Live Webinar: Don’t Lose The AI Race: Why You Need A Data Quality Strategy in Oil & Gas

Join us Thursday May 2 as key members of OspreyData’s Executive Team discuss one of the most crucial issues being faced in the Oil & Gas AI Revolution: developing a robust Data Quality strategy.

OspreyData CTO Ron Frohock (20+ years Technology Executive) and VP of Production Optimization & Services Ken Collins (20+ years Production Engineering & Management Executive) will be demonstrating how operators of any size can leverage data to deploy new methods for Artificial Lift monitoring and achieve a sizable ROI.

  • How Data Quality goes beyond Sensors & Telemetry
  • Ways to approach building your Data Strategy
  • How to leverage data for Optimization & Diagnostics
  • How better data impacts your entire organization

Live Webinar: The Top 3 Problems AI Solves in Artificial Lift Production

Join us for OspreyData’s first webinar in a series discussing the emerging AI revolution in Oil & Gas. Our Data Scientist Venkat Putcha (PhD, Penn State) and VP of Client Services Tim Burke will be demonstrating OspreyData’s latest innovations in Production Optimization and the potential ROI of implementing these AI-based solutions across fields and plays.

OspreyData’s Data Science team presents at Society of Petroleum Engineers Western Regional Meeting

Mike Pennell, Venkat Putcha and Jeff Hsiung of OspreyData’s Data Science team

OspreyData’s Data Science team presents at Society of Petroleum Engineers Western Regional Meeting

Mike Pennell, Jeff Hsiung and Venkat Putcha of OspreyData’s Data Science team presented at the SPE Western Regional Meeting, one of the Oil & Gas industry’s leading events, on April 25, 2018. The team presented a poster on OspreyData’s novel Human Augmented machine learning methodology and fielded questions by interested engineers & experts in the Oil & Gas industry. The audience showed a high interest in OspreyData’s applied neural networks, random forests and other machine learning models for detection of failures and suboptimal states in rod pumps. Jeff Hsiung’s presentation about using Convolutional Neural Networks for Dynacard description, an implementation very similar to image recognition used by smartphones and ID scanners, sparked more interest in conversations.

Their accompanying paper “Detecting Failures and Optimizing Performance in Artificial Lift Using Machine Learning Models” dives into the work they’ve done in diagnosing and predicting Artificial Lift problems using machine learning. This scope covers common tubing and pump failures along with sub-optimal performance of sucker rod pumps and and gas injection units.

These achievements are just the beginning of the valuable work in machine learning based failure prediction they are contributing to the field.

Read the full paper here:

Mike Pennell chats with audience members about OspreyData's Human Augmented machine learning methodology

Venkat Putcha and Jeff Hsuing answer questions with attendees

Mike Pennell chats with audience members about OspreyData's Human Augmented machine learning methodology

Mike Pennell chats with audience members about OspreyData’s Human Augmented machine learning methodology

Venkat Putcha presents OspreyData's work at the 2018 SPE Western Regional Meeting

Venkat Putcha chats with conference attendees

OspreyData Raises $5 Million in Series A Financing led by Houston Ventures

OspreyData Raises $5 Million in Series A Financing led by Houston Ventures

Leading Energy VC firm Houston Ventures and others invest in OspreyData’s
Expert-Augmented Data Analytics platform for Oil and Gas

OspreyData announced a $5 million Series A growth financing led by Houston Ventures with participation from existing shareholders. “This investment will help support our technology leadership position and the further adoption of our unique Expert-Augmented Machine Learning methodology and platform. We will continue to grow the sales and services teams to meet the needs of our global Oil & Gas customers,” commented OspreyData CEO John Burke.

Fred Lummis, Junior Partner at Houston Ventures, said OspreyData was a perfect fit for their fourth fund that targets inefficiencies in Oil & Gas operations. He states, “OspreyData’s hardware-agnostic analytics platform has the ability to deliver massive ROI by leveraging existing production asset data streams to transition operators to an active monitoring program that reduces asset downtime and optimizes well performance. The enthusiastic response from early customers signals a positive shift in the industry’s willingness to adopt Machine Learning-powered analytics solutions that augment the performance of their human and machine assets.”

OspreyData’s core value proposition is maximizing uptime of critical Artificial Lift assets by bringing engineers and operators early detection of key problem states. OspreyData has leveraged the knowledge of leading Oil & Gas industry experts, positioning them alongside Data Scientists to create powerful models capable of predicting problem states with real-time data. OspreyData works with clients in stages, helping them evolve into data-driven producers without requiring proprietary hardware or exorbitant capex investments.

OspreyData and Hortonworks: Performance Optimization for Upstream Oil & Gas

OspreyData is a Hortonworks® technology partner whose solution is certified both for Hortonworks Data Platform and YARN. The company delivers agile big data analytics solutions for the oil and gas industry. In this blog, we share our thoughts on how the industry is addressing a big problem: unplanned interruptions to production.

A Mandate for Operational Efficiency and Margin Growth

The oil and gas industry is constantly challenged with a mandate to operate more efficiently—both in the oilfield and within the data center. The directive to increase overall margins and generate cash flow impacts all segments of the industry, and any downward swings in commodity prices increase the urgency. Now that oil prices are near historic lows, unplanned production interruptions cannot be allowed to erode margins further.

Oil and gas companies are adopting big data technologies, such as the combined Hortonworks Data Platform(HDP)™ and OspreyData solution, to reduce the risk of unplanned interruptions. Our solution captures data from oilfield sensors in near real time and makes that information available for both real-time decisions and historical, long-term analysis.

Unplanned Interruptions: a $100 Billion Dollar Per Year Problem

OspreyData estimates that unplanned interruptions are a problem costing $100 billion dollar per year. This estimate only addresses the loss of revenue from the interruption to production, and says nothing of the cost to replace damaged equipment. For example, replacing a burned motor in an onshore average-sized ESP can cost $25,000 to $200,000 with an additional $20,000 to $35,000 in associated rig and service charges. An operator with 1000 wells using ESPs would face an investment of nearly $100 million in new down-hole and surface equipment. Large rod pump systems can exceed $300,000 in cost per unit and will number in the thousands in the areas where they are used.

Offshore, the problem is much worse. A failed ESP can cause millions of dollars in costs and create additional health, safety and environmental (HSE) risks.

Current Data Storage Technologies Do Not Address the Problem

Much of the oilfield equipment systems today are equipped with high-resolution embedded sensors. These sensors provide a wide range of information regarding the state of the equipment. But the PLC and SCADA systems generally used in the industry can only analyze a small slice of the data generated by the sensors: often only examining the latest values from each sensor with no attention paid to trends, interactions, the history or the character of the well.

If any prognostic analysis exists, it’s performed by manual operator oversight. Operators can be in charge of hundreds of wells, often in remote locations, and that workload greatly limits their ability to intervene proactively. As a result, an analysis report can take months to create and it may contain just a fraction of the collected data. This method provides few (if any) mechanisms for just-in-time notification and what does exist is often delivered too late to detect issues prior to the need for costly equipment repairs or replacement.

However, buried within the discarded sensor data is information that can be used for powerful predictive analytics to identify impending failures and then determine optimal servicing routines and settings. This helps protect people and the environment.

OspreyData – A Packaged Hadoop-based Oil and Gas Application for Production

Optimization and Preventative Maintenance

As all industries adopt Hadoop and realize its business value, innovative enterprise software companies are building vertical solutions that can be leveraged by multiple companies within an industry.

OspreyData is doing this for the oil and gas industry. Together with Hortonworks, OspreyData provides upstream companies the ability to harness the massive stream of sensor data generated by their surface and downhole equipment, providing visibility into operations and points of failure that affect their assets. This improves productivity and lowers maintenance costs significantly.

The OspreyData system embeds “best in class” field practices to predict and proactively prevent failures, reduce downtime and enhance efficiency across your enterprise—all built natively on Hadoop and the Hortonworks Data Platform. This enables a modern data architecture with enterprise services for security, operations, and governance.

OspreyData based on Apache Hadoop and Hortonworks Data Platform is the ideal solution for listening to sensor signals from assets and analyzing assets in real-time. OspreyData is making it easy for oil and gas business units to consume HDP by providing a packaged, vertical solution that addresses the $100 billion dollars lost each year due to operational inefficiency.