Applied Computing Raises $20m to Build a Foundation Model for the Refinery
Plants collect thousands of sensor readings but act on less than 8% of them. The pitch is not more data; it’s about getting three kinds of data to talk.
July 16, 2026 – 8:46 am
A single refinery can carry thousands of sensors measuring temperature, pressure, velocity, and viscosity. According to Applied Computing, operators make decisions using less than 8% of what those sensors tell them.
The London startup has raised a $20m Series A led by engineering giant KBR with Databricks Ventures participating. Founded in 2023, it is building a foundation model for oil, gas, refining, and petrochemicals.
Co-founder and CEO Callum Adamson argues that the problem isn’t collection; operators already gather the information. The challenge lies in combining sensor readings, engineering documentation, and underlying physics and chemistry to predict useful outcomes.
"It’s getting those three data sources to talk to each other in real time," Adamson told TechCrunch. "That’s the real key."
Its model, Orbital, is not a language model with an industrial skin on it. Instead, Applied Computing fuses a time series model, a physics-based model, and a language model to predict facility states by reading sensor data while accounting for chemistry, equipment constraints, and operator actions.
Orbital also allows technicians to simulate how changes in one part of a plant would affect the rest, automating tasks traditionally requiring consultants and weeks of downtime.
The startup claims Orbital can flag anomalies, diagnose their causes, and model potential issues from proposed fixes within minutes—compressing investigations that once took days or weeks into seconds.
Applied Computing boasts transitioning from stealth to double-digit millions in annual recurring revenue (ARR) in under 18 months, with Orbital deployed at unnamed "large, publicly listed" upstream, refining, and petrochemical companies.
KBR has integrated Orbital into its INSITE 3.0 platform for ammonia production, and Adamson predicts announcements from a major US upstream operator and a European oil major in the coming weeks.
The competitive landscape is crowded and established, with players like AspenTech and AVEVA offering simulation and AI-powered modelling across various industries.