--- title: Terra Quantum and Empa Develop AI Model for Laser... description: Terra Quantum and Empa announced LP-FNO, a Fourier Neural Operator model that predicts 3D temperature fields and melt-pool boundaries in laser welding,... canonical: https://daily.dev/posts/terra-quantum-and-empa-develop-ai-model-for-laser-welding-prediction-qxblk4wff twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Terra Quantum and Empa Develop AI Model for Laser Welding Prediction | daily.dev og:description: Terra Quantum and Empa announced LP-FNO, a Fourier Neural Operator model that predicts 3D temperature fields and melt-pool boundaries in laser welding,... og:url: https://daily.dev/posts/terra-quantum-and-empa-develop-ai-model-for-laser-welding-prediction-qxblk4wff og:image: https://api.daily.dev/og/posts/qxbLK4wFf.png og:image:alt: Terra Quantum and Empa Develop AI Model for Laser Welding Prediction og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Terra Quantum and Empa Develop AI Model for Laser Welding Prediction **[The Quantum Insider](https://daily.dev/sources/thequantuminsider)** · 5 min read · 0 upvotes · 0 comments ## Summary Terra Quantum and Empa announced LP-FNO, a Fourier Neural Operator model that predicts 3D temperature fields and melt-pool boundaries in laser welding, claiming up to 100,000x speedup over traditional multiphysics simulation. Trained on high-fidelity simulations of Ti-6Al-4V across laser powers of 40-190W and scan speeds of 0.1-1 m/s, it produces full 3D predictions in about 8ms (standard resolution) or 88ms (double resolution), with roughly 2.5% temperature error and an IoU above 0.9 for melt-pool boundary segmentation. The model is resolution-invariant and covers both conduction and keyhole welding regimes, a first according to the researchers. Findings were published in the Journal of Intelligent Manufacturing. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How much faster is the LP-FNO neural operator model compared to traditional multiphysics laser welding simulation? LP-FNO is up to 100,000 times faster than equivalent high-fidelity multiphysics simulation of laser welding. Where a gold-standard simulation takes about six minutes at 10 micron resolution or over an hour at 5 micron resolution, LP-FNO generates full 3D temperature and melt-pool predictions in roughly 8 milliseconds at standard resolution and 88 milliseconds at double resolution. _daily.dev surfaces developments like this for engineers evaluating AI surrogate models against traditional simulation pipelines._ ### What accuracy does the LP-FNO model achieve for melt-pool boundary prediction in laser welding? LP-FNO achieves an intersection-over-union score above 0.9 for melt-pool boundary segmentation, alongside roughly 2.5% average relative error in temperature field predictions. It was trained on Ti-6Al-4V titanium alloy simulations spanning laser powers of 40 to 190 watts and scan speeds of 0.1 to 1 meter per second, covering both conduction and keyhole welding regimes. _Teams benchmarking neural surrogate models against physics simulators can track these accuracy figures via daily.dev._ ## Similar posts on daily.dev - [FirstQFM Model Cuts Single-Qubit Gate Times by 33% on QuantWare Processor](https://daily.dev/posts/firstqfm-model-cuts-single-qubit-gate-times-by-33-on-quantware-processor-yhbsm2dok) · The Quantum Insider · 0 upvotes · 0 comments - [MIT researchers use AI to uncover atomic defects in materials](https://daily.dev/posts/mit-researchers-use-ai-to-uncover-atomic-defects-in-materials-cqhw9wmyv) · MIT News · 0 upvotes · 0 comments - [Accelerate Clean, Modular, Nuclear Reactor Design with AI Physics](https://daily.dev/posts/accelerate-clean-modular-nuclear-reactor-design-with-ai-physics-m29ozpt8s) · NVIDIA Developer · 1 upvotes · 0 comments - [Qwen3-VL can scan two-hour videos and pinpoint nearly every detail](https://daily.dev/posts/qwen3-vl-can-scan-two-hour-videos-and-pinpoint-nearly-every-detail-5dvyilfvf) · Hacker News · 1 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning) [View this post on daily.dev](https://daily.dev/posts/terra-quantum-and-empa-develop-ai-model-for-laser-welding-prediction-qxblk4wff) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Terra Quantum and Empa Develop AI Model for Laser Welding Prediction","url":"https://daily.dev/posts/terra-quantum-and-empa-develop-ai-model-for-laser-welding-prediction-qxblk4wff","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/terra-quantum-and-empa-develop-ai-model-for-laser-welding-prediction-qxblk4wff"},"datePublished":"2026-09-29T13:08:10.324Z","dateModified":"2026-09-29T13:08:34.607Z","description":"Terra Quantum and Empa announced LP-FNO, a Fourier Neural Operator model that predicts 3D temperature fields and melt-pool boundaries in laser welding,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d14df98a53cf9837747c66a114c0461e?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d14df98a53cf9837747c66a114c0461e?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The Quantum Insider","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The Quantum Insider","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/7b14a6b34c1b464c9e8a88d9a0dac951","url":"https://daily.dev/sources/thequantuminsider"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/terra-quantum-and-empa-develop-ai-model-for-laser-welding-prediction-qxblk4wff","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The Quantum Insider","item":"https://daily.dev/sources/thequantuminsider"},{"@type":"ListItem","position":3,"name":"Terra Quantum and Empa Develop AI Model for Laser Welding Prediction"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/terra-quantum-and-empa-develop-ai-model-for-laser-welding-prediction-qxblk4wff#faq","mainEntity":[{"@type":"Question","name":"How much faster is the LP-FNO neural operator model compared to traditional multiphysics laser welding simulation?","acceptedAnswer":{"@type":"Answer","text":"LP-FNO is up to 100,000 times faster than equivalent high-fidelity multiphysics simulation of laser welding. Where a gold-standard simulation takes about six minutes at 10 micron resolution or over an hour at 5 micron resolution, LP-FNO generates full 3D temperature and melt-pool predictions in roughly 8 milliseconds at standard resolution and 88 milliseconds at double resolution. daily.dev surfaces developments like this for engineers evaluating AI surrogate models against traditional simulation pipelines."}},{"@type":"Question","name":"What accuracy does the LP-FNO model achieve for melt-pool boundary prediction in laser welding?","acceptedAnswer":{"@type":"Answer","text":"LP-FNO achieves an intersection-over-union score above 0.9 for melt-pool boundary segmentation, alongside roughly 2.5% average relative error in temperature field predictions. It was trained on Ti-6Al-4V titanium alloy simulations spanning laser powers of 40 to 190 watts and scan speeds of 0.1 to 1 meter per second, covering both conduction and keyhole welding regimes. Teams benchmarking neural surrogate models against physics simulators can track these accuracy figures via daily.dev."}}]} ```