rouyang2017/SISSO
A data-driven method combining symbolic regression and compressed sensing for accurate & interpretable models.
This tool helps materials scientists and researchers quickly find simple, understandable mathematical formulas that predict material properties or classify material types. You provide a dataset of material characteristics and their corresponding properties or categories. It then outputs the most accurate and interpretable equations, making it easier to understand the underlying relationships in your data.
353 stars.
Use this if you need to discover clear, concise formulas from complex materials data that can predict outcomes or classify materials, enabling you to gain insights and share models easily.
Not ideal if you prefer black-box machine learning models where interpretability is not a primary concern, or if you are not comfortable working with command-line Fortran applications.
Stars
353
Forks
93
Language
Fortran
License
Apache-2.0
Category
Last pushed
Jan 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rouyang2017/SISSO"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
CliMA/Oceananigans.jl
🌊 Julia software for fast, friendly, flexible, ocean-flavored fluid dynamics on CPUs and GPUs
JuliaLang/julia
The Julia Programming Language
WassimTenachi/PhySO
Physical Symbolic Optimization
FluxML/Flux.jl
Relax! Flux is the ML library that doesn't make you tensor
EnzymeAD/Enzyme.jl
Julia bindings for the Enzyme automatic differentiator