Register      Login
Australian Energy Producers Journal Australian Energy Producers Journal Society
Journal of Australian Energy Producers
RESEARCH ARTICLE (Non peer reviewed)

Big data analytics—lessons learnt from global E&P operators

Kevin Kalish
+ Author Affiliations
- Author Affiliations

SAS Institute Australia.

The APPEA Journal 55(2) 409-409 https://doi.org/10.1071/AJ14044
Published: 2015

Abstract

Exploration and production operators are striving to attain the hidden knowledge in their key asset: data.

Data and real-time data from intelligent wells supplement historical interpretations and generated datasets. It is paramount to gain insight from these multiple datasets, which enable engineers and stakeholders to make faster and more accurate decisions under uncertainty. By combining the traditional deterministic and interpretive workflows with a data-driven probabilistic set of analyses, it is possible to predict events that result in poor reservoir or well performance or facility failures.

By building predictive models based on cleansed historical data and by analysing them in real-time data streams, it is now feasible to optimise production.

Controlling costs and ensuring efficient processes that impact positively on health, safety and environment and resource usage are key benefits that fall out of analytical methodologies.

This extended abstract provides recent examples of global exploration and production operators using an analytics oilfield framework to:

  1. improve the quality of data by integrating relevant sources from multiple monitoring and surveillance systems across all geology, geophysics and reservoir engineering (GGRE) disciplines into a unified view;

  2. predict unplanned events so that mitigation can be planned in advance;

  3. use predictive models to avoid frequent and unnecessary preventive maintenance that interferes with production schedules, strains maintenance staff and increases costs; and,

  4. increase decision support across disparate upstream disciplines by using data mining to create accurate predictive and descriptive models.

Kevin Kalish is a senior manager in the SAS Australia Energy practice. He brings over 15 years of international management and IT consulting experience with particular focus on the role, application and operational usage of analytics and information management solutions in the mining, oil and gas industries, resulting in improved maintenance and operational practices. Kevin has a proven track record of providing analytics-driven advice to oil and gas companies to better understand how analytics can deliver significant value across the hydrocarbon value chain through exploiting existing data assets. Kevin holds a bachelor’s degree in economics and has an MBA in strategic management.


References

Orenstein, H., and Kurdi, M., 2001—Improved asset availability and reduced costs with proactive detection of performance change. Middle East Process Engineering Conference and Exhibition, Riyadh, Saudi Arabia, 24–26 October, MEPEC 138.