skip to main content
Explore Scholarly Publications and Datasets in the NSF-PAR

Title: 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.
Authors:
; ; ;
Award ID(s):
1849228 1828678
Publication Date:
NSF-PAR ID:
10136251
Journal Name:
WUWNET'19: Proceedings of the International Conference on Underwater Networks & Systems
Issue:
28
Page Range or eLocation-ID:
1 to 7
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ( )
    Abstract
    Excessive phosphorus (P) applications to croplands can contribute to eutrophication of surface waters through surface runoff and subsurface (leaching) losses. We analyzed leaching losses of total dissolved P (TDP) from no-till corn, hybrid poplar (Populus nigra X P. maximowiczii), switchgrass (Panicum virgatum), miscanthus (Miscanthus giganteus), native grasses, and restored prairie, all planted in 2008 on former cropland in Michigan, USA. All crops except corn (13 kg P ha−1 year−1) were grown without P fertilization. Biomass was harvested at the end of each growing season except for poplar. Soil water at 1.2 m depth was sampled weekly to biweekly for TDP determination during March–November 2009–2016 using tension lysimeters. Soil test P (0–25 cm depth) was measured every autumn. Soil water TDP concentrations were usually below levels where eutrophication of surface waters is frequently observed (> 0.02 mg L−1) but often higher than in deep groundwater or nearby streams and lakes. Rates of P leaching, estimated from measured concentrations and modeled drainage, did not differ statistically among cropping systems across years; 7-year cropping system means ranged from 0.035 to 0.072 kg P ha−1 year−1 with large interannual variation. Leached P was positively related to STP, which decreased over the 7 years in all systems. These results indicate that both P-fertilized and unfertilized cropping systems mayMore>>
  2. ; ; ; ; ; ; ; ; ; ; et al ( , The cryosphere)
    Assimilation of remote-sensing products of sea ice thickness (SIT) into sea ice–ocean models has been shown to improve the quality of sea ice forecasts. Key open questions are whether assimilation of lower-level data products such as radar freeboard (RFB) can further improve model performance and what performance gains can be achieved through joint assimilation of these data products in combination with a snow depth product. The Arctic Mission Benefit Analysis system was developed to address this type of question. Using the quantitative network design (QND) approach, the system can evaluate, in a mathematically rigorous fashion, the observational constraints imposed by individual and groups of data products. We demonstrate the approach by presenting assessments of the observation impact (added value) of different Earth observation (EO) products in terms of the uncertainty reduction in a 4-week forecast of sea ice volume (SIV) and snow volume (SNV) for three regions along the Northern Sea Route in May 2015 using a coupled model of the sea ice–ocean system, specifically the Max Planck Institute Ocean Model. We assess seven satellite products: three real products and four hypothetical products. The real products are monthly SIT, sea ice freeboard (SIFB), and RFB, all derived from CryoSat-2 bymore »the AlfredWegener Institute. These are complemented by two hypothetical monthly laser freeboard (LFB) products with low and high accuracy, as well as two hypothetical monthly snow depth products with low and high accuracy. On the basis of the per-pixel uncertainty ranges provided with the CryoSat-2 SIT, SIFB, and RFB products, the SIT and RFB achieve a much better performance for SIV than the SIFB product. For SNV, the performance of SIT is only low, the performance of SIFB is higher and the performance of RFB is yet higher. A hypothetical LFB product with low accuracy (20 cm uncertainty) falls between SIFB and RFB in performance for both SIV and SNV. A reduction in the uncertainty of the LFB product to 2 cm yields a significant increase in performance. Combining either of the SIT or freeboard products with a hypothetical snow depth product achieves a significant performance increase. The uncertainty in the snow product matters: a higher-accuracy product achieves an extra performance gain. Providing spatial and temporal uncertainty correlations with the EO products would be beneficial not only for QND assessments, but also for assimilation of the products.« less
  3. ; ; ( , Journal of Space Weather and Space Climate)
    To improve Thermosphere–Ionosphere modeling during disturbed conditions, data assimilation schemes that can account for the large and fast-moving gradients moving through the modeled domain are necessary. We argue that this requires a physics based background model with a non-stationary covariance. An added benefit of using physics-based models would be improved forecasting capability over largely persistence-based forecasts of empirical models. As a reference implementation, we have developed an ensemble Kalman Filter (enKF) software called Thermosphere Ionosphere Data Assimilation (TIDA) using the physics-based Coupled Thermosphere Ionosphere Plasmasphere electrodynamics (CTIPe) model as the background. In this paper, we present detailed results from experiments during the 2003 Halloween Storm, 27–31 October 2003, under very disturbed ( K p  = 9) conditions while assimilating GRACE-A and B, and CHAMP neutral density measurements. TIDA simulates this disturbed period without using the L1 solar wind measurements, which were contaminated by solar energetic protons, by estimating the model drivers from the density measurements. We also briefly present statistical results for two additional storms: September 27 – October 2, 2002, and July 26 – 30, 2004, to show that the improvement in assimilated neutral density specification is not an artifact of the corrupted forcing observations during the 2003 Halloween Storm.more »By showing statistical results from assimilating one satellite at a time, we show that TIDA produces a coherent global specification for neutral density throughout the storm – a critical capability in calculating satellite drag and debris collision avoidance for space traffic management.« less
  4. ( , Monthly Weather Review)
    Abstract Weather prediction models currently operate within a probabilistic framework for generating forecasts conditioned on recent measurements of Earth’s atmosphere. This framework can be conceptualized as one that approximates parts of a Bayesian posterior density estimated under assumptions of Gaussian errors. Gaussian error approximations are appropriate for synoptic-scale atmospheric flow, which experiences quasi-linear error evolution over time scales depicted by measurements, but are often hypothesized to be inappropriate for highly nonlinear, sparsely-observed mesoscale processes. The current study adopts an experimental regional modeling system to examine the impact of Gaussian prior error approximations, which are adopted by ensemble Kalman filters (EnKFs) to generate probabilistic predictions. The analysis is aided by results obtained using recently-introduced particle filter (PF) methodology that relies on an implicit non-parametric representation of prior probability densities—but with added computational expense. The investigation focuses on EnKF and PF comparisons over month-long experiments performed using an extensive domain, which features the development and passage of numerous extratropical and tropical cyclones. The experiments reveal spurious small-scale corrections in EnKF members, which come about from inappropriate Gaussian approximations for priors dominated by alignment uncertainty in mesoscale weather systems. Similar behavior is found in PF members, owing to the use of a localizationmore »operator, but to a much lesser extent. This result is reproduced and studied using a low-dimensional model, which permits the use of large sample estimates of the Bayesian posterior distribution. Findings from this study motivate the use of data assimilation techniques that provide a more appropriate specification of multivariate non-Gaussian prior densities or a multi-scale treatment of alignment errors during data assimilation.« less
  5. ; ; ; ; ( , Forecasting)
    Despite the large efforts made by the ocean modeling community, such as the GODAE (Global Ocean Data Assimilation Experiment), which started in 1997 and was renamed as OceanPredict in 2019, the prediction of ocean currents has remained a challenge until the present day—particularly in ocean regions that are characterized by rapid changes in their circulation due to changes in atmospheric forcing or due to the release of available potential energy through the development of instabilities. Ocean numerical models’ useful forecast window is no longer than two days over a given area with the best initialization possible. Predictions quickly diverge from the observational field throughout the water and become unreliable, despite the fact that they can simulate the observed dynamics through other variables such as temperature, salinity and sea surface height. Numerical methods such as harmonic analysis are used to predict both short- and long-term tidal currents with significant accuracy. However, they are limited to the areas where the tide was measured. In this study, a new approach to ocean current prediction based on deep learning is proposed. This method is evaluated on the measured energetic currents of the Gulf of Mexico circulation dominated by the Loop Current (LC) at multiplemore »spatial and temporal scales. The approach taken herein consists of dividing the velocity tensor into planes perpendicular to each of the three Cartesian coordinate system directions. A Long Short-Term Memory Recurrent Neural Network, which is best suited to handling long-term dependencies in the data, was thus used to predict the evolution of the velocity field in each plane, along each of the three directions. The predicted tensors, made of the planes perpendicular to each Cartesian direction, revealed that the model’s prediction skills were best for the flow field in the planes perpendicular to the direction of prediction. Furthermore, the fusion of all three predicted tensors significantly increased the overall skills of the flow prediction over the individual model’s predictions. The useful forecast period of this new model was greater than 4 days with a root mean square error less than 0.05 cm·s−1 and a correlation coefficient of 0.6.« less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email