Terra Quantum and Empa have developed LP-FNO, an AI model that predicts three-dimensional melt-pool dynamics in laser welding up to 100,000 times faster than traditional simulation. The technology addresses a key bottleneck in industrial laser processing by enabling real-time process control and digital twin deployment. The model uses Fourier Neural Operator architecture to learn relationships between laser process parameters and resulting temperature fields. It produces full 3D predictions in approximately 8 milliseconds at standard resolution, compared to six minutes for conventional high-fidelity simulations. LP-FNO achieves 2.5% average relative error in temperature accuracy and an intersection-over-union score above 0.9 for melt-pool boundary segmentation. The model covers both conduction and stable keyhole welding regimes within a single framework. The research has been published in the Journal of Intelligent Manufacturing.

From hours to sub-seconds: AI model allows real-time control of laser welding. Thun, 29.09.2026 - Laser welding is an advanced technique used to manufacture high-quality components for a variety of applications, from space to medicine. Researchers from Empa and the quantum computing company Terra Quantum have developed an AI model to accurately simulate and optimize the complex welding process - in fractions of a second. Laser welding is a precision manufacturing process used across aerospace, medical device, and automotive production. The technique is fast, precise, and easy to automate - but the process is complex and difficult to predict, as it couples many different physical effects. The laser melts a pool of metal spanning a few hundred micrometers. Within this pool, temperature-dependent surface tension drives flow; recoil pressure caused by evaporation leads to the formation of deep and narrow cavities known as keyholes. The keyholes then trap reflecting beams of light, locally increasing the absorbed fraction of the laser power. Physics-based computer simulations are commonly used to optimize laser welding. However, a high-fidelity simulation may take hours to complete, as it entails solving fluid flow, heat transfer, phase change and a moving free surface at once. This makes optimization costly and puts real-time process control completely out of reach. Researchers from Empa and the quantum computing company Terra Quantum have now trained a Machine Learning (ML) model which massively speeds up this process without compromising on accuracy. They have published their results in the Journal of Intelligent Manufacturing. What used to take hours, can now be accomplished in fractions of a second. Solving the simulation bottleneck. The model, which the researchers call the Laser Processing Fourier Neural Operator (LP-FNO), is an AI surrogate model. It predicts full three-dimensional melt-pool dynamics in laser welding up to 100,000 times faster than traditional multiphysics simulation, thus removing the computational bottleneck that has long blocked real-time process control and digital twin deployment in industrial laser processing. Control of the melt pool, the zone of molten metal found beneath the laser beam, is central to weld quality and consistency. High-fidelity multiphysics simulations have been the primary tool for understanding and optimizing the process, but their computational cost has made real-time application impractical. A single simulation run using current gold-standard tools takes approximately six minutes at standard 10 μm resolution and over one hour at finer 5 μm resolution, placing process control, large-scale parameter optimization, and uncertainty quantification out of reach for industrial operators. LP-FNO learns the relationship between laser process parameters, power and scan speed, and the resulting three-dimensional temperature fields and melt-pool boundaries, using a Fourier Neural Operator architecture that mixes information globally across the physical domain in a single forward pass. Once trained, LP-FNO produces full 3D predictions in approximately eight milliseconds at standard resolution and 88 milliseconds at twice the resolution. A key element of the approach is a quasi-steady reformulation of the laser-scanning problem. By transforming the transient simulation into a reference frame that moves with the laser beam and applying temporal averaging, the research team converted an inherently time-dependent problem into a form suitable for operator learning. This enabled LP-FNO to accurately represent stable keyhole welding dynamics, the most physically complex regime, involving deep vapor depressions, recoil-pressure-driven surface deformation, and strong laser-absorption variation, within the same framework used for conduction-mode welding. A fruitful collaboration. "The ability to compress hours of physics simulation into milliseconds is not an incremental improvement, it is the kind of change that makes entirely new applications possible," says Markus Pflitsch, CEO and Founder of Terra Quantum. "With LP-FNO, industrial operators can run process optimization in real time, build digital twins that stay synchronized with the physical process, and explore parameter spaces that were previously too expensive to probe. This is what deploying AI on the toughest problems in manufacturing looks like." "This partnership brought together Empa's expertise in laser processing, materials science, and process-modelling with Terra Quantum's capability in advanced machine learning and neural operator methods" says Elia Iseli, head of the Light-Matter Dynamics Group at Empa. "The accuracy with which LP-FNO reproduces the manufacturing-relevant outputs of the high-fidelity models, including temperature fields, melt-pool geometry, and phase interfaces, highlights the predictive power of the surrogate approach. This level of agreement reflects the close integration of machine-learning development and expertise in laser process modelling throughout the project. It is a result that could not have been achieved without this partnership." "Fourier Neural Operators are architecturally well-suited to this class of problem because they learn in spectral space, mixing information across the full physical domain at each layer rather than propagating it locally through convolutional neighborhoods," adds Florian Neukart, Chief Technology Officer at Terra Quantum. "That global perspective is what gives the model its resolution-invariant property: The spectral weights learned on coarse training data generalizes naturally to finer evaluation grids. Combined with the quasi-steady reformulation, this gave us a single trained model that handles both conduction and keyhole regimes with consistent accuracy across the process window." The long-term vision is to enable much faster process optimization, digital twins, and real-time control for laser manufacturing - and potentially other computationally intensive manufacturing processes. There is still a lot to solve, particularly for highly transient phenomena such as pore formation and keyhole collapse. But the researchers have demonstrated how combining physics, AI, and quantum computing could fundamentally change how we simulate advanced manufacturing processes in the future. Literature. A Benoit, T Ivas, M Papierz, A Sagingalieva, A Melnikov, E Iseli: A fast and accurate fourier neural operator-based surrogate for melt-pool prediction in laser processing; Journal of Intelligent Manufacturing (2026); doi: 10.1007/s10845-026-02917-0 M Papierz, A Sagingalieva, A Benoit, T Ivas, E Iseli, A Melnikov: Hybrid Fourier Neural Operator for Surrogate Modeling of Laser Processing with a Quantum-Circuit Mixer (2026); doi:10.48550/arXiv.2604.04828 Further information. Dr. Elia Iseli Empa, Head of Light-Matter Dynamics Group Phone +41 58 765 63 28 [email protected] Dr. Alexey Melnikov Terra Quantum, Global Director of Artificial Intelligence Phone +41 71 228 12 05 [email protected] Address for enquiries. Publisher. Federal laboratory for materials testing and research. Topics. * Education, Research & Innovation * Education, Research & Innovation: Science

Terra Quantum and Apex.AI integrate NIST post-quantum cryptography into robotics software. Insider Brief * Terra Quantum and Apex.AI have demonstrated an implementation of NIST-standardized post-quantum cryptography for secure communication between an Apex.AI-based robotic software environment and a cloud control system. * The integration applies quantum-resistant cryptographic algorithms while maintaining existing software architectures and communication workflows used by connected intelligent systems. * The companies said the implementation provides a pathway for industries including robotics, automotive, defense, and critical infrastructure to begin adopting quantum-safe security measures. Press release - Terra Quantum, a global leader in quantum technologies, and Apex.AI, a leading provider of safe and secure software for software-defined vehicles and intelligent machines, today announced the successful implementation of NIST-standardized post-quantum cryptography (PQC) for secure communication between an Apex.AI-based robotic software environment and a cloud-based control system. The collaboration demonstrates how connected robotic, automotive, and defense systems can securely exchange information with cloud services using standardized quantum-resistant cryptography while preserving the communication patterns and distributed software architectures that modern intelligent systems rely on. The implementation provides a practical blueprint for bringing quantum-safe security to long-lived connected systems without requiring fundamental changes to existing applications. As quantum computing continues to advance, many of today's widely deployed public-key cryptographic algorithms are expected to become vulnerable to cryptographically relevant quantum computers. For software-defined vehicles, autonomous systems, connected robotics, data of national security concern, and platforms designed to remain in service for decades, this creates a long-term cybersecurity challenge. These systems increasingly depend on secure communication with cloud-based services for monitoring, diagnostics, software updates, fleet management, coordination, and remote operation, making the transition to quantum-resistant security an important priority. The implementation combines Terra Quantum's post-quantum cryptography capabilities with Apex.OS to enable secure cloud communication using NIST-standardized quantum-resistant cryptographic algorithms. Apex.OS provides the software-defined robotics and intelligent-machine foundation for this joint solution, enabling secure edge-to-cloud communication in an application environment representative of modern autonomous and connected systems. Importantly, the solution preserves existing communication workflows and application architectures, enabling organizations to strengthen cybersecurity while maintaining compatibility with modern distributed software systems. "Connected intelligent systems are rapidly becoming critical infrastructure," said Markus Pflitsch, CEO, Founder and Chairman of Terra Quantum. "The vehicles, robots, and industrial systems being deployed today will still be operating when quantum computers begin challenging today's cryptographic standards. Organizations cannot afford to wait until that moment arrives. This implementation demonstrates that NIST-standardized post-quantum cryptography is ready to protect cloud-connected systems today, providing a practical path toward quantum resilience without disrupting existing software architectures." Dr. Florian Neukart, Chief Technology Officer at Terra Quantum, added: "The transition to post-quantum cryptography must be practical, standards-based, and interoperable with the software systems organizations already operate. Our collaboration with Apex.AI demonstrates that NIST-standardized post-quantum cryptography can be integrated into modern robotics and software-defined vehicle environments without changing application logic or communication architectures. By preserving existing development workflows while strengthening cryptographic resilience, we enable organizations to begin their migration to quantum-safe security today." Dr. Jan Becker, CEO at Apex.AI, said: "Software-defined vehicles, intelligent machines, and connected defense systems increasingly rely on trusted communication with cloud infrastructure throughout their operational lifetime. Our collaboration with Terra Quantum demonstrates that standardized post-quantum cryptography can be integrated into modern robotics software environments while preserving the flexibility, scalability, and communication models developers rely on to build next-generation intelligent systems. For organizations developing platforms that may remain in operation for years or decades, preparing for post-quantum security is becoming an important lifecycle consideration that should be addressed early in the architecture and product planning process." Unlike approaches that require redesigning applications or communication frameworks, the demonstrated implementation enables organizations to begin adopting standardized post-quantum security using technologies available today. By preserving established software architectures while replacing vulnerable cryptographic building blocks, organizations can prepare long-lived connected systems for the post-quantum era with minimal operational disruption. The implementation is particularly relevant for industries operating mission-critical connected assets, including robotics, autonomous mobility, industrial automation, manufacturing, logistics, aerospace, defense, and critical infrastructure, where devices deployed today must remain secure throughout operational lifecycles that often extend well beyond the arrival of cryptographically relevant quantum computers. Beyond securing individual platforms, the joint solution enables quantum-safe protection of interconnected Systems-of-Systems operating across cloud, edge, autonomous, and mission networks. In line with NATO's Multi-Domain Operations approach, resilient and interoperable communication infrastructures are essential to orchestrate effects across land, air, maritime, cyber, and space domains. The demonstrated architecture provides a scalable foundation for secure information exchange and mission assurance across complex, software-defined operational ecosystems. As governments and industry accelerate the adoption of NIST's post-quantum cryptographic standards, the collaboration demonstrates that organizations can begin their migration to quantum-safe communication today using standardized technologies without redesigning existing software-defined systems. Mohib ur rehman. Covering quantum and emerging technologies, Mohib explores the intersection of technology, security, and society. His work also frequently examines surveillance infrastructure and the institutions shaping the digital world. In addition to his work at The Quantum Insider, he co-runs SK NEXUS, an independent technology publication that helps readers understand the technologies shaping their lives. Stay Ahead of Quantum Get the latest research, company news, and market intelligence every week. MENTIONED IN THE ARTICLE More in Research