AI startup leads UK steel towards ‘net zero’

Deep.Meta, a London-based manufacturing start-up, has demonstrated that its technology can cut steel production emissions by almost 10% at Spartan UK’s steel plant in Newcastle-upon-Tyne. The achievement marks a significant milestone for the country’s steel processing capability, as Spartan UK is the country’s only producer of steel plates. In 2024, the UK steel industry contributed £1.7 billion in gross value added, yet steelmaking remains carbon-intensive, accounting for 9% of global CO₂ emissions.

Deep.Meta’s solution — Deep.Optimiser-PhyX — is an AI-powered ‘digital twin’ that combines physics and machine learning to optimise furnace operations. By using real-time sensor data and material science, it predicts steel slab temperatures more accurately and improves scheduling, boosting energy efficiency and reducing emissions. The technology will now enter a live pilot phase at Spartan UK.

Dr Osas Omoigiade, founder and CEO of Deep.Meta, said: “Steel is one of the most important materials on which our society is built. However, its production generates 9% of all global CO₂ emissions. We cannot reach ‘net zero’ without solving steel’s climate impact. We are developing Deep.Optimiser-PhyX to tackle inefficiencies that result in avoidable emissions — a crucial step in helping to decarbonise the industry. Our ultimate ambition is to save 10 megatonnes of CO₂ from entering the environment by 2030, creating a lasting impact here in the UK and across the global steel industry.”

Reliable and robust decision-making
Dr Kwangkyu Alex Yoo, senior machine learning scientist at Deep.Meta, added: “Today’s machine-learning models often operate as black boxes, lacking fundamental principles that clearly link inputs to outputs. Our physics-based machine-learning approach addresses these challenges by incorporating physical laws into both the training process and data generation. This leads to models that are more explainable and trustworthy, while enabling more reliable and robust decision-making.”

Spartan UK CEO Michael Brierley said: “Deep.Meta is a trusted partner, and we are piloting the Deep.Optimiser solution because of the rising costs of energy and carbon. Increasing the efficiency of production is of high importance as energy costs form a significant part of our cost structure. Around 40% of steel production costs are from energy and much of this is fossil-fuel based, so driving a reduction in energy directly cuts CO₂ emissions.”

Since its inception in 2020, Deep.Meta has secured £2.1 million in investment and was named a finalist in the Department for Science, Innovation and Technology’s Manchester Prize, which supports bold AI solutions for a clean energy economy. The winner, to be announced in March 2026, will receive £1 million to accelerate development.

Industry leaders have welcomed the innovation. Chris Oswin, CEO of the Materials Processing Institute, said: “Innovation will be absolutely central to the future of the UK steel industry and we believe AI will play an important role in improving processes and embracing digital and low-carbon solutions.”

Jon Bolton, co-chair of the UK Steel Council, concluded: “Collaboration between industry and the Government is vital if we are to secure a sustainable future for UK steel. Technologies like Deep.Optimiser-PhyX are the kind of solutions we need to drive that change.”