Big Data Every Day: Predictive Analytics Used to Improve Production Surveillance

Abstract

Terabytes of data are being collected every day in the oilfield. Intuition suggests that the more data the better and that if a little bit of information is valuable, then a lot must be incredibly more so. And yet, is it? It is not the data itself, but the ability to put it toward some useful task which matters. One of the most concrete ways in which Big Data can be brought to bear on the everyday is through predictive analytics, the science of using facts from the past to analyze the present and predict the future. In the oil field, a simple and powerful way of making use of data and predictive analytics is for automatic surveillance by exception. By learning from the past it is possible to predict what should be happening today and compare the prediction to what is actually going on. If the two do not match then a problem has been identified and a solution found. Addressing problems early is one of the cheapest ways to boost production.

A Comprehensive Review on Big Data for Industries: Challenges and Opportunities

“…3) Reservoir Management Big data provides an opportunity for reservoir engineers to monitor and sorting of reservoir simulation results. The explanation, system design, and prediction of the reservoir simulation parameters heavily rely on the analysis of stratigraphic rock [30], [114]. However, it is very difficult to digitalize 3D seismic data and estimate relative permeability parameters, and bottom hole pressure, which restricts the monitoring task of reservoir engineers [130].…”

“…Seismic interpretation [30], analysis [19], Drilling knowledge discovery [68], [83], optimization [43], Drilling cost optimization [77], [34] Production engineering [90], production allocation [21], well productivity [55], surveillance [114],…”

Production Prediction Model of Tight Gas Well Based on Neural Network Driven by Decline Curve and Data

“…After using the physics and flexibility of the growth model to reduce the requirements for the data, the data-driven model is used for correlation correction, which has a high accuracy in medium-and long-term shale gas production prediction. Raphae [22] and others use the prediction algorithm based on big data to compare the actual production data with the forecast data in order to evaluate the production situation in this area. In 2016, Cao [23] proposed a production prediction model for unconventional oil and gas wells based on an artificial neural network.…”