What do retail and mature oil/gas fields have in common? They both have complex and varied datasets in large quantities. Data Analytics utilizes powerful methods and techniques to handle such data. The goal is to design and implement a scalable and customizable analytics solution for preparing and refining underutilized datasets from mature Oil and Gas Fields. This involves performing Visual Exploration, Descriptive Analytics, Predictive Analytics, and Forecasting of oil and water productions.
These slides show a few examples of possible designs: from the basic, using only free-of-cost Google Colab and Workspace collaborative tools, to a very sophisticated design pattern using several Google Cloud Platform services and tools.
The slides show various design examples, from basic to sophisticated, using Google tools. "Scalable-elastic" refers to cloud-based solutions that adjust to workload and user demands, as illustrated in the image below:
This solution, designed and implemented in collaboration with OILSTONE and MineaOil Ltd, is relevant for the oil and gas industry because it provides actionable knowledge from underutilized datasets, allowing field operators to generate revenue with reduced investment costs. It can be used as a scouting tool for evaluating potential asset acquisitions or for other practical applications, and the results can be integrated into traditional oil and gas workflows.
Here's a summary: this example showcases the use of Google Cloud Platform to analyze publicly available but underutilized massive datasets from YPF. The data covers well information and oil, gas, and water production from over 6 thousand wells in Argentina. The data was refined and analyzed using Trifacta Cloud Dataprep, Google Looker Studio, and Tableau Public for advanced visual exploration and predictive analytics, including forecasting of oil and water production.
A fully automated, scalable, and elastic version of this End-to-End Analytics solution can be implemented using Trifacta Cloud Dataprep, BigQuery, Cloud Function, and Google Looker Studio, or Tableau Online. As illustrated in the figure above, this architecture operates at a high level. It's crucial to note that both the architecture mentioned in the previous paragraphs and this fully automated version are scalable and elastic, capable of processing massive datasets as well as small ones. As mentioned earlier, they can smoothly adapt to varying workloads and user demands. It's important to emphasize that Data Analytics is not restricted to so-called "Big Data" exclusively...
Results:
Implemented a Design Pattern for an End-to-End Analytics Solution.
Easy-to-digest, fully interactive visualizations, and dashboards are available in Tableau Public, allowing actionable insights to be quickly extracted with just a few clicks.
To enhance the User Experience, results are also accessible in Google Looker Studio as easy-to-digest, fully interactive dashboards and visualizations. Actionable knowledge can be quickly extracted with just a few clicks, and filtered data tables can be downloaded or published as Google Sheets for use in other applications or integration into various oil and gas workflows.
The four images below display a set of fully interactive visualizations that have been designed and successfully deployed in Tableau Public. This platform allows users to create visualizations and dashboards with more advanced features, including the ability to forecast oil and gas production by month. Additionally, important information such as surface facilities, 3D seismic surveys, seismic lines, water, oil, and gas pipelines, etc., can be displayed and considered in the analysis. Be sure to check the image to the right in the two figures immediately below for more details.
Now, let's consider the Ugarteche area/reservoir (field) located south of Mendoza city, as shown in the map below. In the last two figures above, filters were applied to zoom in and highlight the Ugarteche field. The oil production has increased (thicker curve), while water production has decreased (less blue curve). The dotted trend line and forecast consistently predict sustained fluid production over the next few years. This insight is crucial if the field is put up for bidding,
Once the engineer or analyst has utilized the available resources to identify an attractive area/field, such as Ugarteche, they may want to know which other reservoirs or fields could be of interest. To speed up the decision-making process, an easy-to-use Content-Based Recommendation Engine has been developed and included in the solution, utilizing all relevant data. The image below displays the engine's front panel implemented in Google Looker Studio. It uses a Pearson Similarity Index to generate recommendations and presents reservoirs/fields from both the Neuquina and Cuyana basins in a word cloud.
In the graphic below, by selecting "Ugarteche-Cuyana" from the Reference Reservoir(s) dropdown and adjusting the Similarity Index slider to 91%, you can identify the top five reservoirs/fields that are most similar to the Ugarteche reservoir. These results are visualized in a word cloud and ranked in a table to the left of the figure. If Ugarteche (in Cuyana Basin) is an attractive prospect for investment, then La Ventana and Rio Viejas, which are in the same basin, would also be worth considering. With just a few clicks, the analyst can quickly generate a shortlist of additional reservoirs to focus on, saving time and effort, even if more data and analysis are needed. This speeds up the decision-making process.
Hoping the provided example of a Cloud-Based Analytics Solution, which incorporates various Google Cloud Platform Services and Tools, will help streamline processes in oil and gas Scouting Tools—interested in learning more or conducting a one-on-one user test?
For more information about our solutions and services, don't hesitate to get in touch with us through our partner MineaOil Ltd, visit our Website, or use the contact form on this page.
Yorumlar