shayansss/pmse
Implementation of a new pointwise metric using Keras and Abaqus.
This project helps engineers and researchers working with numerical simulations quickly evaluate the accuracy of machine learning models used to speed up those simulations. It takes outputs from your finite element analysis software (like Abaqus) and your machine learning surrogate models, then produces visual error correlations, plots, and a unique 'Pointwise Mean Squared Error' (PMSE) contour.
No commits in the last 6 months.
Use this if you are developing or evaluating machine learning surrogate models to accelerate complex numerical simulations and need a detailed, visual way to understand where and how your surrogate model's errors correlate with your full numerical model's outputs.
Not ideal if you are not using finite element analysis or similar numerical simulations, or if you only need standard, non-pointwise evaluation metrics for your machine learning models.
Stars
9
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Sep 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/shayansss/pmse"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pdebench/PDEBench
PDEBench: An Extensive Benchmark for Scientific Machine Learning
tum-pbs/PhiFlow
A differentiable PDE solving framework for machine learning
ArnauMiro/pyLowOrder
High performance parallel reduced order Modelling library
peterdsharpe/NeuralFoil
NeuralFoil is a practical airfoil aerodynamics analysis tool using physics-informed machine...
lettucecfd/lettuce
Computational Fluid Dynamics based on PyTorch and the Lattice Boltzmann Method