AI Model for the Entire Plant

Applied Computing, a London-based startup, has raised $20 million in a Series A funding round led by engineering giant KBR, with Databricks Ventures participating. This significant investment aims to support the development of the company’s foundation AI model for the oil, gas, and petrochemical industry.

Source: techcrunch.com

Founded in 2023, Applied Computing targets oil, gas, refining, and petrochemical systems, where thousands of sensors measure various parameters such as temperature, pressure, velocity, and viscosity. The challenge lies in the massive amount of data generated, which is often fragmented and difficult to analyze. As a result, facilities typically utilize less than 8% of the available data when making operating decisions.

According to Callum Adamson, co-founder and CEO of Applied Computing, the key issue is not the lack of data, but rather the inability to combine sensor readings, engineering documentation, and physics and chemistry quickly enough to analyze and make predictions. ‘It’s getting those three data sources to talk to each other in real time. That’s the real key,’ he explained.

Unlike large language models, which predict the next word, Applied Computing’s foundation model, Orbital, combines a time series model, a physics-based model, and a language model to predict the state of a facility. This is achieved by analyzing sensor readings, taking into account physics and chemistry, and recognizing equipment constraints and operator activity. Orbital also allows technicians to run simulations of how a change in one part of a facility could affect the rest of its operations.

Applied Computing’s product promises speed, claiming that Orbital can flag anomalies, investigate their causes, and model whether a proposed fix could create problems elsewhere in the facility, all within minutes. This is a significant improvement over the previous process, which could take days or weeks. By reducing energy use and maintaining output, operators can benefit from the use of Orbital.

The startup’s success is evident in its rapid growth, having gone from stealth to double-digit millions in annual recurring revenue in under 18 months. Orbital is currently in use at some ‘large, publicly listed’ upstream oil and gas, downstream refining, and petrochemical companies, although the exact number of customers remains undisclosed.

Applied Computing’s partners include Indian energy company Wipro, and KBR, which has integrated Orbital into its INSITE 3.0 digital platform for energy projects. The product is being used for ammonia production, and the startup is working with a ‘major U.S. upstream operator’ and plans to announce a partnership with a European oil major in the coming weeks.

The market for Applied Computing’s product is not without competition, with entrenched industrial software suppliers and more focused AI startups vying for attention. AspenTech sells simulation and AI-powered modeling software for upstream, refining, and chemical operations, while AVEVA offers physics-based process simulation, optimization, and ‘what-if’ modeling for industrial plants. Cognite and Seeq target the data layer, helping facilities analyze industrial data and apply AI to design workflows.

According to Adamson, the company’s moat is not access to industrial data or process knowledge, but rather assembling AI researchers to build a model that can compete with Orbital. ‘It’s an AI problem. It’s not a data problem, and it’s not an energy problem,’ he said. ‘If you’re a tier-one AI researcher, where are you going to work?… I don’t think Shell’s on that list.’

The KBR partnership provides Applied Computing with access to operational data and industry expertise, as well as introductions to more potential customers. The company plans to use the $20 million investment to expand internationally, hire for research and engineering roles, and explore deployments with energy clients.

Applied Computing has also opened an office in Houston, adding to its headquarters in London and operational hub in Bengaluru. This strategic move brings the startup closer to two existing customers in North America and sets the stage for an expansion into the Middle East.

By combining a time series model, a physics-based model, and a language model, Orbital offers a unique solution to the complex challenges faced by oil and gas operators. As Applied Computing continues to grow and develop its product, the potential for revolutionizing the industry becomes increasingly clear.