A rather overblown marketing document from Hortonworks sets out the stall for the use of innovative ‘big data’ technology in oil and gas. The release includes grandiose claims for Hadoops’ contribution to US energy independence and mitigating declining world oil production to propose three use cases, seismic, lease bidding and compliance with health safety and environmental reporting.
Machine learning algorithms running against massive volumes of sensor data from multiple wells can be used to optimize production and extend a well’s life. Once an optimization strategy has been obtained, optimal set points can be maintained with Apache Storm’s fault-tolerant, real-time analytics and alerts. Storm running in Hadoop can monitor variables like pump pressures, RPMs, flow rates, and temperatures and take corrective action if any of these set points deviate from pre-determined ranges.
In
lease bidding, Hadoop is claimed to provide competitive advantage by
efficiently storing image files, sensor data and seismic measurements,
adding context to third-party surveys of a tract open for bidding.
Apache Hadoop also offers a ‘secure data lake’ of compliance-related
information. Improved data capture and retention make compliance
reporting easier. Because Hadoop does not require ‘schema on load,’
data can be captured in native format, as pdf documents, videos, sensor
data, or structured ERP data. More from Hortonworks.