Fracture Permeability Estimation Under Complex Physics: A Data-Driven Model Using Machine Learning

2021 ◽  
Author(s):  
Xupeng He ◽  
Weiwei Zhu ◽  
Ryan Santoso ◽  
Marwa Alsinan ◽  
Hyung Kwak ◽  
...  
Keyword(s):  
Machine Learning ◽  
Surrogate Model ◽  
Bayesian Optimization ◽  
Data Driven ◽  
Uncertain Parameters ◽  
Fracture Permeability ◽  
Model Based ◽  
Training Samples ◽  
Proposed Model ◽  
Inputs And Outputs

Abstract The permeability of fractures, including natural and hydraulic, are essential parameters for the modeling of fluid flow in conventional and unconventional fractured reservoirs. However, traditional analytical cubic law (CL-based) models used to estimate fracture permeability show unsatisfactory performance when dealing with different dynamic complexities of fractures. This work presents a data-driven, physics-included model based on machine learning as an alternative to traditional methods. The workflow for the development of the data-driven model includes four steps. Step 1: Identify uncertain parameters and perform Latin Hypercube Sampling (LHS). We first identify the uncertain parameters which affect the fracture permeability. We then generate training samples using LHS. Step 2: Perform training simulations and collect inputs and outputs. In this step, high-resolution simulations with parallel computing for the Navier-Stokes equations (NSEs) are run for each of the training samples. We then collect the inputs and outputs from the simulations. Step 3: Construct an optimized data-driven surrogate model. A data-driven model based on machine learning is then built to model the nonlinear mapping between the inputs and outputs collected from Step 2. Herein, Artificial Neural Network (ANN) coupling with Bayesian optimization algorithm is implemented to obtain the optimized surrogate model. Step 4: Validate the proposed data-driven model. In this step, we conduct blind validation on the proposed model with high-fidelity simulations. We further test the developed surrogate model with newly generated fracture cases with a broad range of roughness and tortuosity under different Reynolds numbers. We then compare its performance to the reference NSEs solutions. Results show that the developed data-driven model delivers good accuracy exceeding 90% for all training, validation, and test samples. This work introduces an integrated workflow for developing a data-driven, physics-included model using machine learning to estimate fracture permeability under complex physics (e.g., inertial effect). To our knowledge, this technique is introduced for the first time for the upscaling of rock fractures. The proposed model offers an efficient and accurate alternative to the traditional upscaling methods that can be readily implemented in reservoir characterization and modeling workflows.

CO2 Leakage Rate Forecasting Using Optimized Deep Learning

2021 ◽  
Author(s):  
Xupeng He ◽  
Weiwei Zhu ◽  
Ryan Santoso ◽  
Marwa Alsinan ◽  
Hyung Kwak ◽  
...  
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Surrogate Model ◽  
Network Architecture ◽  
Leakage Rate ◽  
Bayesian Optimization ◽  
Data Driven ◽  
Co2 Leakage ◽  
Model Based ◽  
Uncertainty Parameters

Abstract Geologic CO2 Sequestration (GCS) is a promising engineering technology to reduce global greenhouse emissions. Real-time forecasting of CO2 leakage rates is an essential aspect of large-scale GCS deployment. This work introduces a data-driven, physics-featuring surrogate model based on deep-learning technique for CO2 leakage rate forecasting. The workflow for the development of data-driven, physics-featuring surrogate model includes three steps: 1) Datasets Generation: We first identify uncertainty parameters that affect the objective of interests (i.e., CO2 leakage rates). For the identified uncertainty parameters, various realizations are then generated based on Latin Hypercube Sampling (LHS). High-fidelity simulations based on a two-phase black-oil solver within MRST are performed to generate the objective functions. Datasets including inputs (i.e., the uncertainty parameters) and outputs (CO2 leakage rates) are collected. 2) Surrogate Development: In this step, a time-series surrogate model using long short-term memory (LSTM) is constructed to map the nonlinear relationship between these uncertainty parameters as inputs and CO2 leakage rates as outputs. We perform Bayesian optimization to automate the tuning of hyperparameters and network architecture instead of the traditional trial-error tuning process. 3) Uncertainty Analysis: This step aims to perform Monte Carlo (MC) simulations using the successfully trained surrogate model to explore uncertainty propagation. The sampled realizations are collected in the form of distributions from which the probabilistic forecast of percentiles, P10, P50, and P50, are evaluated. We propose a data-driven, physics-featuring surrogate model based on LSTM for CO2 leakage rate forecasting. We demonstrate its performance in terms of accuracy and efficiency by comparing it with ground-truth solutions. The proposed deep-learning workflow shows promising potential and could be readily implemented in commercial-scale GCS for real-time monitoring applications.

scholarly journals Data-driven symbol detection via model-based machine learning

2020 ◽  
Vol 20 (3) ◽  
pp. 283-317
Author(s):  
Nariman Farsad ◽  
Nir Shlezinger ◽  
Andrea J. Goldsmith ◽  
Yonina C. Eldar
Keyword(s):  
Machine Learning ◽  
Data Driven ◽  
Model Based ◽  
Symbol Detection

scholarly journals Model-based tumor subclonal reconstruction

2019 ◽  
Author(s):  
Giulio Caravagna ◽  
Timon Heide ◽  
Marc Williams ◽  
Luis Zapata ◽  
Daniel Nichol ◽  
...  
Keyword(s):  
Machine Learning ◽  
Evolutionary Theory ◽  
Data Driven ◽  
Next Generation Sequencing Data ◽  
Tumor Evolution ◽  
Sequencing Data ◽  
Model Based ◽  
Novel Approach ◽  
History Of ◽  
Multiple Samples

AbstractThe vast majority of cancer next-generation sequencing data consist of bulk samples composed of mixtures of cancer and normal cells. To study tumor evolution, subclonal reconstruction approaches based on machine learning are used to separate subpopulation of cancer cells and reconstruct their ancestral relationships. However, current approaches are entirely data-driven and agnostic to evolutionary theory. We demonstrate that systematic errors occur in subclonal reconstruction if tumor evolution is not accounted for, and that those errors increase when multiple samples are taken from the same tumor. To address this issue, we present a novel approach for model-based subclonal reconstruction that combines data-driven machine learning with evolutionary theory. Using public, synthetic and newly generated data, we show the method is more robust and accurate than current techniques in both single-sample and multi-region sequencing data. With careful data curation and interpretation, we show how the method allows minimizing the confounding factors that affect non-evolutionary methods, leading to a more accurate recovery of the evolutionary history of human tumors.

Data-driven stochastic model for cross-interacting processes with different time scales

2021 ◽  
Author(s):  
Andrey Gavrilov ◽  
Aleksei Seleznev ◽  
Dmitry Mukhin ◽  
Alexander Feigin
Keyword(s):  
Time Series ◽  
Stochastic Model ◽  
Time Scales ◽  
Time Scale ◽  
Sampling Interval ◽  
Bayesian Optimization ◽  
Data Driven ◽  
Middle Pleistocene ◽  
Model Based ◽  
Different Time Scales

<p>The problem of modeling interaction between processes with different time scales is very important in geoscience. In this report, we propose a new form of empirical evolution operator model based on the analysis of multiple time series representing processes with different time scales. We assume that the time series are given on the same time interval.</p><p>To construct the model, we extend the previously developed general form of nonlinear stochastic model based on artificial neural networks and designed for the case of time series with constant sampling interval [1]. This sampling interval is related to the main time scale of the process under consideration, which is described by the deterministic component of the model, while the faster time scales are modeled by its stochastic component, possibly depending on the system’s state. This model also includes slower processes in the form of weak time-dependence, as well as external forcing. The structure of the model is optimized using Bayesian approach [1]. The model has proven its efficiency in a number of applications [2-4].</p><p>The idea of modeling time series with different time scales is to formulate the above-described model individually for each time scale, and then to include the parameterized influence of the other time scales in it. Particularly, the influence of “slower” time series is included in the form of parameter trends, and the influence of “faster” time series is included by time-averaging their statistics. The algorithm and first results of comparison between the new model and the model without cross-interactions will be discussed.</p><p>The work was supported by the Russian Science Foundation (Grant No. 20-62-46056).</p><p>1. Gavrilov, A., Loskutov, E., & Mukhin, D. (2017). Bayesian optimization of empirical model with state-dependent stochastic forcing. Chaos, Solitons & Fractals, 104, 327–337. http://doi.org/10.1016/j.chaos.2017.08.032</p><p>2. Mukhin, D., Kondrashov, D., Loskutov, E., Gavrilov, A., Feigin, A., & Ghil, M. (2015). Predicting Critical Transitions in ENSO models. Part II: Spatially Dependent Models. Journal of Climate, 28(5), 1962–1976. http://doi.org/10.1175/JCLI-D-14-00240.1</p><p>3. Gavrilov, A., Seleznev, A., Mukhin, D., Loskutov, E., Feigin, A., & Kurths, J. (2019). Linear dynamical modes as new variables for data-driven ENSO forecast. Climate Dynamics, 52(3–4), 2199–2216. http://doi.org/10.1007/s00382-018-4255-7</p><p>4. Mukhin, D., Gavrilov, A., Loskutov, E., Kurths, J., & Feigin, A. (2019). Bayesian Data Analysis for Revealing Causes of the Middle Pleistocene Transition. Scientific Reports, 9(1), 7328. http://doi.org/10.1038/s41598-019-43867-3</p>

Dynamic Predictive Maintenance Model Based on Data-Driven Machinery Prognostics Approach

2011 ◽  
Vol 143-144 ◽  
pp. 901-906
Author(s):  
W.Z. Liao ◽  
Y. Wang
Keyword(s):  
Paradigm Shift ◽  
Health Condition ◽  
Predictive Maintenance ◽  
Data Driven ◽  
Computational Results ◽  
Maintenance Policy ◽  
Model Based ◽  
Proposed Model ◽  
Maintenance Model

As an increasing number of manufacturers realize the importance of adopting new maintenance technologies to enable systems to achieve near-zero downtime, machinery prognostics which enables this paradigm shift from traditional fail-and-fix maintenance to a predict-and-prevent paradigm has arose interests from researchers. Machine's condition and degradation estimated by machinery prognostics approach can be used to support predictive maintenance policy. This paper develops a novel data-driven machine prognostics approach to assess machine's health condition and predict machine degradation. With this prognostics information, a predictive maintenance model is constructed to decide machine's maintenance threshold and predictive maintenance cycles number. Through a case study, this predictive maintenance model is verified, and the computational results show that this proposed model is efficient and practical.

Prediction of Nitrogen Concentration in Fuel Cells Using Data-Driven Modeling

2019 ◽  
Author(s):  
Tong Lin ◽  
Leiming Hu ◽  
Shawn Litster ◽  
Levent Burak Kara
Keyword(s):  
Machine Learning ◽  
Fuel Cells ◽  
Fuel Cell ◽  
Nitrogen Concentration ◽  
Proton Exchange ◽  
Learning System ◽  
Data Driven ◽  
Nitrogen Accumulation ◽  
Model Based ◽  
Data Generator

Abstract This paper presents a set of data-driven methods for predicting nitrogen concentration in proton exchange membrane fuel cells (PEMFCs). The nitrogen that accumulates in the anode channel is a critical factor giving rise to significant inefficiency in fuel cells. While periodically purging the gases in the anode channel is a common strategy to combat nitrogen accumulation, such open-loop strategies also create sub-optimal purging decisions. Instead, an accurate prediction of nitrogen concentration can help devise optimal purging strategies. However, model based approaches such as CFD simulations for nitrogen prediction are often unavailable for long-stack fuel cells due to the complexity of the chemical environment, or are inherently slow preventing them from being used for real-time nitrogen prediction on deployed fuel cells. As one step toward addressing this challenge, we explore a set of data-driven techniques for learning a regression model from the input parameters to the nitrogen build-up using a model-based fuel cell simulator as an offline data generator. This allows the trained machine learning system to make fast decisions about nitrogen concentration during deployment based on other parameters that can be obtained through sensors. We describe the various methods we explore, compare the outcomes, and provide future directions in utilizing machine learning for fuel cell physics modeling in general.

scholarly journals A Convolutional Neural Network with Fletcher–Reeves Algorithm for Hyperspectral Image Classification

2019 ◽  
Vol 11 (11) ◽  
pp. 1325 ◽  
Author(s):  
Chen Chen ◽  
Yi Ma ◽  
Guangbo Ren
Keyword(s):  
Image Classification ◽  
Classification Accuracy ◽  
Hyperspectral Image ◽  
Training Sample ◽  
Practical Applications ◽  
Model Based ◽  
Training Samples ◽  
Proposed Model ◽  
Convergence Performance ◽  
Hyperspectral Classification

Deep learning models, especially the convolutional neural networks (CNNs), are very active in hyperspectral remote sensing image classification. In order to better apply the CNN model to hyperspectral classification, we propose a CNN model based on Fletcher–Reeves algorithm (F–R CNN), which uses the Fletcher–Reeves (F–R) algorithm for gradient updating to optimize the convergence performance of the model in classification. In view of the fact that there are fewer optional training samples in practical applications, we further propose a method of increasing the number of samples by adding a certain degree of perturbed samples, which can also test the anti-interference ability of classification methods. Furthermore, we analyze the anti-interference and convergence performance of the proposed model in terms of different training sample data sets, different batch training sample numbers and iteration time. In this paper, we describe the experimental process in detail and comprehensively evaluate the proposed model based on the classification of CHRIS hyperspectral imagery covering coastal wetlands, and further evaluate it on a commonly used hyperspectral image benchmark dataset. The experimental results show that the accuracy of the two models after increasing training samples and adjusting the number of batch training samples is improved. When the number of batch training samples is continuously increased to 350, the classification accuracy of the proposed method can still be maintained above 80.7%, which is 2.9% higher than the traditional one. And its time consumption is less than that of the traditional one while ensuring classification accuracy. It can be concluded that the proposed method has anti-interference ability and outperforms the traditional CNN in terms of batch computing adaptability and convergence speed.

scholarly journals A Data-Driven Emotion Model for English Learners Based on Machine Learning

2021 ◽  
Vol 16 (08) ◽  
pp. 34
Author(s):  
Zhao Zheng ◽  
Kew Si Na
Keyword(s):  
Machine Learning ◽  
Academic Performance ◽  
Facial Expression ◽  
English Learners ◽  
Experimental Results ◽  
Data Driven ◽  
Proposed Model ◽  
Research Findings ◽  
Emotion Model ◽  
The Relationship

Learning confusion is a common emotion among learners. With the aid of machine learning, this paper develops a data-driven emotion model that automatically recognizes learning confusion in facial expression images. The data on learning behaviors and learning confusion of multiple subjects were collected through an online English evaluation experiment, and imported to the proposed model to derive the relationship between learning confusion and academic performance, which is measured by the correctness of the students’ answers to the test questions. The experimental results show that the students with learning confusion had relatively low correct rate of answering test questions. The research findings reveal the relationship between learning confusion and academic performance, laying the basis for predicting the academic performance of English learners through machine learning.

Sign in / Sign up

Export Citation Format

Share Document