Physics-Informed Neural networks for Advanced modeling
Physics-Informed Neural networks for Advanced modeling - Published in JOSS (2023)
Science Score: 100.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 3 DOI reference(s) in README and JOSS metadata -
✓Academic publication links
Links to: joss.theoj.org -
✓Committers with academic emails
9 of 34 committers (26.5%) from academic institutions -
○Institutional organization owner
-
✓JOSS paper metadata
Published in Journal of Open Source Software
Keywords
Keywords from Contributors
Repository
Physics-Informed Neural networks for Advanced modeling
Basic Info
- Host: GitHub
- Owner: mathLab
- License: mit
- Language: Python
- Default Branch: master
- Homepage: https://mathlab.github.io/PINA/
- Size: 133 MB
Statistics
- Stars: 554
- Watchers: 15
- Forks: 81
- Open Issues: 31
- Releases: 43
Topics
Metadata Files
README.md
|
Solving Scientific Problems with Machine Learning, Intuitively |
Getting Started | Documentation | Contributing
PINA is an open-source Python library designed to simplify and accelerate the development of Scientific Machine Learning (SciML) solutions. Built on top of PyTorch, PyTorch Lightning, and PyTorch Geometric, PINA provides an intuitive framework for defining, experimenting with, and solving complex problems using Neural Networks, Physics-Informed Neural Networks (PINNs), Neural Operators, and more.
Modular Architecture: Designed with modularity in mind and relying on powerful yet composable abstractions, PINA allows users to easily plug, replace, or extend components, making experimentation and customization straightforward.
Scalable Performance: With native support for multi-device training, PINA handles large datasets efficiently, offering performance close to hand-crafted implementations with minimal overhead.
Highly Flexible: Whether you're looking for full automation or granular control, PINA adapts to your workflow. High-level abstractions simplify model definition, while expert users can dive deep to fine-tune every aspect of the training and inference process.
Installation
Installing a stable PINA release
Install using pip:
sh
pip install "pina-mathlab"
Install from source:
sh
git clone https://github.com/mathLab/PINA
cd PINA
git checkout master
pip install .
Install with extra packages:
To install extra dependencies required to run tests or tutorials directories, please use the following command:
sh
pip install "pina-mathlab[extras]"
Available extras include:
* dev for development purpuses, use this if you want to Contribute.
* test for running test locally.
* doc for building documentation locally.
* tutorial for running Tutorials.
Quick Tour for New Users
Solving a differential problem in PINA follows the four steps pipeline:
Define the problem to be solved with its constraints using the Problem API.
Design your model using PyTorch, or for graph-based problems, leverage PyTorch Geometric to build Graph Neural Networks. You can also import models directly from the Model API.
Select or build a Solver for the Problem, e.g., supervised solvers, or physics-informed (e.g., PINN) solvers. PINA Solvers are modular and can be used as-is or customized.
Train the model using the Trainer API class, built on PyTorch Lightning, which supports efficient, scalable training with advanced features.
Do you want to learn more about it? Look at our Tutorials.
Solve Data Driven Problems
Data driven modelling aims to learn a function that given some input data gives an output (e.g. regression, classification, ...). In PINA you can easily do this by: ```python import torch from pina import Trainer from pina.model import FeedForward from pina.solver import SupervisedSolver from pina.problem.zoo import SupervisedProblem
inputtensor = torch.rand((10, 1)) targettensor = input_tensor.pow(3)
Step 1. Define problem
problem = SupervisedProblem(inputtensor, targettensor)
Step 2. Design model (you can use your favourite torch.nn.Module in here)
model = FeedForward(inputdimensions=1, outputdimensions=1, layers=[64, 64])
Step 3. Define Solver
solver = SupervisedSolver(problem, model, use_lt=False)
Step 4. Train
trainer = Trainer(solver, max_epochs=1000, accelerator='gpu') trainer.train() ```
Solve Physics Informed Problems
Physics-informed modeling aims to learn functions that not only fit data, but also satisfy known physical laws, such as differential equations or boundary conditions. For example, the following differential problem:
$$ \begin{cases} \frac{d}{dx}u(x) &= u(x) \quad x \in(0,1)\ u(x=0) &= 1 \end{cases} $$
in PINA, can be easily implemented by:
```python from pina import Trainer, Condition from pina.problem import SpatialProblem from pina.operator import grad from pina.solver import PINN from pina.model import FeedForward from pina.domain import CartesianDomain from pina.equation import Equation, FixedValue
def odeequation(input, output): ux = grad(output, input, components=["u"], d=["x"]) u = output.extract(["u"]) return ux - u
build the problem
class SimpleODE(SpatialProblem): outputvariables = ["u"] spatialdomain = CartesianDomain({"x": [0, 1]}) domains = { "x0": CartesianDomain({"x": 0.0}), "D": CartesianDomain({"x": [0, 1]}), } conditions = { "boundcond": Condition(domain="x0", equation=FixedValue(1.0)), "physcond": Condition(domain="D", equation=Equation(ode_equation)), }
Step 1. Define problem
problem = SimpleODE() problem.discretise_domain(n=100, mode="grid", domains=["D", "x0"])
Step 2. Design model (you can use your favourite torch.nn.Module in here)
model = FeedForward(inputdimensions=1, outputdimensions=1, layers=[64, 64])
Step 3. Define Solver
solver = PINN(problem, model)
Step 4. Train
trainer = Trainer(solver, max_epochs=1000, accelerator='gpu') trainer.train() ```
Application Programming Interface
Here's a quick look at PINA's main module. For a better experience and full details, check out the documentation.
Contributing and Community
We would love to develop PINA together with our community! Best way to get started is to select any issue from the good-first-issue label. If you would like to contribute, please review our Contributing Guide for all relevant details.
We warmly thank all the contributors that have supported PINA so far:
Made with contrib.rocks.
Citation
If PINA has been significant in your research, and you would like to acknowledge the project in your academic publication, we suggest citing the following paper:
Coscia, D., Ivagnes, A., Demo, N., & Rozza, G. (2023). Physics-Informed Neural networks for Advanced modeling. Journal of Open Source Software, 8(87), 5352.
Or in BibTex format
@article{coscia2023physics,
title={Physics-Informed Neural networks for Advanced modeling},
author={Coscia, Dario and Ivagnes, Anna and Demo, Nicola and Rozza, Gianluigi},
journal={Journal of Open Source Software},
volume={8},
number={87},
pages={5352},
year={2023}
}
Owner
- Name: SISSA mathLab
- Login: mathLab
- Kind: organization
- Email: luca.heltai@sissa.it
- Location: Via Bonomea 265, 34133 Trieste, TS, Italy
- Website: http://mathlab.sissa.it
- Repositories: 29
- Profile: https://github.com/mathLab
Applied Mathematics Laboratory @ SISSA
JOSS Publication
Physics-Informed Neural networks for Advanced modeling
Authors
SISSA, International School of Advanced Studies, Via Bonomea 265, Trieste, Italy
SISSA, International School of Advanced Studies, Via Bonomea 265, Trieste, Italy
SISSA, International School of Advanced Studies, Via Bonomea 265, Trieste, Italy
SISSA, International School of Advanced Studies, Via Bonomea 265, Trieste, Italy
Editor
Daniel S. Katz
Tags
python deep learning physics-informed neural networks scientific machine learning differential equations.Citation (CITATION.cff)
cff-version: "1.2.0"
authors:
- family-names: Coscia
given-names: Dario
orcid: "https://orcid.org/0000-0001-8833-6833"
- family-names: Ivagnes
given-names: Anna
orcid: "https://orcid.org/0000-0002-2369-4493"
- family-names: Demo
given-names: Nicola
orcid: "https://orcid.org/0000-0003-3107-9738"
- family-names: Rozza
given-names: Gianluigi
orcid: "https://orcid.org/0000-0002-0810-8812"
doi: 10.5281/zenodo.8163732
message: If you use this software, please cite our article in the
Journal of Open Source Software.
preferred-citation:
authors:
- family-names: Coscia
given-names: Dario
orcid: "https://orcid.org/0000-0001-8833-6833"
- family-names: Ivagnes
given-names: Anna
orcid: "https://orcid.org/0000-0002-2369-4493"
- family-names: Demo
given-names: Nicola
orcid: "https://orcid.org/0000-0003-3107-9738"
- family-names: Rozza
given-names: Gianluigi
orcid: "https://orcid.org/0000-0002-0810-8812"
date-published: 2023-07-19
doi: 10.21105/joss.05352
issn: 2475-9066
issue: 87
journal: Journal of Open Source Software
publisher:
name: Open Journals
start: 5352
title: Physics-Informed Neural networks for Advanced modeling
type: article
url: "https://joss.theoj.org/papers/10.21105/joss.05352"
volume: 8
title: Physics-Informed Neural networks for Advanced modeling
GitHub Events
Total
- Create event: 104
- Release event: 17
- Issues event: 132
- Watch event: 153
- Delete event: 87
- Member event: 2
- Issue comment event: 242
- Push event: 613
- Pull request review comment event: 276
- Pull request review event: 320
- Pull request event: 258
- Fork event: 14
Last Year
- Create event: 104
- Release event: 17
- Issues event: 133
- Watch event: 154
- Delete event: 87
- Member event: 2
- Issue comment event: 243
- Push event: 613
- Pull request review comment event: 276
- Pull request review event: 320
- Pull request event: 258
- Fork event: 14
Committers
Last synced: 5 months ago
Top Committers
| Name | Commits | |
|---|---|---|
| Dario Coscia | 9****a | 158 |
| Nicola Demo | d****a@g****m | 140 |
| FilippoOlivo | f****o@f****m | 95 |
| giovanni | g****8@y****t | 33 |
| Matteo Bertocchi | m****4@g****m | 19 |
| Anna Ivagnes | 7****s | 17 |
| github-actions[bot] | 4****] | 14 |
| Dario Coscia | d****a@c****t | 11 |
| Dario Coscia | d****a@D****l | 9 |
| Giovanni Canali | 1****8 | 8 |
| Francesco Andreuzzi | a****o@g****m | 8 |
| Dario Coscia | d****a@d****t | 8 |
| Giuseppe Alessio D'Inverno | 6****e | 6 |
| Kush | 5****K | 6 |
| Zahra Mirzaiyan Dehkordi | z****y@z****t | 6 |
| Dario Coscia | d****a@c****t | 5 |
| Monthly Tag bot | m****t@n****m | 4 |
| Dario Coscia | d****a@d****t | 2 |
| Dario Coscia | d****a@d****t | 2 |
| Ben Volokh | 8****3 | 2 |
| guglielmopadula | 9****a | 2 |
| M.Couraud | m****s@c****t | 2 |
| Pasquale Africa | p****a@s****t | 2 |
| Daniel S. Katz | d****z@i****g | 2 |
| Bo van Hasselt | 6****t | 1 |
| Dario Coscia | d****a@c****t | 1 |
| Dario Coscia | d****a@c****t | 1 |
| Dario Coscia | d****a@c****t | 1 |
| Eli Prater | p****4@g****m | 1 |
| Gabriele Codega | 1****a | 1 |
| and 4 more... | ||
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 4 months ago
All Time
- Total issues: 182
- Total pull requests: 519
- Average time to close issues: about 2 months
- Average time to close pull requests: 9 days
- Total issue authors: 33
- Total pull request authors: 30
- Average comments per issue: 1.16
- Average comments per pull request: 1.0
- Merged pull requests: 387
- Bot issues: 0
- Bot pull requests: 58
Past Year
- Issues: 94
- Pull requests: 225
- Average time to close issues: about 1 month
- Average time to close pull requests: 4 days
- Issue authors: 15
- Pull request authors: 14
- Average comments per issue: 0.45
- Average comments per pull request: 1.19
- Merged pull requests: 147
- Bot issues: 0
- Bot pull requests: 27
Top Authors
Issue Authors
- dario-coscia (62)
- ndem0 (34)
- GiovanniCanali (15)
- LoveFrootLoops (8)
- FilippoOlivo (6)
- annaivagnes (5)
- gc031298 (5)
- dgm2 (5)
- karthikncsuiisc (5)
- luAndre00 (4)
- Bovhasselt (3)
- AleDinve (3)
- yorkiva (2)
- karfungc (2)
- akshaysubr (2)
Pull Request Authors
- dario-coscia (196)
- ndem0 (90)
- github-actions[bot] (58)
- FilippoOlivo (45)
- GiovanniCanali (20)
- annaivagnes (18)
- AleDinve (12)
- gc031298 (10)
- fAndreuzzi (9)
- MatteB03 (8)
- SpartaKushK (8)
- benv123 (8)
- guglielmopadula (7)
- ZahraMirzaiyan (4)
- avisquid (3)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 1
-
Total downloads:
- pypi 217 last-month
- Total dependent packages: 0
- Total dependent repositories: 1
- Total versions: 26
- Total maintainers: 1
pypi.org: pina-mathlab
Physic Informed Neural networks for Advance modeling.
- Homepage: https://mathlab.github.io/PINA/
- Documentation: https://pina-mathlab.readthedocs.io/
- License: MIT
-
Latest release: 0.2.2
published 6 months ago
Rankings
Maintainers (1)
Dependencies
- actions/checkout v2 composite
- actions/setup-python v2 composite
- actions/checkout v2 composite
- ncipollo/release-action v1 composite
- actions/checkout v2 composite
- actions/setup-python v2 composite
- actions/checkout v2 composite
- actions/setup-python v1 composite
- pypa/gh-action-pypi-publish master composite
- actions/checkout v2 composite
- ammaraskar/sphinx-action master composite
- peaceiris/actions-gh-pages v3 composite
- actions/checkout v2 composite
- actions/setup-python v2 composite