Maana integrates with Microsoft Azure, focusing on oil and gas

March 27 2019

During CERAWeek earlier in March, process analysis provider, Maana, announced a collaboration with Microsoft's Manufacturing and Resource Industry group to integrate its Knowledge Platform with Azure. MSDW spoke with co-founder, president and CTO, Donald Thompson, about the integration.

Thompson co-launched Maana with Babur Ozden six years ago, after a 15 year career with Microsoft in which he built one of the world's largest knowledge graphs from crawling the web—data which was used to inform Cortana— and built a semantic engine for SQL Server 2012.

Maana works to create models and simulations that often involve physical assets in a bid to help decision makers understand and optimize complex processes. Thompson said that the company's approach is similar to the concept of an IoT digital twin (known as an artifact in Maana parlance) in which a digital model is created for a physical asset such as a generator, pump or diesel engine to model how it would operate in the real world. He said that modeling a business' entire operation is a key goal:

We don't want to model just local optimums. [For example], a trading group for oil and gas is optimized around crude prices. Other things like contract or in-house vessels for shipping are also very local [optimums]. Yet, they have huge impacts on one another. The people working in those individual departments don't see the broader impact. We aim to come up with models that help decision makers and connect across the company. [These models] get richer over time to understand impacts.

The simulated artifacts in Maana's Knowledge Platform, built on Azure, can be reused from one situation to another by end customers.

From Maana's perspective, the partnership with the Azure team is both technological and business-based. The company is taking advantage of Microsoft distributed GPUs and machine learning infrastructure, while sharing many customers with Microsoft, including Airbus and big players in the oil and gas market.

We're in the world of computational knowledge graphs. For us we're able to have these individual services represent algorithms, encoding of subject matter expertise. With a knowledge-first approach [we can decompose] what it's going to take to solve the problem, putting things in terms of a question.

Thompson gave the example of reservoir management using a well plan. The two or three people could architect and design the end solution to determine different outcomes for the reservoir, such as time to pumping completion. Recently, Maana has trained models to analyze handwritten comments from drilling engineers, including acronyms, to assess the lifecycle of assets such as wells.

According to Thompson, the oil and gas industry has a huge appetite for digital transformation and smart applications that are capable of learning and becoming more intelligent over time. He says Azure uptake is significant among the companies in this space that Maana works with on a regular basis:

Many of our customers have private Azure cloud environments firewalled away from the public environment—we typically see this the most, or deployed into private cloud. Starting in the second half of this year, Maana will be available in the Azure Marketplace. Customers will be able to set up a cluster and provision Maana. This is our newest deployment model. Many of our previous models were on-premises. Now with container technology, Docker [and] Kubernetes, the shift toward cloud makes it much easier, including getting access to data within a company. More and more companies are migrating, which relieves logistics issues. Typically, customers have multiple instances and ways to connect, from access controls and role-based models to various governance and compliance models to prevent co-location of data.

FREE Membership Required to View Full Content:

Become a MemberLogin
Joining MSDynamicsWorld.com gives you free, unlimited access to news, analysis, white papers, case studies, product brochures, and more, and it’s all FREE. You’ll also have the option to receive periodic email newsletters with the latest relevant articles and content updates. Learn more about us here
About Eamon McCarthy Earls

As the assistant editor of MSDynamicsWorld.com, Eamon helps to oversee editorial content on the site and supports site management and strategy. He can be reached at eearls@msdynamicsworld.com.

Before joining MSDynamicsWorld.com, Eamon was editor for SearchNetworking.com at TechTarget, where he covered networking technology, IoT, and cybersecurity. He is also the author of multiple books and previously contributed to publications such as the Boston Globe, Milford Daily News, and DefenceWeb.

More about Eamon McCarthy Earls