Dev updates

.github/PULL_REQUEST_TEMPLATE.md

@@ -1 +1,12 @@
-Fixes #ISSUE_NUMBER
+## Description
+<!-- Provide a standalone description of changes in this PR. -->
+<!-- Reference any issues closed by this PR with "closes #1234". -->
+
+This PR fixes #ISSUE_NUMBER. <!-- Possible other comments. -->
+
+## Checklist
+
+- [ ] Code follows the project’s [Code Style Guidelines](https://github.com/mathLab/PINA/blob/master/CONTRIBUTING.md#code-style--guidelines)
+- [ ] Tests have been added or updated
+- [ ] Documentation has been updated if necessary
+- [ ] Pull request is linked to an open issue

.github/workflows/monthly-tagger.yml

@@ -11,7 +11,7 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest, macos-latest, ubuntu-latest]
-        python-version: [3.8, 3.9, '3.10', '3.11', '3.12'] 
+        python-version: [3.9, '3.10', '3.11', '3.12', '3.13'] 
     steps:
     - uses: actions/checkout@v2
     - name: Set up Python

.github/workflows/tester.yml

@@ -13,7 +13,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [windows-latest, macos-latest, ubuntu-latest]
-        python-version: [3.8, 3.9, '3.10', '3.11', '3.12']
+        python-version: [3.9, '3.10', '3.11', '3.12', '3.13']
 
     steps:
     - uses: actions/checkout@v4

.github/workflows/tutorial_exporter.yml

@@ -23,7 +23,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
-        python-version: 3.8
+        python-version: 3.9
 
     - name: Install dependencies
       run: |
@@ -91,7 +91,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v5
       with:
-        python-version: 3.8
+        python-version: 3.9
 
     - name: Install dependencies
       run: |

.gitignore

@@ -145,3 +145,6 @@ cython_debug/
 
 # tmp dir
 **tmp*
+
+# Avoid add of DS_Store files
+**.DS_Store

docs/source/_installation.rst

@@ -1,7 +1,7 @@
 Installation
 ============
 
-**PINA** requires requires `numpy`, `matplotlib`, `torch`, `lightning`, `sphinx` (for the documentation) and `pytest` (for local test). The code is tested for Python 3, while compatibility of Python 2 is not guaranteed anymore. It can be installed using `pip` or directly from the source code.
+**PINA** requires requires `torch`, `lightning`, `torch_geometric` and `matplotlib`. 
 
 Installing via PIP
 __________________
@@ -32,3 +32,21 @@ To install the package just type:
 .. code-block:: bash
 
     $ pip install -e .
+
+
+Install with extra packages
+____________________________
+
+To install extra dependencies required to run tests or tutorials directories, please use the following command:
+
+.. code-block:: bash
+
+    $ 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

docs/source/_rst/_code.rst

@@ -3,7 +3,7 @@ Code Documentation
 Welcome to PINA documentation! Here you can find the modules of the package divided in different sections.
 The high-level structure of the package is depicted in our API.
 
-.. figure:: ../index_files/API_color.png
+.. figure:: ../index_files/PINA_API.png
     :alt: PINA application program interface
     :align: center
     :width: 400
@@ -68,15 +68,19 @@ Solvers
     SolverInterface <solver/solver_interface.rst>
     SingleSolverInterface <solver/single_solver_interface.rst>
     MultiSolverInterface <solver/multi_solver_interface.rst>
+    SupervisedSolverInterface <solver/supervised_solver/supervised_solver_interface>
+    DeepEnsembleSolverInterface <solver/ensemble_solver/ensemble_solver_interface>
     PINNInterface <solver/physics_informed_solver/pinn_interface.rst>
     PINN <solver/physics_informed_solver/pinn.rst>
     GradientPINN <solver/physics_informed_solver/gradient_pinn.rst>
     CausalPINN <solver/physics_informed_solver/causal_pinn.rst>
     CompetitivePINN <solver/physics_informed_solver/competitive_pinn.rst>
     SelfAdaptivePINN <solver/physics_informed_solver/self_adaptive_pinn.rst>
     RBAPINN <solver/physics_informed_solver/rba_pinn.rst>
-    SupervisedSolver <solver/supervised.rst>
-    ReducedOrderModelSolver <solver/reduced_order_model.rst>
+    DeepEnsemblePINN <solver/ensemble_solver/ensemble_pinn>
+    SupervisedSolver <solver/supervised_solver/supervised.rst>
+    DeepEnsembleSupervisedSolver <solver/ensemble_solver/ensemble_supervised>
+    ReducedOrderModelSolver <solver/supervised_solver/reduced_order_model.rst>
     GAROM <solver/garom.rst>
 
 

docs/source/_rst/solver/ensemble_solver/ensemble_pinn.rst

@@ -0,0 +1,8 @@
+DeepEnsemblePINN
+==================
+.. currentmodule:: pina.solver.ensemble_solver.ensemble_pinn
+
+.. autoclass:: DeepEnsemblePINN
+    :show-inheritance:
+    :members:
+

docs/source/_rst/solver/ensemble_solver/ensemble_solver_interface.rst

@@ -0,0 +1,8 @@
+DeepEnsembleSolverInterface
+=============================
+.. currentmodule:: pina.solver.ensemble_solver.ensemble_solver_interface
+
+.. autoclass:: DeepEnsembleSolverInterface
+    :show-inheritance:
+    :members:
+

docs/source/_rst/solver/ensemble_solver/ensemble_supervised.rst

@@ -0,0 +1,8 @@
+DeepEnsembleSupervisedSolver
+=============================
+.. currentmodule:: pina.solver.ensemble_solver.ensemble_supervised
+
+.. autoclass:: DeepEnsembleSupervisedSolver
+    :show-inheritance:
+    :members:
+

docs/source/_rst/solver/reduced_order_model.rst → docs/source/_rst/solver/supervised_solver/reduced_order_model.rst

@@ -1,6 +1,6 @@
 ReducedOrderModelSolver
 ==========================
-.. currentmodule:: pina.solver.reduced_order_model
+.. currentmodule:: pina.solver.supervised_solver.reduced_order_model
 
 .. autoclass:: ReducedOrderModelSolver
    :members:

docs/source/_rst/solver/supervised.rst → docs/source/_rst/solver/supervised_solver/supervised.rst

@@ -1,6 +1,6 @@
 SupervisedSolver
 ===================
-.. currentmodule:: pina.solver.supervised
+.. currentmodule:: pina.solver.supervised_solver.supervised
 
 .. autoclass:: SupervisedSolver
    :members:

docs/source/_rst/solver/supervised_solver/supervised_solver_interface.rst

@@ -0,0 +1,8 @@
+SupervisedSolverInterface
+==========================
+.. currentmodule:: pina.solver.supervised_solver.supervised_solver_interface
+
+.. autoclass:: SupervisedSolverInterface
+    :show-inheritance:
+    :members:
+

docs/source/_tutorial.rst

@@ -1,35 +1,43 @@
-PINA Tutorials
-======================
+🚀 Welcome to the PINA Tutorials!
+==================================
 
 
-In this folder we collect useful tutorials in order to understand the principles and the potential of **PINA**.
+In this folder we collect useful tutorials in order to understand the principles and the potential of **PINA**. 
+Whether you're just getting started or looking to deepen your understanding, these resources are here to guide you.
 
 Getting started with PINA
 -------------------------
 
-- `Introduction to PINA for Physics Informed Neural Networks training <tutorial1/tutorial.html>`_
+- `Introductory Tutorial: A Beginner's Guide to PINA <tutorial17/tutorial.html>`_
+- `How to build a Problem in PINA <tutorial16/tutorial.html>`_
+- `Introduction to Solver classes <tutorial18/tutorial.html>`_
+- `Introduction to Trainer class <tutorial11/tutorial.html>`_
+- `Data structure for SciML: Tensor, LabelTensor, Data and Graph <tutorial19/tutorial.html>`_
+- `Building geometries with DomainInterface class <tutorial6/tutorial.html>`_
 - `Introduction to PINA Equation class <tutorial12/tutorial.html>`_
-- `PINA and PyTorch Lightning, training tips and visualizations <tutorial11/tutorial.html>`_
-- `Building custom geometries with PINA Location class <tutorial6/tutorial.html>`_
-
 
 Physics Informed Neural Networks
 --------------------------------
 
-- `Two dimensional Poisson problem using Extra Features Learning <tutorial2/tutorial.html>`_
-- `Two dimensional Wave problem with hard constraint <tutorial3/tutorial.html>`_
-- `Resolution of a 2D Poisson inverse problem <tutorial7/tutorial.html>`_
-- `Periodic Boundary Conditions for Helmotz Equation <tutorial9/tutorial.html>`_
-- `Multiscale PDE learning with Fourier Feature Network <tutorial13/tutorial.html>`_
+- `Introductory Tutorial: Physics Informed Neural Networks with PINA <tutorial1/tutorial.html>`_
+- `Enhancing PINNs with Extra Features to solve the Poisson Problem <tutorial2/tutorial.html>`_
+- `Applying Hard Constraints in PINNs to solve the Wave Problem <tutorial3/tutorial.html>`_
+- `Applying Periodic Boundary Conditions in PINNs to solve the Helmotz Problem <tutorial9/tutorial.html>`_
+- `Inverse Problem Solving with Physics-Informed Neural Network <tutorial7/tutorial.html>`_
+- `Learning Multiscale PDEs Using Fourier Feature Networks <tutorial13/tutorial.html>`_
+- `Learning Bifurcating PDE Solutions with Physics-Informed Deep Ensembles <tutorial14/tutorial.html>`_
 
 Neural Operator Learning
 ------------------------
 
-- `Two dimensional Darcy flow using the Fourier Neural Operator <tutorial5/tutorial.html>`_
-- `Time dependent Kuramoto Sivashinsky equation using the Averaging Neural Operator <tutorial10/tutorial.html>`_
+- `Introductory Tutorial: Neural Operator Learning with PINA <tutorial21/tutorial.html>`_
+- `Modeling 2D Darcy Flow with the Fourier Neural Operator <tutorial5/tutorial.html>`_
+- `Solving the Kuramoto-Sivashinsky Equation with Averaging Neural Operator <tutorial10/tutorial.html>`_
 
 Supervised Learning
 -------------------
 
-- `Unstructured convolutional autoencoder via continuous convolution <tutorial4/tutorial.html>`_
-- `POD-RBF and POD-NN for reduced order modeling <tutorial8/tutorial.html>`_
+- `Introductory Tutorial: Supervised Learning with PINA  <tutorial20/tutorial.html>`_
+- `Chemical Properties Prediction with Graph Neural Networks <tutorial25/tutorial.html>`_
+- `Unstructured Convolutional Autoencoders with Continuous Convolution <tutorial4/tutorial.html>`_
+- `Reduced Order Modeling with POD-RBF and POD-NN Approaches for Fluid Dynamics <tutorial8/tutorial.html>`_

docs/source/index.rst

@@ -1,6 +1,6 @@
 :html_theme.sidebar_secondary.remove:
 
-Welcome to PINA’s documentation!
+Welcome to PINA's documentation!
 =======================================
 
 .. grid:: 6
@@ -41,35 +41,36 @@ Welcome to PINA’s documentation!
   .. grid-item::
     :columns: 12 12 8 8
 
-    Physics Informed Neural network for Advanced modeling (**PINA**) is
-    an open-source Python library providing an intuitive interface for
-    solving differential equations using PINNs, NOs or both together.
+    **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 <https://pytorch.org/>`_, `PyTorch Lightning <https://lightning.ai/docs/pytorch/stable/>`_, 
+    and `PyTorch Geometric <https://pytorch-geometric.readthedocs.io/en/latest/>`_, 
+    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.
 
-    Based on `PyTorch <https://pytorch.org/>`_, `PyTorchLightning <https://lightning.ai/docs/pytorch/stable/>`_, and `PyG <https://pytorch-geometric.readthedocs.io/en/latest/>`_, **PINA** offers a simple and intuitive way to formalize a specific (differential) problem
-    and solve it using neural networks . The approximated solution of a differential equation
-    can be implemented using PINA in a few lines of code thanks to the intuitive and user-friendly  interface.        
+    - **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.
 
     For further information or questions about **PINA** contact us by email. 
 
-
-
-
   .. grid-item-card:: Contents
     :class-title: sd-fs-5
     :class-body: sd-pl-4
 
     .. toctree::
       :maxdepth: 1
 
-      API <_rst/_code>
-      Tutorial <_tutorial>
       Installing <_installation>
-      Team & Foundings <_team.rst>
+      API <_rst/_code>
+      Tutorials <_tutorial>
+      Cite PINA <_cite.rst>
       Contributing <_contributing>
+      Team & Foundings <_team.rst>
       License <_LICENSE.rst>
-      Cite PINA <_cite.rst>