Latest posts tagged with #sciML on Bluesky
Join us for a Dyad Modeling Livestream today - this time at 1pm ET / 10 am PT! Michael Tiller will joining us today to model a hybrid-EV powertrain!
Tune in on YouTube and send us your thoughts in the chat!
www.youtube.com/watch?v=qLfV...
#sciml #julialang #dyad
Find more here: https://oroikono.github.io/sigs-paper-site/#benchmarks
Surrogate accuracy isn’t the same as verification. Analytical solutions act as unit tests when you need credibility. the motivation behind the updated SIGS: grammar-valid candidates → latent exploration → residual-validated refinement (incl. coupled systems).
#SciML #PDE @eth-ai-center.bsky.social
Recent optimizations in SciMLSensitivity.jl are having some pretty good payoffs! Given we just 2.5x'd 2 months ago, this next change of 3.2x is putting us almost an order of magnitude ahead! See the latest autodiff benchmarks docs.sciml.ai/SciMLBenchma...
#sciml #julialang
February JuliaHub #newsletter is live—spotlighting Dyad 2.0 with agentic #AI, new modeling livestreams, #SciML breakthroughs, media features, and upcoming #webinars. Explore how physics-based AI is reshaping engineering workflows.
juliahub.com/blog/februar...
#JuliaHub #Dyad #AgenticAI #JuliaLang
Julia’s GPU-accelerated ODE solvers deliver 20–100× speedups over JAX and PyTorch. In this talk, Chris Rackauckas explains the GPU architecture choices behind the gains—and where they matter most.
youtu.be/ZSFfv2cckx0
#JuliaLang #GPUComputing #SciML #HPC #ScientificComputing
New fastest explicit non-stiff ODE solver? That's right, we now have something beating the pants off of the high order explicit RK methods! Check out the new symbolic-numeric optimized Taylor methods available in DifferentialEquations.jl!
#julialang #diffeq #sciml
At AIAA SciTech, JuliaHub demonstrated Dyad’s agentic AI for interacting with complex, physics-based models. From aerospace to fluid mechanics, Dyad sparked conversations on scalable, trustworthy AI-assisted engineering.
juliahub.com/blog/juliahu...
#julialang #JuliaHub #Dyad #SciML #EngineeringAI
Scientific machine learning (SciML) methods are techniques which incorporate machine learning with mechanistic modeling. The purpose of this minisymposium is to share improved methods and applications of SciML to showcase the ever advancing ecosystem in Julia. Examples of topics fit for this minisymposium include: New algorithms and software for physics-informed neural networks Tips, tricks, and techniques for improving convergence of universal differential equations Applications of fitting universal differential equations on real data and verification Methods which use neural networks with classical solvers in new ways Advancements in automatic differentiation for SciML applications Methods which use learning to accelerate numerical simulations (surrogates, metamodels, emulators, reduced order methods (ROMs)) Advancements in compiler and optimization techniques to improve learning in SciML scenarios.
@juliacon.org 2026 will have a minisymposium on "Methods and Applications of Scientific Machine Learning (SciML)" hosted by @chrisrackauckas.bsky.social find out more on pretalx.com/juliacon-202... and submit your proposal through juliacon.org/2026/cfp/
#julialang #sciml
Engineering models are getting more complex—and the tools to work with them must evolve. This webinar explores the #Dyad Agent and how agentic AI helps engineers build, modify, and reason about system models using physics-grounded workflows.
juliahub.com/events/intro...
#JuliaLang #AgenticAI #SciML
Machine Design highlights how Scientific Machine Learning is transforming #predictive #maintenance. By combining physics with data, #SciML delivers scalable, reliable insights—even with limited telemetry. juliahub.com/blog/juliahu...
#Julialang #DigitalTwins #Manufacturing #JuliaHub
Your college professor teaches you "A-stable methods are required for stiff ODEs". But PSA, the most commonly used stiff ODE solvers (adaptive order BDF methods) are not A-stable. #sciml #numericalanalysis #diffeq
www.youtube.com/shorts/hmKVQ...
Physics-Informed Neural Surrogates for Mesh-Invariant Modeling of High-Speed Flows at #AIAA #SciTech!
We built a neural surrogate that predicts aerodynamic behavior 595x faster than CFD while maintaining ~1% relative error.
#sciml #Julialang #CFD #Hypersonics #AIAASciTech
Join our live webinar on interactive dashboards with Dyad and Makie.jl. Learn how to link models to dynamic visualizations, run live parameter sweeps with UI controls, and explore 3D, physically meaningful views.
juliahub.com/events/inter...
#JuliaLang #Dyad #Makie #ScientificComputing #SciML
An episode with Dr. Viral Shah and Dr. Chris Rackauckas on rethinking engineering simulation. They discuss modern solver stacks, SciML, digital twins, and how hybrid physics–ML tools may reshape industrial engineering.
open.spotify.com/episode/16wQ...
#JuliaLang #SciML #ScientificComputing
71 citations: MyCrunchGPT makes SciML accessible through an LLM-powered framework. Users provide simple prompts; the system handles problem formulation, code generation & analysis with a web interface.
📖 www.dl.begellhouse.com/journals/558...
#GenerativeAI #SciML
New paper with J.A. Christen, just accepted in Statistical Methods in Medical Research
"Hazard-based distributional regression via ordinary differential equations"
preprint: arxiv.org/abs/2512.16336
R and Julia code + data: github.com/FJRubio67/Su...
#rstats #JuliaLang #SciML
SciML is transforming predictive maintenance by combining physics and limited telemetry. Binnies UK, Williams Grand Prix Technologies and JuliaHub achieved 90%+ accuracy using just four signals.
juliahub.com/blog/water-i...
#SciML #JuliaHub
Explore how causal and acausal modeling differ in system design. This session uses RC and RLC circuits to show why acausal #modeling scales better as complexity grows, and how Dyad with Julia and #SciML makes it practical for real #engineering.
juliahub.com/events/causa...
#JuliaLang #Dyad
See how #Dyad Model Discovery uses Universal Differential Equations and neural networks to learn the physics traditional models miss. This session covers how neural components integrate with physical models and how data reveals the missing dynamics. juliahub.com/events/lever... #JuliaLang #SciML
New livestream, #Dyad Modeling Live! In this stream we built up a thermal model of a room using #AgenticAI and added a heat pump with different control strategies and analyzed the power efficiency. Join the fun live next week! #julialang #sciml
youtube.com/live/I542x6g...
See how Dyad Model Discovery uses Universal Differential Equations and neural networks to learn missing physics in real systems. This session shows how neural components fit inside physical models to reveal unmodeled dynamics.
juliahub.com/events/lever...
#JuliaLang #Dyad #SciML
See how #Dyad Model Discovery uses Universal Differential Equations to learn missing physics by embedding a neural network inside a component and training it on experimental data. This walkthrough shows how Dyad reveals dynamics you can’t fully model.
juliahub.com/blog/missing...
#JuliaLang #SciML
ANSYS /Synopsys, one of the largest simulation companies in the world, is partnering with @JuliaHub_Inc in order to bring #Dyad, #Julialang, and #SciML to next level of adoption. We have many things planned. This is how research becomes reality.
www.prnewswire.com/news-release...
#SciML fact of the day: automatic differentiation fails to give the correct derivative on a lot of very simple functions 😱 😱 😱 . #julialang #automaticdifferentiation
youtube.com/shorts/KTguZ...
Can Agentic AI turn single purpose code into reusable modular code? Dyad's specialized AI can!
Watch our latest video on AI-assisted model restructuring and physics enhancement:
www.youtube.com/watch?v=0RdA...
#ModelingAndSimulation #AIAgent #JuliaLang #SciML #Dyad #SystemsEngineering #Modelica
Unseen factors can make or break control systems. Learn how Scientific Machine Learning (SciML) in Julia models unknown disturbances—like sunlight’s effect on smart home temperature—to improve prediction and control.
juliahub.com/blog/disturb...
#JuliaLang #SciML #SystemSimulation
Watch Dyad's AI agent build a complete thermal model from just an image! Picture -> validated DAEs in minutes.
Features: Auto parameter generation, model optimization, custom animations. All with production-ready Julia code.
youtu.be/eKLDVCkJC1s
#dyad #julialang #sciml
Causal modeling defines signal flow, but it gets rigid as systems scale. Acausal modeling focuses on physical relationships—letting equations form automatically. See how Dyad, built on Julia and #SciML, makes system #modeling more scalable and reusable. juliahub.com/blog/causal-...
#JuliaLang #Dyad
Accurate refrigerant mass estimation is key to #HVAC efficiency and compliance. Join Mitsubishi Electric + JuliaHub to see how #ModelingToolkit and #SciML enable a #digitaltwin estimator with <2% error using only pressure & temperature data.
juliahub.com/events/mitsu...
#JuliaLang #Simulation #Dyad
Refrigerant mass estimation in #HVAC just got easier. Join experts from Mitsubishi Electric & JuliaHub for a #webinar on using #SciML + #ModelingToolkit to build a high-accuracy, non-invasive model using just pressure & temp data. juliahub.com/events/mitsu...
#julialang #DigitalTwin #Dyad
