Quantifying Expected Uncertainty Reduction and Value of Information Using Ensemble-Variance Analysis

He, Jiankui; Sarma, Pallav; Bhark, Eric; Tanaka, Shusei; Chen, Bailian; Wen, Xian‐Huan; Kamath, Jairam

doi:10.2118/182609-pa

Cited by 27 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Satija and Caers [42] used the same approach in a reservoir problem and concluded that the method provided uncertainty estimates of production forecast in reasonable agreement with rejection sampling. More recently, He et al [22] used similar ideas from DSI to estimate the uncertainty reduction in a study to compute the value of information of data-acquisition plans. Jeong et al [24] applied machine learning techniques (neural networks and support vector regression) to DSI.…”

Section: Introductionmentioning

confidence: 99%

Data-space inversion with ensemble smoother

2020

View full text Add to dashboard Cite

Reservoir engineers use large-scale numerical models to predict the production performance in oil and gas fields. However, these models are constructed based on scarce and often inaccurate data, making their predictions highly uncertain. On the other hand, measurements of pressure and flow rates are constantly collected during the operation of the field. The assimilation of these data into the reservoir models (history matching) helps to mitigate uncertainty and improve their predictive capacity. History matching is a nonlinear inverse problem, which is typically handled using optimization and Monte Carlo methods. In practice, however, generating a set of properly history-matched models that preserve the geological realism is very challenging, especially in cases with complicated prior description, such as models with fractures and complex facies distributions. Recently, a new data-space inversion (DSI) approach was introduced in the literature as an alternative to the model-space inversion used in history matching. The essential idea is to update directly the predictions from a prior ensemble of models to account for the observed production history without updating the corresponding models. The present paper introduces a DSI implementation based on the use of an iterative ensemble smoother and demonstrates with examples that the new implementation is computationally faster and more robust than the earlier method based on principal component analysis. The new DSI is also applied to estimate the production forecast in a real field with long production history and a large number of wells. For this field problem, the new DSI obtained forecasts comparable with a more traditional ensemble-based history matching.

show abstract

Section: Introductionmentioning

confidence: 99%

Data-space inversion with ensemble smoother

2020

View full text Add to dashboard Cite

show abstract

“…Our approach builds on work in other disciplines in which uncertainty quantification and reduction are applied to understand or improve the behavior of domain-specific models. For example, in petroleum engineering, an ensemble-based approach is used to derive value of information (VOI) estimates for resolving parameter values in models of oil reservoir management (He et al, 2018). In this setting, a company may be interested in performing the experiment or analysis needed to improve their certainty in a model of profit gain or risk.…”

Section: Discussionmentioning

confidence: 99%

Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine Learning

Medlock

Papin

2020

Cell Systems

View full text Add to dashboard Cite

Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine Learning Highlights d Prioritizing curation of complex mechanistic models is challenging d Development of curation guidance approach for genomescale metabolic models d Ensembles and machine learning are used to prioritize possible curation efforts d Application to metabolic models for 29 bacterial species and a biochemical database

show abstract

“…Our approach builds on work in other disciplines in which uncertainty quantification and reduction are applied to understand or improve the behavior of domainspecific models. For example, in petroleum engineering, an ensemblebased approach is used to derive value of information (VOI) estimates for resolving parameter values in models of oil reservoir management (He et al, 2018) . In this setting, a company may be interested in performing the experiment or analysis needed to improve their certainty in a model of profit gain or risk.…”

Section: Discussionmentioning

confidence: 99%

Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine Learning

Medlock

Papin

2018

Preprint

View full text Add to dashboard Cite

Mechanistic models are becoming common in biology and medicine. These models are often more generalizable than datadriven models because they explicitly represent biological knowledge, enabling simulation of scenarios that were not used to construct the model. While this generalizability has advantages, it also creates a dilemma: how should model curation efforts be focused to improve model performance? Here, we develop a machine learningguided solution to this problem for genomescale metabolic models. We generate an ensemble of candidate models consistent with experimental data, then perform in silico ensemble simulations for which improved predictiveness is desired. We apply unsupervised and supervised learning to the simulation output to identify structural variation in ensemble members that maximally influences variance in simulation outcomes across the ensemble. The resulting structural variants are high priority candidates for curation through targeted experimentation. We demonstrate this approach, called A utomated M etabolic M odel E nsemble D riven E limination of U ncertainty with S tatistical learning ( AMMEDEUS ), by applying it to 29 bacterial species to identify curation targets that improve gene essentiality predictions. We then compile these curation targets from all 29 species to prioritize refinement of the entire biochemical database used to generate them. AMMEDEUS is a fully automated, scalable, and performancedriven recommendation system that complements human intuition during the curation of hypothesisdriven models and biochemical databases. SignificanceMechanistic computational models, such as metabolic and signaling networks, are becoming common in biology. These models contain a comprehensive representation of components and interactions for a given system, making them generalizable and often more predictive than simpler models. However, their size and connectivity make it difficult to identify which parts of a model need to be changed to improve performance further. Here, we develop a strategy to guide this process and apply it to metabolic models for a set of bacterial species. We use this strategy to identify model components that should be investigated, and demonstrate that it can improve predictive performance. This approach systematically aides the curation of metabolic models, and the databases used to construct them, without relying on the intuition of the curator.

show abstract

Quantifying Expected Uncertainty Reduction and Value of Information Using Ensemble-Variance Analysis

Cited by 27 publications

References 13 publications

Data-space inversion with ensemble smoother

Data-space inversion with ensemble smoother

Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine Learning

Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine Learning

Contact Info

Product

Resources

About