Integration of Ensemble Data Assimilation and Deep Learning for History Matching Facies Models

2017 ◽  
Author(s):  
Smith Arauco Canchumuni ◽  
Alexandre A. Emerick ◽  
Marco Aurelio Pacheco
Keyword(s):  
Deep Learning ◽  
Data Assimilation ◽  
History Matching ◽  
Ensemble Data Assimilation ◽  
Ensemble Data ◽  
Facies Models

Deep Learning for Latent Space Data Assimilation LSDA in Subsurface Flow Systems

2021 ◽  
Author(s):  
Syamil Mohd Razak ◽  
Atefeh Jahandideh ◽  
Ulugbek Djuraev ◽  
Behnam Jafarpour
Keyword(s):  
Deep Learning ◽  
Data Assimilation ◽  
Model Updating ◽  
Statistical Information ◽  
Ensemble Data Assimilation ◽  
Ensemble Data ◽  
Latent Space ◽  
Feature Based ◽  
Consistent Feature ◽  
Low Dimensional

Abstract We present a deep learning architecture for efficient reduced-order implementation of ensemble data assimilation. Specifically, deep learning is used to improve two important aspects of data assimilation workflows: (i) low-rank representation of complex reservoir property distributions for geologically consistent feature-based model updating, and (ii) efficient prediction of the statistical information that are required for model updating. The proposed method uses deep convolutional autoencoders to nonlinearly map the original complex and high-dimensional parameters onto a low-dimensional parameter latent space that compactly represents the original parameters. In addition, a low-dimensional data latent space is constructed to predict the observable response of each model parameter realization, which can be used to compute the statistical information needed for the data assimilation step. The two mappings are developed as a joint deep learning architecture with two autoencoders that are connected and trained together. The training uses an ensemble of model parameters and their corresponding production response predictions as needed in implementing the standard ensemble-based data assimilation frameworks. Simultaneous training of the two mappings leads to a joint data-parameter manifold that captures the most salient information in the two spaces for a more effective data assimilation, where only relevant data and parameter features are included. Moreover, the parameter-to-data mapping provides a fast forecast model that can be used to increase the ensemble size for a more accurate data assimilation, without a major computational overhead. We implement the developed approach to a series of numerical experiments, including a 3D example based on the Volve field in the North Sea. For data assimilation methods that involve iterative schemes, such as ensemble smoothers with multiple data assimilation or iterative forms of ensemble Kalman filter, the proposed approach offers a computationally competitive alternative. Our results show that a fully low-dimensional implementation of ensemble data assimilation using deep learning architectures offers several advantages compared to standard algorithms, including joint data-parameter reduction that respects the salient features in each space, geologically consistent feature-based updates, increased ensemble sizes to improve the accuracy and computational efficiency of the calculated statistics for the update step.

scholarly journals Novel iterative ensemble smoothers derived from a class of generalized cost functions

2021 ◽  
Author(s):  
Xiaodong Luo
Keyword(s):  
Data Assimilation ◽  
History Matching ◽  
Nonlinear Least Squares ◽  
Cost Functions ◽  
Matching Problems ◽  
Ensemble Data Assimilation ◽  
Ensemble Data ◽  
Ensemble Smoothers ◽  
Iterative Ensemble Smoothers ◽  
Generalized Cost

AbstractIterative ensemble smoothers (IES) are among the state-of-the-art approaches to solving history matching problems. From an optimization-theoretic point of view, these algorithms can be derived by solving certain stochastic nonlinear-least-squares problems. In a broader picture, history matching is essentially an inverse problem, which is often ill-posed and may not possess a unique solution. To mitigate the ill-posedness, in the course of solving an inverse problem, prior knowledge and domain experience are often incorporated, as a regularization term, into a suitable cost function within a respective optimization problem. Whereas in the inverse theory there is a rich class of inversion algorithms resulting from various choices of regularized cost functions, there are few ensemble data assimilation algorithms (including IES) which in their practical uses are implemented in a form beyond nonlinear-least-squares. This work aims to narrow this noticed gap. Specifically, we consider a class of more generalized cost functions, and establish a unified formula that can be used to construct a corresponding group of novel ensemble data assimilation algorithms, called generalized IES (GIES), in a principled and systematic way. For demonstration, we choose a subset (up to 30 +) of the GIES algorithms derived from the unified formula, and apply them to two history matching problems. Experiment results indicate that many of the tested GIES algorithms exhibit superior performance to that of an original IES developed in a previous work, showcasing the potential benefit of designing new ensemble data assimilation algorithms through the proposed framework.

Initiation of ensemble data assimilation

2006 ◽  
Author(s):  
M. Zupanski ◽  
S. J. Fletcher ◽  
I. M. Navon ◽  
B. Uzunoglu ◽  
R. P. Heikes ◽  
...  
Keyword(s):  
Data Assimilation ◽  
Ensemble Data Assimilation ◽  
Ensemble Data

Using a machine learning proxy for localization in ensemble data assimilation

2021 ◽  
Vol 25 (3) ◽  
pp. 931-944
Author(s):  
Johann M. Lacerda ◽  
Alexandre A. Emerick ◽  
Adolfo P. Pires
Keyword(s):  
Machine Learning ◽  
Data Assimilation ◽  
Ensemble Data Assimilation ◽  
Ensemble Data

Maximum Likelihood Ensemble Filter: Theoretical Aspects

2005 ◽  
Vol 133 (6) ◽  
pp. 1710-1726 ◽  
Author(s):  
Milija Zupanski
Keyword(s):  
Maximum Likelihood ◽  
Data Assimilation ◽  
Cost Function ◽  
Ensemble Data Assimilation ◽  
Error Covariance ◽  
Ensemble Data ◽  
Analysis Error ◽  
Nonlinear Observation ◽  
The Cost ◽  
Maximum Likelihood Ensemble Filter

Abstract A new ensemble-based data assimilation method, named the maximum likelihood ensemble filter (MLEF), is presented. The analysis solution maximizes the likelihood of the posterior probability distribution, obtained by minimization of a cost function that depends on a general nonlinear observation operator. The MLEF belongs to the class of deterministic ensemble filters, since no perturbed observations are employed. As in variational and ensemble data assimilation methods, the cost function is derived using a Gaussian probability density function framework. Like other ensemble data assimilation algorithms, the MLEF produces an estimate of the analysis uncertainty (e.g., analysis error covariance). In addition to the common use of ensembles in calculation of the forecast error covariance, the ensembles in MLEF are exploited to efficiently calculate the Hessian preconditioning and the gradient of the cost function. A sufficient number of iterative minimization steps is 2–3, because of superior Hessian preconditioning. The MLEF method is well suited for use with highly nonlinear observation operators, for a small additional computational cost of minimization. The consistent treatment of nonlinear observation operators through optimization is an advantage of the MLEF over other ensemble data assimilation algorithms. The cost of MLEF is comparable to the cost of existing ensemble Kalman filter algorithms. The method is directly applicable to most complex forecast models and observation operators. In this paper, the MLEF method is applied to data assimilation with the one-dimensional Korteweg–de Vries–Burgers equation. The tested observation operator is quadratic, in order to make the assimilation problem more challenging. The results illustrate the stability of the MLEF performance, as well as the benefit of the cost function minimization. The improvement is noted in terms of the rms error, as well as the analysis error covariance. The statistics of innovation vectors (observation minus forecast) also indicate a stable performance of the MLEF algorithm. Additional experiments suggest the amplified benefit of targeted observations in ensemble data assimilation.

scholarly journals Convection-Permitting Forecasts Initialized with Continuously Cycling Limited-Area 3DVAR, Ensemble Kalman Filter, and “Hybrid” Variational–Ensemble Data Assimilation Systems

2014 ◽  
Vol 142 (2) ◽  
pp. 716-738 ◽  
Author(s):  
Craig S. Schwartz ◽  
Zhiquan Liu
Keyword(s):  
Kalman Filter ◽  
Data Assimilation ◽  
Three Dimensional ◽  
Skill Score ◽  
Limited Area ◽  
Computational Domain ◽  
Ensemble Data Assimilation ◽  
Ensemble Data ◽  
Precipitation Characteristics ◽  
High Precipitation

Abstract Analyses with 20-km horizontal grid spacing were produced from parallel continuously cycling three-dimensional variational (3DVAR), ensemble square root Kalman filter (EnSRF), and “hybrid” variational–ensemble data assimilation (DA) systems between 0000 UTC 6 May and 0000 UTC 21 June 2011 over a domain spanning the contiguous United States. Beginning 9 May, the 0000 UTC analyses initialized 36-h Weather Research and Forecasting Model (WRF) forecasts containing a large convection-permitting 4-km nest. These 4-km 3DVAR-, EnSRF-, and hybrid-initialized forecasts were compared to benchmark WRF forecasts initialized by interpolating 0000 UTC Global Forecast System (GFS) analyses onto the computational domain. While important differences regarding mean state characteristics of the 20-km DA systems were noted, verification efforts focused on the 4-km precipitation forecasts. The 3DVAR-, hybrid-, and EnSRF-initialized 4-km precipitation forecasts performed similarly regarding general precipitation characteristics, such as timing of the diurnal cycle, and all three forecast sets had high precipitation biases at heavier rainfall rates. However, meaningful differences emerged regarding precipitation placement as quantified by the fractions skill score. For most forecast hours, the hybrid-initialized 4-km precipitation forecasts were better than the EnSRF-, 3DVAR-, and GFS-initialized forecasts, and the improvement was often statistically significant at the 95th percentile. These results demonstrate the potential of limited-area continuously cycling hybrid DA configurations and suggest additional hybrid development is warranted.

scholarly journals Southern High-Latitude Ensemble Data Assimilation in the Antarctic Mesoscale Prediction System

2005 ◽  
Vol 133 (12) ◽  
pp. 3431-3449 ◽  
Author(s):  
D. M. Barker
Keyword(s):  
Data Assimilation ◽  
Sampling Error ◽  
Forecast Error ◽  
Weather Prediction ◽  
Forecast Errors ◽  
Prediction System ◽  
Spatial Covariance ◽  
Ensemble Data Assimilation ◽  
Ensemble Data ◽  
The Antarctic

Abstract Ensemble data assimilation systems incorporate observations into numerical models via solution of the Kalman filter update equations, and estimates of forecast error covariances derived from ensembles of model integrations. In this paper, a particular algorithm, the ensemble square root filter (EnSRF), is tested in a limited-area, polar numerical weather prediction (NWP) model: the Antarctic Mesoscale Prediction System (AMPS). For application in the real-time AMPS, the number of model integrations that can be run to provide forecast error covariances is limited, resulting in an ensemble sampling error that degrades the analysis fit to observations. In this work, multivariate, climatologically plausible forecast error covariances are specified via averaged forecast difference statistics. Ensemble representations of the “true” forecast errors, created using randomized control variables of the fifth-generation Pennsylvania State University–National Center for Atmospheric Research (PSU–NCAR) Mesoscale Model (MM5) three-dimensional variational (3DVAR) data assimilation system, are then used to assess the dependence of sampling error on ensemble size, data density, and localization of covariances using simulated observation networks. Results highlight the detrimental impact of ensemble sampling error on the analysis increment structure of correlated, but unobserved fields—an issue not addressed by the spatial covariance localization techniques used to date. A 12-hourly cycling EnSRF/AMPS assimilation/forecast system is tested for a two-week period in December 2002 using real, conventional (surface, rawinsonde, satellite retrieval) observations. The dependence of forecast scores on methods used to maintain ensemble spread and the inclusion of perturbations to lateral boundary conditions are studied.

Sign in / Sign up

Export Citation Format

Share Document