Research

Artificial Scientific
Ingelligence

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

Advanced materials, from the semiconductors in our devices to the composites in aerospace, are foundational to technological progress. However, discovering novel materials and scaling their production is uniquely challenging. Their properties often arise from complex quantum interactions difficult to model accurately, and translating lab breakthroughs to industrial manufacturing involves significant hurdles in hardware design, process optimization, and quality control. These factors have traditionally made materials development a slow, resource-intensive process.

Artificial Scientific Intelligence offers a transformative path forward. By applying AI specifically to these scientific and engineering problems, we can navigate complexity more effectively. ASI enables researchers and engineers to design, simulate, and test new materials and optimize manufacturing processes with much greater speed and precision than traditional methods allow. This accelerates the entire pipeline, from fundamental discovery to market-ready products. Orbital's research is dedicated to building and deploying these Artificial Scientific Intelligence capabilities to unlock the next generation of materials.

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.