Abstract: A computer-based method for rapidly updating a history-matched reservoir simulation model selected from among a plurality of history-matched reservoir simulation models hosted on an information technology system. A software module configured to perform an update by parametrically varying the time over the selected update period and the position for each selected well model file and a corresponding well update file, replacing outdated well model file data with well update file data at each respective time and each respective position. The method is configured by selecting a reservoir simulation model for update, a petroleum field model to use, a reservoir model within the field, and one or more wells within the reservoir for the update. The well model files to be updated and the time interval over which the updates are to be made can be set by a user.

Abstract: A computer-based method for rapidly updating a history-matched reservoir simulation model selected from among a plurality of history-matched reservoir simulation models hosted on an information technology system. A software module configured to perform an update by parametrically varying the time over the selected update period and the position for each selected well model file and a corresponding well update file, replacing outdated well model file data with well update file data at each respective time and each respective position. The method is configured by selecting a reservoir simulation model for update, a petroleum field model to use, a reservoir model within the field, and one or more wells within the reservoir for the update. The well model files to be updated and the time interval over which the updates are to be made can be set by a user.

Abstract: A heterogeneous classifier based on actual reservoir and well data is developed to qualitatively classify oil well producer performance. Based on the classification a new well is drilled into a producing reservoir, or fluid flows in an existing well are adjusted. The data include perforation interval(s), completion type, and how far or close the perforated zones are located relative to the free water level or gas cap. The data also include geological data, such as major geological bodies like regional faults and fractures. The features may be prioritized before classification. The classifier utilizes four different techniques to apply pattern recognition on reservoir simulation vector data to classify the wells, Three of the classification techniques are supervised learning methods: Bayesian classification, dynamic time warping and neural network. The fourth classification is an unsupervised method, clustering, to automate well grouping into similar categories.

Abstract: A heterogeneous classifier based on actual reservoir and well data is developed to qualitatively classify oil well producer performance, and based on the classification drill a new well into a producing reservoir or adjust fluid flows in an existing well. The data includes perforation interval(s), completion type, and how far or close the perforated zones are located relative to the free water level or gas cap. The data also include geological data, such as major geological bodies like regional faults and fractures. The features may be prioritized before classification. The classifier utilizes four different techniques to apply pattern recognition on reservoir simulation vector data to classify the wells. Three of the classification techniques are supervised learning methods: Bayesian classification, dynamic time warping and Neural Network. The fourth classification is an unsupervised method, clustering, to automate well grouping into similar categories.