Latest
Introducing Frontier
Frontier turns the simulations your team has already run into physics models you can train, evaluate and deploy on your own infrastructure. Today we are opening the waitlist.
DimensionLab
Blog
Writing on machine learning for physics and engineering simulation: research notes, product updates and news from the team.
All posts
21 articles
Sunsetting Siml.ai
We shut down the Siml.ai platform on 31 March 2025. Here is what Siml.ai was, what happened to user data, and where the work continues.
Siml.ai v0.6: Expressions in Constraints, Datasets and UX improvements
Siml.ai v0.6 adds expressions in constraint nodes, an improved overview page and a smoother environment creation flow, with datasets coming next.
Aerodynamic Simulation: Transforming with State-of-the-Art Neural Network Architectures
We recently published a research paper titled "Simulation Analysis of Car Aerodynamics within Tunnel Environment using Deep Learning: A Comparative Architectural Study".
The Nuances of Spectral Bias: How Stubborn is AI?
Neural networks learn coarse, low-frequency patterns first and struggle with fine detail. This post explains spectral bias and how Fourier feature mappings help.
Multi-Scale CFD Simulations: Challenges and Opportunities in Bridging Micro to Macro Scales
Multi-scale CFD simulations involve the integration of models and computational techniques that operate at different lengths and time scales.
Geometry-Informed Neural Operators: Transforming 3D Fluid Dynamics Simulations
Partial Differential Equations (PDEs) are crucial for modeling and comprehending natural events in the computer sciences, particularly in computational fluid dynamics (CFD).
Enter Siml.ai v0.5: New Features and Enhancements
Welcome to Siml.ai version 0.5. In this release, we focused on user experience enhancements, fixing bugs, and improving performance.
Enhancing User Experience: Automatic Notification for Completed Training Simulations
In our continuous effort to enhance user experience, we are thrilled to introduce a new feature in our application that addresses a common pain point for our users — the waiting time for completing the training of simulations.
Identifying Wind Turbine Dynamics: An Exploration of Simulation for Sustainability
Recent years have seen incredible progress in the field of renewable energy, with wind turbines emerging as imposing representations of environmentally friendly power production.
Revolutionizing Climate Modeling: How SFNO Enhances Weather Forecasting on a Global Scale
When it comes to navigating the effects of climate change, one of the greatest challenges we face today is modelling Earth's complex weather and climate systems accurately and efficiently.
DimensionLab at Web Summit 2023 - Lisbon: Spreading the word about Siml.ai
After the Siml.ai beta launch and the v0.3 release with custom equations and plugins, the DimensionLab team took the product to Web Summit 2023 in Lisbon.
Introducing Compute Credits
Siml.ai introduces compute credits: pay with your preferred method and top up credits for training and simulation in a few clicks.
Siml.ai v0.3 released: Custom equations and plugins
Today marks a significant milestone for the simulation software landscape as we at DimensionLab unveil the latest Siml.ai version 0.3, featuring the most requested “Custom Equations” support.
Earthquake hypocenter localization with X-DeepONet
In one of the previous posts we have talked about brand new Laplace Neural Operator, this time we focus on extention of well-known Deep Operator Network (DeepONet).
Announcing Siml.ai beta: On the road to the future of AI-Driven numerical simulation
Today, we are thrilled to announce the beta release of Siml.ai, the next-generation software platform that is designed to transform the landscape of AI-driven numerical simulation.
DimensionLab at SlovakiaTech 2023: Spreading the word about PhysicsML
In parallel to working hard on our upcoming beta release of Siml.ai, which will launch an upgraded architecture and improved features, we took part at SlovakiaTech 2023 that was held in Košice during 19th and 20th September.
MyCrunchGPT - A ChatGPT Framework for scientific machine learning
Ever since the launch of large language models such as ChatGPT, scientists, engineers and public are trying to find various ways to automate complicated computing tasks with natural language processing.
Laplace Neural Operator
An introduction to the Laplace Neural Operator (LNO), a neural network that learns to solve partial differential equations more efficiently than traditional methods.
Harnessing AI: The New Frontier in Physics Simulation
How physics-informed machine learning can cut simulation time from days to seconds, with examples from weather prediction, wind farm optimization and blood flow in aneurysms.
Introducing Siml.ai alpha
We are happy to announce a launch of Siml.ai alpha release to the public!