Research

AI engineering at the quantum scale.

A fully solvated COVID spike protein with half a million atoms simulated at quantum accuracy on a single GPU.

‍This scale is only possible with Orbital's research.

Research

We live in a material world. The chips powering the computer you're reading this on are advanced materials called semiconductors, crafted from the silicon that gave Silicon Valley its name. The battery in your electric car, the composites in spaceships, and the LEDs in your screen are also advanced materials. New advanced materials powered 20th-century prosperity – and will super charge the 21st

But discovering and scaling up new materials is hard. Not only do their remarkable properties derive from complex quantum interactions that are too difficult for traditional, bottom-up computer simulations to solve accurately, but translating a promising material from the lab to industrial-scale production presents significant hurdles. Designing efficient hardware, optimizing process parameters, and ensuring consistent quality at scale are all complex challenges. This means that materials science has not benefited from the exponential improvements that computers have brought to other fields.

AI has changed this. Instead of painstaking trial-and-error in the lab and on the factory floor, engineers design materials and manufacturing processes with the same fluidity with which they currently design a building or an airfoil in CAD software. AI-powered platforms, combined with robotics, can revolutionize materials development and engineering from start to finish. They enable virtual prototyping and testing, optimize hardware design, and streamline production. AI accelerates not just discovery, but the entire journey from lab to market.

This is the future Orbital is building with our research.

Theme 1

Pretraining & generative models for advanced materials

This research program aims to unlock the extraordinary emergent properties of large materials datasets, mirroring the transformative impact of scale seen in natural language processing, to revolutionize materials discovery. By developing pretraining strategies that harness the complexity of vast chemical and physical data, we seek to create models capable of predicting and designing novel materials with unprecedented accuracy and efficiency, fundamentally changing how we approach materials innovation.

Theme 2

Large-scale simulation

This research program tackles the critical challenge of simulating metallic systems and quantum properties at scales between 10,000 and 100,000 atoms—regimes where traditional quantum methods fail to scale. Many key experimental phenomena, from phase transformations to defect dynamics, emerge at these large scales, yet remain out of reach for conventional quantum simulations. By using accelerated AI simulations, these critical phenomena - often the things you care most about - become within reach.

Materials property predictions

A demonstration of the capabilities to predict a wide range of material properties well, with Orb outperforming other models for properties such as the structure of amorphous Silicon.

Wines et al

Complex Alloy Phases

This paper demonstrates the ability of Orb to predict phase diagrams of complex metal alloys with remarkable computational efficiency and accuracy outperforming other models.

Zhu et al

Potassium Ion Channels

We discover a new mechanism that enables potassium to rapidly leave biological cells through a protein complex demonstrating the ability to generalise well outside of the training data with Orb.

Tim Duignan

Theme 3

New materials synthesis

Materials innovation requires more than just computational insights—it demands hands-on experimental mastery to bridge theory and reality. This research program pioneers advanced synthesis techniques that transform theoretical predictions into tangible breakthroughs. Our team have pioneered breakthrough materials breakthroughs, from initial synthesis to scale up.

Co2 capture in porous materials

This review explores how cutting-edge materials called metal-organic frameworks (MOFs) could revolutionize carbon capture, offering a powerful new way to trap pollution from power plants and fight climate change more efficiently than ever before.

Tom McDonald

Harmful chemical removal

A newly developed material, COF-I, effectively removes harmful PFAS chemicals from water with high efficiency, stability, and reusability, reducing contamination to safer levels.

Anahita Khojastegi

Smart pores enable adaptive materials

This research introduces flexible, porous materials that can expand and contract like a "wine rack," enabling smart materials with tunable optical and electronic properties for future sensors, energy storage, and responsive technologies.

Anahita Khojastegi

Scaling up novel porous materials

Matt, our Head of Technology Evaluation, shares lessons on scaling up porous materials manufacturing in Nature Materials

Matt Kapelewski

Record high hydrogen storage

Record-breaking hydrogen storage capacity in a solid material

Theme 4

Engineering for the future

An advanced material isn't useful unless you know how to use it. In our engineering research we investigate ways to integrate our advanced materials into entire technology packages, doing the chemical, process and mechanical engineering to achieve extraordinary results.