Abstract: Implementations described and claimed herein provide systems and methods for dynamic waterflood forecast modeling utilizing deep thinking computational techniques to reduce the processing time for generating the forecast model and improving the accuracy of resulting forecasts. In one particular implementation, a dataset of a field may be restructured into the spatio-temporal framework and data driven deep neural networks may be utilized to learn the nuances of data interactions to make more accurate forecasts for each well in the field. Further, the generated model may forecast a single time segment and build the complete forecast through recursive prediction instances. The temporal component of the restructured data may include all or a portion of the production history of the field divided into spaced time intervals. The spatial component of the restructure data may include, within each epoch, a computed or estimated spatial relationships of all existing wells.

Abstract: Systems and method for predicting production decline for a target well include generating a static model and a decline model to generate a well production profile. The static model is generated with supervised machine learning using an input data set including historical production data, and calculates an initial resource production rate for the target well. The decline model is generated with a neural network using the input data and dynamic data (e.g., an input time interval and pressure data of the target well), and calculates a plurality of resource production rates for a plurality of time intervals. The system can perform multiple recursive calculations to calculate the plurality of resource production rates, generating the well production profile. For instance, the predicted resource production rate of a first time interval is used as one of inputs for predicting the resource production rate for a second, subsequent time interval.

Abstract: Implementations described and claimed herein provide systems and methods for a framework to achieve completion optimization for waterflood field reservoirs. The proposed methodology leverages adequate data collection, preprocessing, subject matter expert knowledge-based feature engineering for geological, reservoir and completion inputs, and state-of-the-art machine-learning technologies, to indicate important production drivers, provide sensitivity analysis to quantify the impacts of the completion features, and ultimately achieve completion optimization. In this analytical framework, model-less feature ranking based on mutual information concept and model-dependent sensitivity analyses, in which a variety of machine-learning models are trained and validated, provides comprehensive multi-variant analyses that empower subject-matter experts to make a smarter decision in a timely manner.

Abstract: A system and method for reducing the complexity of the reservoir simulation process is described. In more detail, an add-in for spreadsheet software program has been developed allowing a user to input minimal amount of information for a simulation, wherein the add-in exports the data as a file readable by any simulation software. Upon completion of the simulation, the add-in will retrieve the results and display them in an easy-to-interpret manner. Thus, the add-in makes the simulation process easier, robust, and user friendly.

Abstract: A system and method for reducing the complexity of the reservoir simulation process is described. In more detail, an add-in for spreadsheet software program has been developed allowing a user to input minimal amount of information for a simulation, wherein the add-in exports the data as a file readable by any simulation software. Upon completion of the simulation, the add-in will retrieve the results and display them in an easy-to-interpret manner. Thus, the add-in makes the simulation process easier, robust, and user friendly.