Permeability is one of the main oil reservoir characteristics.It affects potential oil production,well-completion technologies,the choice of enhanced oil recovery methods,and more.The methods used to determine and pre...Permeability is one of the main oil reservoir characteristics.It affects potential oil production,well-completion technologies,the choice of enhanced oil recovery methods,and more.The methods used to determine and predict reservoir permeability have serious shortcomings.This article aims to refine and adapt machine learning techniques using historical data from hydrocarbon field development to evaluate and predict parameters such as the skin factor and permeability of the remote reservoir zone.The article analyzes data from 4045 wells tests in oil fields in the Perm Krai(Russia).An evaluation of the performance of different Machine Learning(ML)al-gorithms in the prediction of the well permeability is performed.Three different real datasets are used to train more than 20 machine learning regressors,whose hyperparameters are optimized using Bayesian Optimization(BO).The resulting models demonstrate significantly better predictive performance compared to traditional methods and the best ML model found is one that never was applied before to this problem.The permeability prediction model is characterized by a high R^(2) adjusted value of 0.799.A promising approach is the integration of machine learning methods and the use of pressure recovery curves to estimate permeability in real-time.The work is unique for its approach to predicting pressure recovery curves during well operation without stopping wells,providing primary data for interpretation.These innovations are exclusive and can improve the accuracy of permeability forecasts.It also reduces well downtime associated with traditional well-testing procedures.The proposed methods pave the way for more efficient and cost-effective reservoir development,ultimately sup-porting better decision-making and resource optimization in oil production.展开更多
Resilience assessment of transportation infrastructure is a crucial aspect of ensuring the continued functionality of a city or region in the face of various disruptions.However,these infrastructures are also vulnerab...Resilience assessment of transportation infrastructure is a crucial aspect of ensuring the continued functionality of a city or region in the face of various disruptions.However,these infrastructures are also vulnerable to various types of disruptions,such as natural disasters.The ability of transportation infrastructures to withstand and recover from such disruptions is referred to as their resilience.This research presents a comprehensive framework to develop the resilience surface for assessing the resilience of transportation infrastructure such as bridges,roads,and tunnels.The framework involves the identification of the unique damage configurations through performing the fragility analysis,and the restoration of the infrastructures through developing recovery curves for each damage configuration by considering the relevant restoration data.The framework also considers the inherent uncertainty in the hazard intensity,modeling uncertainty,and restoration process.The framework is illustrated through the application to a case study of a highway bridge in Canada.The aim of this paper is to provide a useful tool for decision-makers to evaluate and improve the resilience of transportation infrastructures.展开更多
基金funded by the Ministry of Science and Higher Education of the Russian Federation(Project No.FSNM-2024-0005).
文摘Permeability is one of the main oil reservoir characteristics.It affects potential oil production,well-completion technologies,the choice of enhanced oil recovery methods,and more.The methods used to determine and predict reservoir permeability have serious shortcomings.This article aims to refine and adapt machine learning techniques using historical data from hydrocarbon field development to evaluate and predict parameters such as the skin factor and permeability of the remote reservoir zone.The article analyzes data from 4045 wells tests in oil fields in the Perm Krai(Russia).An evaluation of the performance of different Machine Learning(ML)al-gorithms in the prediction of the well permeability is performed.Three different real datasets are used to train more than 20 machine learning regressors,whose hyperparameters are optimized using Bayesian Optimization(BO).The resulting models demonstrate significantly better predictive performance compared to traditional methods and the best ML model found is one that never was applied before to this problem.The permeability prediction model is characterized by a high R^(2) adjusted value of 0.799.A promising approach is the integration of machine learning methods and the use of pressure recovery curves to estimate permeability in real-time.The work is unique for its approach to predicting pressure recovery curves during well operation without stopping wells,providing primary data for interpretation.These innovations are exclusive and can improve the accuracy of permeability forecasts.It also reduces well downtime associated with traditional well-testing procedures.The proposed methods pave the way for more efficient and cost-effective reservoir development,ultimately sup-porting better decision-making and resource optimization in oil production.
文摘Resilience assessment of transportation infrastructure is a crucial aspect of ensuring the continued functionality of a city or region in the face of various disruptions.However,these infrastructures are also vulnerable to various types of disruptions,such as natural disasters.The ability of transportation infrastructures to withstand and recover from such disruptions is referred to as their resilience.This research presents a comprehensive framework to develop the resilience surface for assessing the resilience of transportation infrastructure such as bridges,roads,and tunnels.The framework involves the identification of the unique damage configurations through performing the fragility analysis,and the restoration of the infrastructures through developing recovery curves for each damage configuration by considering the relevant restoration data.The framework also considers the inherent uncertainty in the hazard intensity,modeling uncertainty,and restoration process.The framework is illustrated through the application to a case study of a highway bridge in Canada.The aim of this paper is to provide a useful tool for decision-makers to evaluate and improve the resilience of transportation infrastructures.
