... injection over 30 years. The compositional reservoir model is used to generate advanced mud data (light components C1 to C5) to predict fluid phase properties by machine learning. The predicted fluid properties are then compared to the actual model data. The data points represent different well locations...

... machine learning history matching artificial intelligence upstream oil & gas reservoir simulation structural uncertainty fault transmissibility multiplier workflow predictive grid producer ensemble realization iteration dynamic data reduction conditioning posterior ensemble grid...

... of a zone (e.g., 3 m), and the tool will merge and/or replace shorter zones based on the classifier's class probability distribution. The post-processing also assists the machine learning by removing impossible annular conditions from consideration, such as the presence of formation in dual-casing...

... automated well planning well completion planning completion design procedure software petroleum engineer well planning completion program machine learning upstream oil & gas digital experience module requirement completion equipment scenario automation Introduction Field trials...

... distribution machine learning bayesian inference inflow performance information monte carlo bayesian approach petroleum engineer experiment algorithm hamiltonian monte carlo improved estimation target distribution implementation hmc forward model assumption gelman inflow profile...

... at a particular geological feature, through to a multi-day agenda mirroring a conventional field trip. We illustrate our contribution using example VFTs designed for different audiences and geological topics. artificial intelligence machine learning immunology geoscience concept health & medicine...

..., and how we manage, visualise, and interpret data, ensure full data integrity, and make data available for end-users through different applications. We will provide examples on how machine learning can be used for automated trend analysis and identification of relationships across different data types...

... information base case approach ensemble machine learning neural network full ensemble network model rejection dynamic data multiple stochastic approach Introduction With recent advances in software and hardware for reservoir modeling and simulation, it is now possible to build and simulate...

...-in basic equipment models of pumps, turbines and compressors. eCalc enables a multidisciplinary team to quickly assess future scenarios involving drainage strategy, tie-ins and topside modification plans. Introduction enhanced recovery machine learning reservoir surveillance reservoir simulation...

... performance improvements, which, however, is achieved at the cost of increased complexity of the history-matching workflow. machine learning reservoir simulation & nævdal modeling & simulation seismic data experiment information artificial intelligence upstream oil & gas data...

... and contextualized to related assets (wellbores, seismic, etc.) based on keywords and geospatial location. Machine learning categorization supports file grouping into document types, such as a work order or rig action plan. To illustrate this methodology we present two examples. The first example shows how a user...

... Abstract Objectives/Scope The objective of this work is to present a first step towards a hybrid approach between machine learning (ML) and physics-based modelling to provide decision support for drilling problems. The motivation for developing a hybrid approach is to obtain methods...

..., as this was not within the original scope of the Olympus optimization challenge. This work also shows that the NPV is further improved compared to the values obtained by the authors during the Olympus optimization challenge by utilizing optimized well economic limits. machine learning enhanced recovery reservoir...

... the residual model is built from a perspective of machine learning as in Luo (2019 ). More information regarding the RPM and the residual model will be provided in the experiment part later. In Figure 1 , AI is taken as the attribute in SHM. The same framework can also be extended to other types...

... because of irregular channel patterns. With the accessibility of 3D or 4D seismic data, there has been great interest in using machine learning models for seismic reservoir characterization such as facies classification and determining the nonlinear relationship between reservoir properties and seismic...

... Abstract Digital transformation of existing processes using technologies such as big data, advanced data analytics, machine learning, automation and cloud computing will enable continuous performance improvements within the operational sphere. The application of the technology will link...

... detailed depth-based and time-based statistics 2) computation of wear on bit and efficient weight-on-bit (WOB) versus depth for all the runs 3) automated machine learning to generate an accurate predictive model for bit dull grade to deploy for real-time operations. We define and calculate the efficient...

... drilling equipment machine learning artificial intelligence neural network annular pressure drilling flowrate prediction ann model open channel accuracy experiment sensor level sensor drilling fluid management & disposal upstream oil & gas prediction flowmeter flowrate measurement...

... makes it more difficult to analyze in the stipulated period of time and in turn the quality of a planned well is always sub-optimum. The main objective of this study is to make use of machine learning and deep learning algorithms to increase the scope of offset well planning by analyzing a large number...

... Abstract Determining the distribution of optimal injection and production wells along with their operating conditions is a complex problem. The objective of this study is to compare the effectiveness of an experimental based approach (central composite design, CCD) with a machine learning...