Big Data Analytics Can Deliver U.S. Energy Independence

As shocking as it might seem, for the first time in decades, the U.S. is oh so close to energy independence. According to the International Energy Agency, by 2016 the U.S. will surpass Saudi Arabia and Russia to become the world’s largest oil producer.

Greater production and reduced consumption has helped America achieve this status. But the real hero is actually a villain in many circles — shale oil. Shale’s controversial horizontal drilling and hydraulic fracturing (fracking) processes are extracting rich deposits of oil from hard to reach spaces beneath the earth, but not without impacting the environment.

The U.S. is currently on track to match in the next five years its record oil output from 1970 of 9.6 million barrels per day (bpd). Just in Texas alone, Eagle Ford and Permian Basin are generating nearly 2 million bpd in 2013. Several other states are gearing up for oil boom as well. EIA projects U.S. shale oil production will reach 4.8 million bpd in 2021.

While controversial, horizontal drilling and fracking processes are used in about 60 percent of oil and 98 percent of natural gas wells. In response, environmental groups across the country are sounding the alarm of over potential groundwater contamination and earthquakes.

Rather than shutting down new energy sources for their potential to do harm, oil and gas companies have an opportunity to make them safer and more efficient by becoming smarter about the resources and the production process.

As the industry transitions from grabbing acreage to shale manufacturing and the capital expenditures go up, the winners will be the companies that can get more shale oil out cheaper and faster. For example, 80 percent of shale production in North America comes from just 20 percent of the fracking stages. According to PacWest, drillers will spend $31 billion in 2013 on suboptimal frack stages across 26,100 wells in the U.S. There’s obviously plenty of room for improvement.

How? Just listen. The rumbling you hear underground isn’t just oil. It’s gushers of data that if analyzed properly that can yield new insights to producing more shale oil while reducing negative effects on the environment. According to McKinsey, Energy and Big Data are two to top-five game-changers for the U.S. economy and can together add up to $1 trillion to the GDP of U.S. by 2020 — and the interesting thing is this analysis doesn’t even take into account the effect of Big Data Analytics in Energy.

Big Data Analytics is taking on a new role in the oil and gas industry, where companies are combining findings from geoscientists with those from data scientists. The data is complex, varied and massive. But by taking a look into different data sources and data types, Big Data can help oil and gas companies predict where to frack (sometimes called “sweet spotting”) and prescribe how to frack for maximum production with minimum environmental effect.

Big Data Analytics is broken up these days into three primary categories. First, there’s Descriptive Analytics, which tells you what happened. Second, there’s Predictive Analytics, which tells you what will happen. Finally, there’s Prescriptive Analytics, which tells you what will happen, when, why, and how to improve this predicted future.

Shale oil and gas production presents a number of analytical challenges and opportunities because of the growing volume, velocity and variety of data that needs to be analyzed and interpreted to make mission critical investment and drilling decisions. This information includes a hybrid mix of structured and unstructured data such as images, sounds, videos, texts and numbers.

For Big Data Analytics to succeed in oil and gas exploration and production—especially shale—it has to collect and analyze data from a number of sources, such as:

• Images from well logs, mud logs and seismic reports
• Videos from fluid flow from hydraulic fractures
• Sounds from drilling, fracking, completion, production, collected by fiberoptic sensors
• Texts from drillers’ and frack pumpers’ notes
• Numbers from production, artificial lifts

By combining information from all these sources, Prescriptive Analytics can unearth key insights, predict problems and opportunities and prescribe the best course of action. For example, operators engaged in shale exploration and production can better predict where to drill, where to frac, and prescribe how to complete their wells. Doing so maximizes production while minimizing cost and avoiding adverse environmental consequences.

This kind of success requires a combination of a number of disparate technical disciplines. To analyze and interpret sound data — generally speaking — we have to combine machine learning with signal processing, pattern recognition and speech recognition. For images, you have to combine machine learning with pattern recognition, computer vision and image processing.

By combining these disparate scientific disciplines, we have a more holistic view of where and how to drill and frack in a way that allows us to preempt future problems without creating new ones in the process of doing so.

This means predicting production issues by modeling numerous internal and external variables simultaneously. Or it can show the impact of each decision so managers can ensure future production output by proactively taking appropriate and timely measures.

Computers today can see, hear, and understand — a new world ushered by the fascinating mergers among computational and scientific disciplines — in ways that hasn’t been possible to date.

If we allow these new technological inventions — such as Prescriptive Analytics — to use their senses, they we can not only predict the future but also come up with the best way to take advantage of it. The secret though is in evaluating all the data together in a way that the industry has never done before.

Atanu Basus is President and CEO of Ayata.

End of an era at Doe Run with final smelter closure

In the end of an era in US lead operations, Doe Run Company finally shut down all primary lead operations at its Herculaneum, Missouri location as of December 23, 2013. This was the last primary lead smelter operating in the US. Doe Run’s Missouri lead mines and mills continue to operate, producing high quality lead concentrate. Lead is a key component of batteries used for transportation and backup power in a variety of industries, including technology, communications and renewable energy.

Approximately 98% of lead-acid batteries are recycled, turning the used metals and other components into new products. More than 13 million of these batteries are recycled annually at Doe Run’s lead recycling centre in southern Missouri, one of the world’s largest. The Doe Run smelter had been supplying 8 to 10% of US demand for lead through its Herculaneum smelter. Some 75 employees will be retained in 2014 to assist with continued refining and alloying, and the maintenance of our site.

Leading up to the closure, Gary Hughes, General Manager of Doe Run’s Metals Division said: “Our final production days will be our best. We intend to meet our customers’ needs in a safe and responsible manner. We will receive the final shipment of lead concentrates from our Missouri mines in the next several days, producing one of the highest grades of primary lead metal in the world in the final weeks of December. Although we will continue to mine and mill lead, zinc, and copper from our underground mines, the ability to produce primary lead metal and their alloys domestically will vanish.”

In 2010, Doe Run reached a comprehensive settlement with the US Environmental Protection Agency and the State of Missouri. As part of that settlement, Doe Run agreed to discontinue its smelting operations in Herculaneum by the end of 2013. “We saw no alternative to closing our plant,” stated Hughes. “We are aware of no primary lead smelting process that will meet the standard for ambient air at the Herculaneum site. We believe the only existing technology that can meet today’s standards in Herculaneum, as well as potential future standards, is the new electrowinning lead metal process we announced in 2010. We hoped to be building such a plant by now, however, constructing a full-scale plant given other regulatory compliance spending requirements puts our company at financial risk. We may pursue a smaller scale plant if conditions become more favorable.”

The US ambient air quality standard for lead emissions is the most restrictive in the world. In 2008, the National Ambient Air Quality Standard for lead was reduced from 1.5 µg/m³ (micrograms of lead per cubic metre of air) to 0.15 µg/m³. Doe Run had hoped to bring the revolutionary lead metal production technology online prior to the closure of the smelter. This proprietary, new technology uses a wet-chemical, electrowinning process instead of a heat-based smelting process, greatly reducing sulfur dioxide and lead emissions. In 2012, the company announced that costs to build an electrowinning plant similar in production size to the smelter were too great for the company given the present economic conditions and other demands on operations.