Data assimilation empowered neural network parametrizations for subgrid processes in geophysical flows

2021 ◽  
Vol 6 (5) ◽  
Author(s):  
Suraj Pawar ◽  
Omer San
Keyword(s):  
Neural Network ◽  
Data Assimilation ◽  
Geophysical Flows

scholarly journals SMOS Neural Network Soil Moisture Data Assimilation in a Land Surface Model and Atmospheric Impact

2019 ◽  
Author(s):  
Nemesio Rodriguez-Fernandez ◽  
Patricia de Rosnay ◽  
Clement Albergel ◽  
Philippe Richaume ◽  
Filipe Aires ◽  
...  
Keyword(s):  
Neural Network ◽  
Soil Moisture ◽  
Data Assimilation ◽  
Land Surface ◽  
Positive Impact ◽  
Land Surface Model ◽  
Surface Model ◽  
Northern Asia ◽  
The Impact

The assimilation of Soil Moisture and Ocean Salinity (SMOS) data into the ECMWF (European Centre for Medium Range Weather Forecasts) H-TESSEL (Hydrology revised - Tiled ECMWF Scheme for Surface Exchanges over Land) model is presented. SMOS soil moisture (SM) estimates have been produced specifically by training a neural network with SMOS brightness temperatures as input and H-TESSEL model SM simulations as reference. This can help the assimilation of SMOS information in several ways: (1) the neural network soil moisture (NNSM) data have a similar climatology to the model, (2) no global bias is present with respect to the model even if regional differences can exist. Experiments performing joint data assimilation (DA) of NNSM, 2 metre air temperature and relative humidity or NNSM-only DA are discussed. The resulting SM was evaluated against a large number of in situ measurements of SM obtaining similar results to those of the model with no assimilation, even if significant differences were found from site to site. In addition, atmospheric forecasts initialized with H-TESSEL runs (without DA) or with the analysed SM were compared to measure of the impact of the satellite information. Although, NNSM DA has an overall neutral impact in the forecast in the Tropics, a significant positive impact was found in other areas and periods, especially in regions with limited in situ information. The joint NNSM, T2m and RH2m DA improves the forecast for all the seasons in the Southern Hemisphere. The impact is mostly due to T2m and RH2m, but SMOS NN DA alone also improves the forecast in July- September. In the Northern Hemisphere, the joint NNSM, T2m and RH2m DA improves the forecast in April-September, while NNSM alone has a significant positive effect in July-September. Furthermore, forecasting skill maps show that SMOS NNSM improves the forecast in North America and in Northern Asia for up to 72 hours lead time.

Using data assimilation in numerical simulations of experimental geophysical flows

2003 ◽  
Vol 331 (12) ◽  
pp. 843-848 ◽  
Author(s):  
Martin Galmiche ◽  
Joël Sommeria ◽  
Emmanuelle Thivolle-Cazat ◽  
Jacques Verron
Keyword(s):  
Data Assimilation ◽  
Numerical Simulations ◽  
Geophysical Flows ◽  
Using Data

scholarly journals Data Assimilation Procedure by Recurrent Neural Network

2012 ◽  
Vol 6 (2) ◽  
pp. 224-233 ◽  
Author(s):  
Fabrício P. Härter ◽  
Haroldo Fraga de Campos Velho
Keyword(s):  
Neural Network ◽  
Data Assimilation ◽  
Recurrent Neural Network

scholarly journals Using data assimilation in laboratory experiments of geophysical flows

2007 ◽  
Vol 65 (1-4) ◽  
pp. 532-539 ◽  
Author(s):  
M. Galmiche ◽  
J. Sommeria ◽  
P. Brasseur ◽  
J. Verron
Keyword(s):  
Data Assimilation ◽  
Laboratory Experiments ◽  
Geophysical Flows ◽  
Using Data

scholarly journals 644 Data Assimilation and Parameter Estimation by Neural Network

2006 ◽  
Vol 2006.19 (0) ◽  
pp. 743-744
Author(s):  
Tatsuoki TAKEDA ◽  
Jun WU
Keyword(s):  
Neural Network ◽  
Parameter Estimation ◽  
Data Assimilation

A Neural Network-Based Observation Operator for Coupled Ocean-Acoustic Variational Data Assimilation

2021 ◽  
Author(s):  
Andrea Storto ◽  
Giovanni De Magistris ◽  
Silvia Falchetti ◽  
Paolo Oddo
Keyword(s):  
Neural Network ◽  
Data Assimilation ◽  
Automatic Differentiation ◽  
Transmission Loss ◽  
Variational Data Assimilation ◽  
Propagation Model ◽  
Surface Boundary ◽  
Ligurian Sea ◽  
Observation Operator ◽  
The Impact

<p>Variational data assimilation requires implementing the tangent-linear and adjoint (TA/AD) version of any operator. This intrinsically hampers the use of complicated observations. Here, we assess a new data-driven approach to assimilate acoustic underwater propagation measurements (Transmission Loss, TL) into a regional ocean forecasting system. TL measurements depend on the underlying sound speed fields, mostly temperature, and their inversion would require heavy coding of the TA/AD of an acoustic underwater propagation model. In this study, the non-linear version of the acoustic model is applied to an ensemble of perturbed oceanic conditions. TL outputs are used to formulate both a statistical linear operator based on Canonical Correlation Analysis (CCA), and a neural network-based (NN) operator. For the latter, two linearization strategies are compared, the best performing one relying on reverse-mode automatic differentiation. The new observation operator is applied in data assimilation experiments over the Ligurian Sea (Mediterranean Sea), using the Observing System Simulation Experiments (OSSE) methodology to assess the impact of TL observations onto oceanic fields. TL observations are extracted from a nature run with perturbed surface boundary conditions and stochastic ocean physics. Sensitivity analysis and forecast experiments show not only the highest accuracy of the NN reconstruction of TL when compared to CCA, but also that its use in the assimilation of TL observations is able to significantly improve the upper ocean forecast skills. The use of the NN observation operator is computationally affordable, and its general formulation appears promising for the adjoint-free assimilation of any remote sensing observing network.</p>

Efficient Uncertainty Quantification and Data Assimilation via Theory-Guided Convolutional Neural Network

SPE Journal ◽  
1900 ◽  
pp. 1-29
Author(s):  
Nanzhe Wang ◽  
Haibin Chang ◽  
Dongxiao Zhang
Keyword(s):  
Neural Network ◽  
Data Assimilation ◽  
Convolutional Neural Network ◽  
Uncertainty Quantification ◽  
Reservoir Simulation ◽  
High Accuracy ◽  
Training Data ◽  
Flow Problems ◽  
Stochastic Parameter ◽  
Reservoir Flow

Summary A deep learning framework, called the theory-guided convolutional neural network (TgCNN), is developed for efficient uncertainty quantification and data assimilation of reservoir flow with uncertain model parameters. The performance of the proposed framework in terms of accuracy and computational efficiency is assessed by comparing it to classical approaches in reservoir simulation. The essence of the TgCNN is to take into consideration both the available data and underlying physical/engineering principles. The stochastic parameter fields and time matrix comprise the input of the convolutional neural network (CNN), whereas the output is the quantity of interest (e.g., pressure, saturation, etc.). The TgCNN is trained with available data while being simultaneously guided by theory (e.g., governing equations, other physical constraints, and engineering controls) of the underlying problem. The trained TgCNN serves as a surrogate that can predict the solutions of the reservoir flow problem with new stochastic parameter fields. Such approaches, including the Monte Carlo (MC) method and the iterative ensemble smoother (IES) method, can then be used to perform uncertainty quantification and data assimilation efficiently based on the TgCNN surrogate, respectively. The proposed paradigm is evaluated with dynamic reservoir flow problems. The results demonstrate that the TgCNN surrogate can be built with a relatively small number of training data and even in a label-free manner, which can approximate the relationship between model inputs and outputs with high accuracy. The TgCNN surrogate is then used for uncertainty quantification and data assimilation of reservoir flow problems, which achieves satisfactory accuracy and higher efficiency compared with state-of-the-art approaches. The novelty of the work lies in the ability to incorporate physical laws and domain knowledge into the deep learning process and achieve high accuracy with limited training data. The trained surrogate can significantly improve the efficiency of uncertainty quantification and data assimilation processes. NOTE: This paper is published as part of the 2021 Reservoir Simulation Conference Special Issue.

Sign in / Sign up

Export Citation Format

Share Document