What’s new in production

What is Big Data? Mohammadpoor and Torabi (2018) observe that the term Big Data defines the first characteristic of this method—the size of the available data set. They also list other characteristics related to the data that make it viable for Big Data tools. Those characteristics, well-named by IBM, are the three Vs: volume, variety and velocity. More recently, other observers have added two more Vs—veracity and value.

Beside these five Vs, the literature describes another important characteristic, which should be considered for applying Big Data: the complexity of the problem for which the data gathering is conducted.

There’s no need to belabor the “volume” point; most everyone knows how much data is coming in.

Application in production engineering. The authors catalog some examples of Big Data analytics in production engineering:

Seemann et al., from Saudi Aramco developed a smart forecast and flow method to conduct automated decline analysis. Their goal was to identify the underlying pattern in production data and to forecast the output performance.

Rollins et al., conducted a study for Devon Energy, to develop a production allocation technique by using Big Data. For the first task, they used the publicly available data from IHS to develop an allocation methodology. In the next step, Big Data was used as a platform to conduct the allocation procedure for the users. The processing tool for Big Data in their study was Hadoop (more about this later). They finally developed a user-friendly, map-based visual output for the allocated production data.

Sarapulov and Khabibullin used Big Data to evaluate the performance of ESPs by identifying emergency situations, such as overheating and unsuccessful start-ups. For their study, a total of about 200 million logs was gathered from 1,649 wells during one year.

In a study done by Palmer and Turland, Big Data was used to optimize the performance of rod-pumped wells, based on a three-step workflow: 1) the data acquisition composed of well test data, well equipment data, and supervisory control and data acquisition (SCADA); 2) automated workflows that conducted the required calculations to develop the model; and 3) interactive data visualization, which provided a user-friendly interface to extract the results.

Shale operators are also using Big Data to improve hydraulic fracturing projects. In a project done by a shale operator, Southwestern Energy, field and simulation data revealed that proppant loading and spacing between fracturing stages would significantly affect the productivity index.

In a study conducted by Ockree et al., Big Data was used to develop AI-based production-type curves to be incorporated with economic analysis, to conduct field development. In their work, the first step was followed, based on an extensive data processing pipeline, including raw data gathering, data filtering, joining the filtered data, and transferring the data to machine learning pipeline.

Tools of the trade. Big Data, as the name suggests, involves huge data sets and, in some cases, complicated problems. To deal with these challenges, a toolbox of technologies has emerged, with names like Apache Hadoop, MangoDB, Cassandra, R (a programming language), Datameer and BigSheets.

Hadoop appears popular. As IBM describes it, Apache Hadoop (“Hadoop” is allegedly named after a toy elephant) is an open-source platform providing scalable, distributed processing of large data sets, using simple programming models. Hadoop is built on clusters of commodity computers, providing a cost-effective solution for storing and processing massive amounts of structured, semi-structured and unstructured data, with no format requirements.

Recognizing the pattern. Pattern recognition technologies may be the Next Big Thing in Big Data analytics. Udegbe et. al. (2019), point out the proliferation of massive subsurface data sets from sources such as instrumented wells. The authors note the significant challenges that this places on traditional production data analysis methods for extracting useful information, in support of reservoir management and decision-making. In addition, with increased exploration interest in unconventional shale-gas reservoirs, there is a heightened need for improved techniques and technologies to enhance the understanding of induced- and natural-fracture characteristics in the subsurface, as well as their associated effects on fluid flow and well performance.

The authors believe these challenges have the potential to be addressed by developing big-data analytics tools that focus on uncovering masked trends related to fracture properties from large volumes of subsurface data through the application of pattern-recognition techniques. They describe a new framework for fast and robust production-data classification adapted from a real-time, face-detection algorithm: “This is achieved by generalizing production data as vectorized 1D images, with pixel values proportional to rate magnitudes. Using simulated shale-gas production data, we train a cascade of boosted binary classification models that are capable of providing probabilistic predictions. We demonstrate the viability of this approach for identifying hydraulically fractured wells that have the potential to benefit from re-stimulation treatment. The results show significant improvements over existing type-curve-based approaches for recognizing favorable-candidate wells, using only gas-rate profiles.”

Big Data will only get bigger. But in its shadow are remarkably clever and powerful tools keeping in step. The old saw, “There’s data and there’s information,” is true. Thanks to these tools, we’ll have both, in equal measure.