Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
Abdollahzadeh, Asaad
Identifying New Behind Casing Opportunities Using Machine Learning
Fadhil, Imran M (PETRONAS Digital Sdn Bhd) | Shah, Jamari M (PETRONAS) | Sansudin, Salmi (PETRONAS) | Abdollahzadeh, Asaad (PETRONAS Digital Sdn Bhd) | Husiyandi, Husni (PETRONAS Digital Sdn Bhd) | Azizul, Nur Aimi Azimah (PETRONAS Digital Sdn Bhd) | Hasnan, Fairuz Hidayah (PETRONAS Digital Sdn Bhd) | Thai, Yuan Jiun (PETRONAS Digital Sdn Bhd)
Abstract This paper discusses the adoption of Machine Learning (ML) approach to identify new Behind Casing Opportunities (BCO) in two brown fields (B and S) offshore East Malaysia. A multi-stage field-based ML models were developed based on selected wells and consequently used to predict reservoir characteristics in completed wells. The predicted results indicated new upside BCO for add perforation candidate. Raw and interpreted data from B and S fields were analyzed and processed for model training and evaluation. For the case of identifying new opportunity, a specific model development strategy and train dataset selection was employed. The trained ML models evaluated to select the optimal models to predict lithologies, porosity, permeability and water saturations which are then been compared against the actual interpretation. Eventually, the identified upside potentials are validated by Subject Matter Experts (SME) before being proposed as add perforation candidate. It was observed that the modelsโ performances vary between the two fields due to unique geological complexity as well as the varying quality of raw and interpreted data from each field. Field B which is more geologically complex performs less compared to Field S. In conclusion, this study provides and insight on the advantages and limitations of machine learning to identify new upside BCO in completed wells. The novelty in this work is in the specific model development strategy to identify new upside BCO potentials. This work may be beneficial and essential especially in enhancing resource monetization in brown fields which face challenges in terms of high idle well percentage, low recovery, and declining production.
- North America > United States > Texas (1.00)
- Asia (1.00)
- Africa > Middle East > Libya > Murzuq District (0.25)
- Geophysics > Borehole Geophysics (1.00)
- Geophysics > Seismic Surveying (0.68)
- Well Completion > Completion Installation and Operations > Perforating (1.00)
- Reservoir Description and Dynamics > Reservoir Characterization (1.00)
- Reservoir Description and Dynamics > Formation Evaluation & Management (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)
Digital Transformation of Offshore Structure Weight Control Management into Digitally Integrated and Intelligent Analytical Tool
Alias, Nur Dalila (PETRONAS) | Wong, Bak Shiiun (PETRONAS) | Anas, Wan Zalikha (PETRONAS) | Sulaiman, Nur Amalina (PETRONAS) | Epui, Mildred Vanessa (PETRONAS) | A Rahman, Azam (PETRONAS) | A Rahman, Ahmad Rizal (PETRONAS) | Yeoh, Sue Jane (PETRONAS) | Abdollahzadeh, Asaad (PETRONAS) | Ngadan, Linda William (PETRONAS) | Tang, Horng Eng (PETRONAS) | Chooi, Wai Fun (PETRONAS) | Khan, Riaz (PETRONAS) | Ng, Sook Moi (PETRONAS) | Saminal, Siti Nurshamsinazzatulbalqish (PETRONAS) | Ibrahim, M Mujiduddin (PETRONAS) | Hamid, Marklin (PETRONAS) | Suhaili, Ave Suhendra (PETRONAS) | M Hisham, M Said Farhan (MMC Oil)
Abstract Leveraged on the abundant weight data comprised of more than 200 offshore platforms, a smart digitalized analytical tool called i-WEIGHT, an integrated weight control tool consisting of three (3) main modules: centralized multi-discipline weight database module for all offshore platforms, seamlessly linked with Insights dashboard module in providing actionable insights, and weight predictive module supported by Machine Learning (ML) model was developed. This paper discussed the Minimum Viable Product (MVP) Phase 1 development outcome, using a close-loop weight control ecosystem for continuous update of validated weight data in Module 1, and eventually improve & enhance capability of both the EDA and Predictive module. Using a supervised machine learning algorithms, the identified target variables were observed to provide weight prediction between 16% to 38% of Mean Absolute Percentage Error (MAPE), using Extreme Gradient Boosting Regressor (XGBR) algorithm. Top 10 important features were identified for each target variable, which provide insights to the operators on critical data required for topside with identified missing equipment weight data for future i-WEIGHT improvement. Based on more than 200 integrated platform topside data gathered for this study, consolidated insights from the data enabled operators to identify the threat of current data quality and thus bringing forward a promising opportunity to enhance platform weight data management system. Having a centralized and automated platform weights data, this tool has the potential answers for United Nationsโ Sustainability Development Goals, in particular Goal 9.4, where the study represents a small but crucial step to upgrade from an existing conventional process into a digitally driven operation, introducing a sustainable ecosystem in offshore structure weight management, thus fostering sustainable growth within the industry.
- Health & Medicine > Therapeutic Area (1.00)
- Energy > Oil & Gas > Upstream (1.00)
An Adaptive Evolutionary Algorithm for History-Matching
Abdollahzadeh, Asaad (BP) | Christie, Mike (Heriot-Watt University) | Corne, David (Heriot-Watt University) | Davies, Brian (BP) | Elliott, Michael (BP)
Abstract Efficient history matching of highly uncertain reservoir models is important in many applications of the reservoir engineering area, such as reservoir management, production prediction, and development optimisation. History matching has commonly been done manually by a tedious trial and error approach in which global and local adjustments are done to the model properties until a best model is obtained which honours production response of the reservoir model. With recent advances in computer science and hardware, assisted history matching techniques can improve the quality of the match within less time and effort. Stochastic evolutionary algorithms are popular methods in history matching and have been widely used to explore and search the global parameter search space and find multiple good fitting models. They are quite easy to implement, and if well applied, able to be globally convergent even in complex problems such as history matching. General critiques of these algorithms include high computational demands and demand for the tuning of the algorithmโs control parameters. Adaptation methods for EAs adjust algorithmโs control parameters during the evolution to improve the search quality and accelerate the convergence by guiding search toward appropriate regions of the search space. This insures a balance between exploration and exploitation properties of the algorithm. In this paper, we introduce a novel adaptive scheme for EAs, which intelligently adapts the control parameter that affects the diversity of the population. The adapted control parameter is number of selected to generated solutions in each generation, which controls the balance between exploration and exploitation. We apply proposed algorithm to optimisation problem of two test functions and history matching problem of a well-known synthetic reservoir simulation model. Our results show that, compared with the original EAs, adaptive EA is able to find better spread of fitting models with better convergence to the minimum misfit, thus more effective and efficient history matching is achieved.
- Europe (1.00)
- North America > United States > Texas (0.28)
- North America > United States > Michigan (0.28)
Summary The topic of automatically history-matched reservoir models has seen much research activity in recent years. History matching is an example of an inverse problem, and there is significant active research on inverse problems in many other scientific and engineering areas. While many techniques from other fields, such as genetic algorithms, evolutionary strategies, differential evolution, particle swarm optimization, and the ensemble Kalman filter have been tried in the oil industry, more recent and effective ideas have yet to be tested. One of these relatively untested ideas is a class of algorithms known as estimation of distribution algorithms (EDAs). EDAs are population-based algorithms that use probability models to estimate the probability distribution of promising solutions, and then to generate new candidate solutions. EDAs have been shown to be very efficient in very complex high-dimensional problems. An example of a state-of-the-art EDA is the Bayesian optimization algorithm (BOA), which is a multivariate EDA employing Bayesian networks for modeling the relationships between good solutions. The use of a Bayesian network leads to relatively fast convergence as well as high diversity in the matched models. Given the relatively limited number of reservoir simulations used in history matching, EDA-BOA offers the promise of high-quality history matches with a fast convergence rate. In this paper, we introduce EDAs and describe BOA in detail. We show results of the EDA-BOA algorithm on two history-matching problems. First, we tune the algorithm, demonstrate convergence speed, and search diversity on the PUNQ-S3 synthetic case. Second, we apply the algorithm to a real North Sea turbidite field with multiple wells. In both examples, we show improvements in performance over traditional population-based algorithms.
- North America > United States > Texas (0.93)
- Europe > United Kingdom (0.88)
- Europe > Netherlands (0.66)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (21 more...)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Directed Networks > Bayesian Learning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Evolutionary Systems (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Uncertainty > Bayesian Inference (0.88)
Abstract Numerical reservoir models are used to predict, optimise and improve production performance of the oil and gas reservoirs. History matching is required to calibrate reservoir models to dynamic behaviour of the reservoir. On the one hand, historymatching does not have a unique solution and multiple models can fit observation data, on the other hand, history-matching is a tedious and time-consuming trial and error process as it involves numerous reservoir simulation runs. Modern history matching techniques use optimisation algorithms aim at providing a set of good fitting models in an efficient time. Many optimisation algorithms are applied in history-matching. Of them, Evolutionary Algorithms (EAs), inspired by natural evolution, do not use gradient information from the optimisation problem and only require the fitness function, usually defined as the sum of squares root deviation of model response from the observation data. Estimation of distribution algorithms (EDAs) are a novel class of EAs developed as a natural alternative to genetic algorithms in the last decade. To date, many EDAs are introduced which differ in the probabilistic model that guides the search process. Most of the EDAs are designed for discrete problems and require discretisation of search space when used for continuous problems, e.g. in history matching. In some cases, discretization error can be significant and deteriorate the search process. Gaussian-based EDAs use characteristics of Gaussian distribution for multivariate continuous problems. i.e. they make use of mean and covariance matrix of the variables in the promising solutions to generate new solutions which fit better the observation data. In this paper, we introduce and for the first time apply four Gaussian-based EDAs to assisted historymatching of a standard synthetic case. We show our proposed algorithms may produce results more accurately and more efficiently for the continuous problems.
- North America > United States (1.00)
- Europe (1.00)
- Asia (1.00)
- Information Technology > Modeling & Simulation (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Evolutionary Systems (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Clustering (0.47)
Summary Prudent decision making in subsurface assets requires reservoir uncertainty quantification. In a typical uncertainty-quantification study, reservoir models must be updated using the observed response from the reservoir by a process known as history matching. This involves solving an inverse problem, finding reservoir models that produce, under simulation, a similar response to that of the real reservoir. However, this requires multiple expensive multiphase-flow simulations. Thus, uncertainty-quantification studies employ optimization techniques to find acceptable models to be used in prediction. Different optimization algorithms and search strategies are presented in the literature, but they are generally unsatisfactory because of slow convergence to the optimal regions of the global search space, and, more importantly, failure in finding multiple acceptable reservoir models. In this context, a new approach is offered by estimation-of-distribution algorithms (EDAs). EDAs are population-based algorithms that use models to estimate the probability distribution of promising solutions and then generate new candidate solutions. This paper explores the application of EDAs, including univariate and multivariate models. We discuss two histogram-based univariate models and one multivariate model, the Bayesian optimization algorithm (BOA), which employs Bayesian networks for modeling. By considering possible interactions between variables and exploiting explicitly stored knowledge of such interactions, EDAs can accelerate the search process while preserving search diversity. Unlike most existing approaches applied to uncertainty quantification, the Bayesian network allows the BOA to build solutions using flexible rules learned from the models obtained, rather than fixed rules, leading to better solutions and improved convergence. The BOA is naturally suited to finding good solutions in complex high-dimensional spaces, such as those typical in reservoir-uncertainty quantification. We demonstrate the effectiveness of EDA by applying the well-known synthetic PUNQ-S3 case with multiple wells. This allows us to verify the methodology in a well-controlled case. Results show better estimation of uncertainty when compared with some other traditional population-based algorithms.
- Asia (0.93)
- North America > United States > Texas (0.68)
- Europe > United Kingdom (0.68)
- North America > United States > California (0.46)
- Overview > Innovation (0.48)
- Research Report > New Finding (0.48)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (23 more...)
- Reservoir Description and Dynamics > Reservoir Simulation > History matching (1.00)
- Reservoir Description and Dynamics > Reservoir Simulation > Evaluation of uncertainties (1.00)
- Management > Risk Management and Decision-Making > Risk, uncertainty, and risk assessment (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Search (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Optimization (1.00)
- Information Technology > Artificial Intelligence > Natural Language > Information Retrieval (1.00)
- (2 more...)
On Population Diversity Measures of the Evolutionary Algorithms used in History Matching
Abdollahzadeh, Asaad (Heriot-Watt University) | Reynolds, Alan (Heriot-Watt University) | Christie, Mike (Heriot-Watt University) | Corne, David (Heriot-Watt University) | Williams, Glyn (BP) | Davies, Brian (BP)
Abstract In history matching, the aim is to generate multiple good-enough history-matched models with a limited number of simulations which will be used to efficiently predict reservoir performance. History matching is the process of the conditioning reservoir model to the observation data; is mathematically ill-posed, inverse problem and has no unique solution and several good solutions may occur. Numerous evolutionary algorithms are applied to history matching which operate differently in terms of population diversity in the search space throughout the evolution. Even different flavours of an algorithm behave differently and different values of an algorithm's control parameters result in different levels of diversity. These behaviours vary from explorative to exploitative. The need to measure population diversity arises from two bases. On the one hand maintaining population diversity in evolutionary algorithms is essential to detect and sample good history-matched ensemble models in parameter search space. On the other hand, since the objective function evaluations in history matching are computationally expensive, algorithms with fewer total number of reservoir simulations in result of a better convergence are much more favourable. Maintaining population's diversity is crucial for sampling algorithm to avoid premature convergence toward local optima and achieve a better match quality. In this paper, we introduce and use two measures of the population diversity in both genotypic and phenotypic space to monitor and compare performance of the algorithms. These measures include an entropy-based diversity from the genotypic measures and a moment of inertia based diversity from the phenotypic measures. The approach has been illustrated on a synthetic reservoir simulation model, PUNQ-S3, as well as on a real North Sea model with multiple wells. We demonstrate that introduced population diversity measures provide efficient criteria for tuning the control parameters of the population-based evolutionary algorithms as well as performance comparison of the different algorithms used in history matching.
- North America > United States (1.00)
- Europe > United Kingdom > North Sea (0.25)
- Europe > Norway > North Sea (0.25)
- (2 more...)
Abstract To make prudent decisions regarding the exploitation and management of hydrocarbon reservoirs, we need to carry out history matching, a process for conditioning the reservoir simulation model to observation data collected over time. History matching is an inverse problem which requires an optimisation technique to match the simulation results to the measurements. Many techniques have been applied to address this optimisation problem effectively and in efficient time since reservoir simulation runs are computationally expensive. Genetic algorithms (GAs) and Estimation of Distribution Algorithms (EDAs) are two popular types of evolutionary algorithms. In GAs, new candidate solutions are obtained by applying crossover and mutation operators to a population of feasible solutions according to the principle of โsurvival of the fittestโ in natural evolution. The Estimation of Distribution Algorithm (EDA) is a modern class of EA in which new candidate solutions are generating by sampling from a probability distribution inferred from the better members of the population. A suitable hybrid of the GA and EDA algorithms can combine beneficial characteristics from each of GA and EDA, while addressing each otherโs sources of inefficiency. The main difference between these two EAs is the way they generate new individuals, which results in different exploration/exploitation properties. GAs may sample bad representatives of good search regions and good representatives of bad regions, while the EDA may suffer from fitting a single probability distribution to diverse and distinct regions of good solutions. The hybrid algorithm performs a cooperative search that improves the exploitation and the exploration power of both algorithms. In this paper, we applied GA, EDA, and a new hybrid GA-EDA algorithm to optimisation of three cases, a test function, the IC-Fault synthetic reservoir model, and one real reservoir, Teal South. The results show that each of these algorithms can be used for exploring the parameter search space in history matching problem. Depending on the problem type, GA, EDA, and Hybrid GA-EDA can achieve good quality matches while they perform a global seach in the space.
- Asia (0.93)
- Europe (0.68)
- North America > United States > Texas (0.28)
- North America > United States > Michigan (0.28)
- Research Report > New Finding (0.66)
- Research Report > Experimental Study (0.66)
- Europe > United Kingdom > North Sea > Central North Sea > Central Graben > West Central Graben > Block 21/25 > Anasuria Cluster > Teal South Field > Skagerrak Formation (0.98)
- Europe > United Kingdom > North Sea > Central North Sea > Central Graben > West Central Graben > Block 21/25 > Anasuria Cluster > Teal South Field > Heather Formation (0.98)
- Europe > United Kingdom > North Sea > Central North Sea > Central Graben > West Central Graben > Block 21/25 > Anasuria Cluster > Teal South Field > Fulmar Formation (0.98)
- Europe > United Kingdom > North Sea > Central North Sea > Central Graben > West Central Graben > Block 21/25 > Anasuria Cluster > Teal South Field > Forties Formation (0.98)
Abstract Prudent decision making in subsurface assets requires reservoir uncertainty quantification. In a typical uncertainty quantification study, reservoir models must be updated using the observed response from the reservoir via a process known as history matching. This involves solving an inverse problem, finding reservoir models that produce, under simulation, a similar response to that of the real reservoir, requiring multiple expensive multiphase flow simulations. Thus uncertainty quantification studies employ optimization techniques to find acceptable models to be used in prediction. Different optimization algorithms and search strategies are presented in the literature, but they are generally unsatisfactory due to slow convergence to the optimal regions of the global search space, and, more importantly, failure in finding multiple acceptable reservoir models. In this context, a new approach is offered by Estimation of Distribution Algorithms (EDAs). EDAs are population-based algorithms, which use probability models to estimate the probability distribution of promising solutions, and then to generate new candidate solutions. This paper explores the application of EDAs including univariate and multivariate models. We discuss two histogram-based univariate models, and one multivariate model, Bayesian Optimization Algorithm (BOA), which employs Bayesian Networks for modelling. By considering possible interactions between variables and exploiting explicitly stored knowledge of such interactions, EDA can accelerate the search process, while preserving search diversity. Unlike most existing approaches applied to uncertainty quantification, the Bayesian Network allows BOA to build solutions using flexible rules learned from the models obtained, rather than fixed rules, leading to better solutions and improved convergence. BOA is naturally suited to finding good solutions in complex high-dimensional spaces, such as those typical in reservoir uncertainty quantification. We demonstrate the effectiveness of EDA by applying to the well-known synthetic PUNQ-S3 case with multiple wells. This allows us to verify the methodology in a well controlled case. Results show better estimation of uncertainty when compared to some other traditional population-based algorithms.
- Europe (1.00)
- North America > United States > Texas (0.47)
- Research Report > New Finding (0.48)
- Overview > Innovation (0.48)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (21 more...)
- Reservoir Description and Dynamics > Reservoir Simulation > History matching (1.00)
- Reservoir Description and Dynamics > Reservoir Simulation > Evaluation of uncertainties (1.00)
- Management > Risk Management and Decision-Making > Risk, uncertainty, and risk assessment (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Search (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Optimization (1.00)
- Information Technology > Artificial Intelligence > Natural Language > Information Retrieval (1.00)
- (2 more...)
Abstract The topic of automatically history-matched reservoir models has seen much research activity in recent years. History matching is an example of an inverse problem, and there is significant, active research on inverse problems in many other scientific and engineering areas. While many techniques from other fields such as Genetic Algorithms, Evolutionary Strategies, Differential Evolution, Particle Swarm Optimisation, and the Ensemble Kalman Filter have been tried in the oil industry, some more recent and effective ideas have yet to be tested. One of these relatively untested ideas is a class of algorithms known as Estimation of Distribution Algorithms (EDAs). EDAs are population-based algorithms, which use probability models to estimate the probability distribution of promising solutions, then to generate new candidate solutions. EDAs have been shown to be very efficient in very complex high-dimensional problems. An example of a state of the art EDA is the Bayesian Optimisation Algorithm (BOA), which is a multivariate EDA employing Bayesian Networks for modelling the relationships between good solutions. The use of a Bayesian Network leads to relatively fast convergence as well as high diversity in the matched models. Given relatively limited number of reservoir simulations used in history matching, EDA-BOA offers the promise of high quality history matches with a fast convergence rate. In this paper, we introduce EDAs and describe BOA in detail. We shows results of EDA-BOA algorithm on two history matching problems. First, we tune the algorithm and demonstrate convergence speed and search diversity on the PUNQ-S3 synthetic case. Secondly, we apply the algorithm to a real, North Sea, turbidite field with multiple wells. In both examples, we show improvements in performance over traditional population-based algorithms.
- North America > United States > Texas (1.00)
- Europe (1.00)
- Asia > Middle East > UAE > Abu Dhabi Emirate (0.28)
- North America > United States > Texas > Permian Basin > Yeso Formation (0.99)
- North America > United States > Texas > Permian Basin > Yates Formation (0.99)
- North America > United States > Texas > Permian Basin > Wolfcamp Formation (0.99)
- (21 more...)
- Information Technology > Artificial Intelligence > Machine Learning > Evolutionary Systems (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Uncertainty > Bayesian Inference (0.56)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Directed Networks > Bayesian Learning (0.56)