24]  C. C. Eriksen,et al.  Seaglider: a long-range autonomous underwater vehicle for oceanographic research , 2001 .

[25]  Naomi Ehrich Leonard,et al.  Coordinated control of an underwater glider fleet in an adaptive ocean sampling field experiment in Monterey Bay , 2010, J. Field Robotics.

[26]  Quan Pan,et al.  A finite-horizon adaptive Kalman filter for linear systems with unknown disturbances , 2004, Signal Process..

[27]  T. Özgökmen,et al.  A Lagrangian subgridscale model for particle transport improvement and application in the Adriatic Sea using the Navy Coastal Ocean Model , 2007 .

[28]  Bertrand Chapron,et al.  Neural Network Based Kalman Filters for the Spatio-Temporal Interpolation of Satellite-Derived Sea Surface Temperature , 2018, Remote. Sens..

[29]  Naomi Ehrich Leonard,et al.  Control of coordinated patterns for ocean sampling , 2007, Int. J. Control.