Probabilistic Data-Driven Prediction of Wellbore Signatures in High-Dimensional Data Using Bayesian Networks

SPE Journal ◽  
2018 ◽  
Vol 23 (04) ◽  
pp. 1090-1104 ◽  
Author(s):  
Nastaran Bassamzadeh ◽  
Roger Ghanem
Keyword(s):  
Production Rate ◽  
Oil Field ◽  
Assessment Tools ◽  
Data Driven ◽  
High Dimensional ◽  
Dimensional System ◽  
Probabilistic Prediction ◽  
Modeling Framework ◽  
Data Set ◽  
Local Linear Embedding

Summary Accurate, data-driven, stochastic models for fluid-flow prediction in hydrocarbon reservoirs are of particular interest to reservoir engineers. Being computationally less costly than conventional physical simulations, such predictive models can serve as rapid-risk-assessment tools. In this research, we seek to probabilistically predict the oil-production rate at locations where limited data are observed using the available data at other spatial points in the oil field. To do so, we use the Bayesian network (BN), which is a modeling framework for capturing dependencies between uncertain variables in a high-dimensional system. The model is applied to a real data set from the Gulf of Mexico (GOM) and it is shown that BN is able to predict the production rate with 86% accuracy. The results are compared with neural-network and co-Kriging methods. Moreover, BN structure enables us to select the most-relevant variables for prediction, and thus we managed to reduce the input dimension from 36 to 17 variables while preserving the same prediction accuracy. Similarly, we use the local-linear-embedding (LLE) method as a feature-extraction tool to nonlinearly reduce the input dimension from 36 to 10 variables with negligible loss in accuracy. Accordingly, we claim that BN is a valuable modeling tool that can be efficiently used for probabilistic prediction and dimension reduction in the oil industry.

Digitalization of Seagoing Vessels Under High Dimensional Data Driven Models

2017 ◽  
Author(s):  
Lokukaluge P. Perera ◽  
Brage Mo
Keyword(s):  
Domain Knowledge ◽  
Large Scale ◽  
Dimensional Space ◽  
Data Driven ◽  
High Dimensional ◽  
Data Handling ◽  
Shipping Industry ◽  
Data Set ◽  
Data Clusters ◽  
Ship Performance

Modern ships are supported by internet of things (IoT) to collect ship performance and navigation information. That should be utilized towards digitalization of the shipping industry. However, such information collection systems are always associated with large-scale data sets, so called Big Data, where various industrial challenges are encountered during the respective data handling processes. This study proposes a data handling framework with data driven models (i.e. digital models) to cope with the shipping industrial challenges as the main contribution, where conventional mathematical models may fail. The proposed data driven models are developed in a high dimensional space, where the respective ship performance and navigation parameters of a selected vessel are separated as several data clusters. Hence, this study identifies the distribution of the respective data clusters and the structure of each data cluster in relation to ship performance and navigation conditions. An appropriate structure into the data set of ship performance and navigation parameters is assigned by this method as the main contribution. However, the domain knowledge (i.e. vessel operational and navigation conditions) is also included in this situation to derive a meaningful data structure.

scholarly journals Physics-informed neural networks method in high-dimensional integrable systems

2021 ◽  
Author(s):  
Zheng Wu Miao ◽  
Yong Chen
Keyword(s):  
Neural Networks ◽  
Integrable Systems ◽  
Initial Boundary ◽  
Initial Boundary Value Problem ◽  
Data Driven ◽  
High Dimensional ◽  
Classical Solutions ◽  
Dimensional System ◽  
Kp Equation ◽  
Initial Boundary Value

In this paper, the physics-informed neural networks (PINNs) are applied to high-dimensional system to solve the [Formula: see text]-dimensional initial-boundary value problem with [Formula: see text] hyperplane boundaries. This method is used to solve the most classic (2+1)-dimensional integrable Kadomtsev–Petviashvili (KP) equation and (3+1)-dimensional reduced KP equation. The dynamics of (2+1)-dimensional local waves such as solitons, breathers, lump and resonance rogue are reproduced. Numerical results display that the magnitude of the error is much smaller than the wave height itself, so it is considered that the classical solutions in these integrable systems are well obtained based on the data-driven mechanism.

A Review and evaluation of Machine Translation methods for Lumasaaba

2020 ◽  
pp. 3-17
Author(s):  
Peter Nabende
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Machine Translation ◽  
Language Processing ◽  
Research Area ◽  
Data Driven ◽  
East African ◽  
Data Set ◽  
African Languages ◽  
Translation Methods

Natural Language Processing for under-resourced languages is now a mainstream research area. However, there are limited studies on Natural Language Processing applications for many indigenous East African languages. As a contribution to covering the current gap of knowledge, this paper focuses on evaluating the application of well-established machine translation methods for one heavily under-resourced indigenous East African language called Lumasaaba. Specifically, we review the most common machine translation methods in the context of Lumasaaba including both rule-based and data-driven methods. Then we apply a state of the art data-driven machine translation method to learn models for automating translation between Lumasaaba and English using a very limited data set of parallel sentences. Automatic evaluation results show that a transformer-based Neural Machine Translation model architecture leads to consistently better BLEU scores than the recurrent neural network-based models. Moreover, the automatically generated translations can be comprehended to a reasonable extent and are usually associated with the source language input.

scholarly journals A Data-Driven Surrogate Approach for the Temporal Stability Forecasting of Vegetation Covered Dikes

Water ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 107
Author(s):  
Elahe Jamalinia ◽  
Faraz S. Tehrani ◽  
Susan C. Steele-Dunne ◽  
Philip J. Vardon
Keyword(s):  
Numerical Simulation ◽  
Water Flux ◽  
Temporal Stability ◽  
Synthetic Data ◽  
Climatic Conditions ◽  
Training Data ◽  
Data Driven ◽  
Data Set ◽  
Surface Cracking ◽  
Real Time Analysis

Climatic conditions and vegetation cover influence water flux in a dike, and potentially the dike stability. A comprehensive numerical simulation is computationally too expensive to be used for the near real-time analysis of a dike network. Therefore, this study investigates a random forest (RF) regressor to build a data-driven surrogate for a numerical model to forecast the temporal macro-stability of dikes. To that end, daily inputs and outputs of a ten-year coupled numerical simulation of an idealised dike (2009–2019) are used to create a synthetic data set, comprising features that can be observed from a dike surface, with the calculated factor of safety (FoS) as the target variable. The data set before 2018 is split into training and testing sets to build and train the RF. The predicted FoS is strongly correlated with the numerical FoS for data that belong to the test set (before 2018). However, the trained model shows lower performance for data in the evaluation set (after 2018) if further surface cracking occurs. This proof-of-concept shows that a data-driven surrogate can be used to determine dike stability for conditions similar to the training data, which could be used to identify vulnerable locations in a dike network for further examination.

scholarly journals A COVID-19 Supply Chain Management Strategy Based on Variable Production under Uncertain Environment Conditions

2021 ◽  
Vol 18 (4) ◽  
pp. 1662
Author(s):  
Mohammed Alkahtani ◽  
Muhammad Omair ◽  
Qazi Salman Khalid ◽  
Ghulam Hussain ◽  
Imran Ahmad ◽  
...  
Keyword(s):  
Supply Chain ◽  
Supply Chain Management ◽  
Production Rate ◽  
Manufacturing System ◽  
Working Environment ◽  
Data Set ◽  
Manufacturing Firm ◽  
Chain Management ◽  
Ripple Effects ◽  
Multi Stage

The management of a controllable production in the manufacturing system is essential to achieve viable advantages, particularly during emergency conditions. Disasters, either man-made or natural, affect production and supply chains negatively with perilous effects. On the other hand, flexibility and resilience to manage the perpetuated risks in a manufacturing system are vital for achieving a controllable production rate. Still, these performances are strongly dependent on the multi-criteria decision making in the working environment with the policies launched during the crisis. Undoubtedly, health stability in a society generates ripple effects in the supply chain due to high demand fluctuation, likewise due to the Coronavirus disease-2019 (COVID-19) pandemic. Incorporation of dependent demand factors to manage the risk from uncertainty during this pandemic has been a challenge to achieve a viable profit for the supply chain partners. A non-linear supply chain management model is developed with a controllable production rate to provide an economic benefit to the manufacturing firm in terms of the optimized total cost of production and to deal with the different situations under variable demand. The costs in the model are set as fuzzy to cope up with the uncertain conditions created by lasting pandemic. A numerical experiment is performed by utilizing the data set of the multi-stage manufacturing firm. The optimal results provide support for the industrial managers based on the proactive plan by the optimal utilization of the resources and controllable production rate to cope with the emergencies in a pandemic.

scholarly journals Diffuse approximation for identification of the mechanical properties of microcapsules

2020 ◽  
pp. 108128652097760
Author(s):  
Carlos Quesada ◽  
Claire Dupont ◽  
Pierre Villon ◽  
Anne-Virginie Salsac
Keyword(s):  
Mechanical Properties ◽  
Active Material ◽  
Liquid Core ◽  
Constitutive Law ◽  
Data Driven ◽  
Membrane Properties ◽  
Mechanical Resistance ◽  
Data Set ◽  
Diffuse Approximation ◽  
Capsule Size

A novel data-driven real-time procedure based on diffuse approximation is proposed to characterize the mechanical behavior of liquid-core microcapsules from their deformed shape and identify the mechanical properties of the submicron-thick membrane that protects the inner core through inverse analysis. The method first involves experimentally acquiring the deformed shape that a given microcapsule takes at steady state when it flows through a microfluidic microchannel of comparable cross-sectional size. From the mid-plane capsule profile, we deduce two characteristic geometric quantities that uniquely characterize the shape taken by the microcapsule under external hydrodynamic stresses. To identify the values of the unknown rigidity of the membrane and of the size of the capsule, we compare the geometric quantities with the values predicted numerically using a fluid-structure-interaction model by solving the three-dimensional capsule-flow interactions. The complete numerical data set is obtained off-line by systematically varying the governing parameters of the problem, i.e. the capsule-to-tube confinement ratio, and the capillary number, which is the ratio of the viscous to elastic forces. We show that diffuse approximation efficiently estimates the unknown mechanical resistance of the capsule membrane. We validate the data-driven procedure by applying it to the geometric and mechanical characterization of ovalbumin microcapsules (diameter of the order of a few tens of microns). As soon as the capsule is sufficiently deformed to exhibit a parachute shape at the rear, the capsule size and surface shear modulus are determined with an accuracy of 0.2% and 2.7%, respectively, as compared with 2–3% and 25% without it, in the best cases (Hu et al. Characterizing the membrane properties of capsules flowing in a square-section microfluidic channel: Effects of the membrane constitutive law. Phys Rev E 2013; 87(6): 063008). Diffuse approximation thus allows the capsule size and membrane elastic resistance to be provided quasi-instantly with very high precision. This opens interesting perspectives for industrial applications that require tight control of the capsule mechanical properties in order to secure their behavior when they transport active material.

Fusion based learning approach for predicting concrete pouring productivity based on construction and supply parameters

2016 ◽  
Vol 16 (2) ◽  
pp. 185-202 ◽  
Author(s):  
Mojtaba Maghrebi ◽  
Ali Shamsoddini ◽  
S. Travis Waller
Keyword(s):  
Supply Chain ◽  
Production Rate ◽  
Learning Method ◽  
Data Set ◽  
Content Type ◽  
Field Database ◽  
The Stability ◽  
Stable Learning ◽  
Ready Mixed Concrete ◽  
Practical Implications

Purpose The purpose of this paper is to predict the concrete pouring production rate by considering both construction and supply parameters, and by using a more stable learning method. Design/methodology/approach Unlike similar approaches, this paper considers not only construction site parameters, but also supply chain parameters. Machine learner fusion-regression (MLF-R) is used to predict the production rate of concrete pouring tasks. Findings MLF-R is used on a field database including 2,600 deliveries to 507 different locations. The proposed data set and the results are compared with ANN-Gaussian, ANN-Sigmoid and Adaboost.R2 (ANN-Gaussian). The results show better performance of MLF-R obtaining the least root mean square error (RMSE) compared with other methods. Moreover, the RMSEs derived from the predictions by MLF-R in some trials had the least standard deviation, indicating the stability of this approach among similar used approaches. Practical implications The size of the database used in this study is much larger than the size of databases used in previous studies. It helps authors draw their conclusions more confidently and introduce more generalised models that can be used in the ready-mixed concrete industry. Originality/value Introducing a more stable learning method for predicting the concrete pouring production rate helps not only construction parameters, but also traffic and supply chain parameters.

Sign in / Sign up

Export Citation Format

Share Document