# nguyenkhoa0209/pinns_tutorial architecture

> Architecture diagram of the GitHub repository nguyenkhoa0209/pinns_tutorial, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-06-07). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/nguyenkhoa0209/pinns_tutorial
- Repository: https://github.com/nguyenkhoa0209/pinns_tutorial

## Overview

##### Project type and purpose
- Project type: An educational/open-source tutorial library for Physics‐Informed Neural Networks (PINNs).
- Purpose: Provide code modules, Jupyter notebooks, and data to demonstrate how to solve PDEs via data‐driven ML and PINNs, including advanced sampling strategies.

##### File structure
- Top‐level modules:
- data/ (raw numerical data for training & validation)
- networks.py (neural network architectures)
- pinns.py & pinns_draft_lbfgs.py (PINN training engines, loss definitions)
- adapt_sampling.py (adaptive or residual‐based collocation‐point selection)
- utils.py (data loading, normalization, visualization helpers)
- *.ipynb notebooks (tutorial entry points: part1, part2, solutions)
- slides/ (PDF and text docs for background theory)
- Patterns: Modular Python scripts for core functionality; notebooks orchestrate workflows.

##### README for insights
- Two phases: Part 1 (pure data‐driven ML) and Part 2 (PINNs for PDEs).
- Online execution via Colab/Binder—emphasizes notebooks as front end.
- References indicate focus on sampling strategies, training stability, advanced PINN features.

##### Main components & interactions
a. Components:
1. Data Store (data/ folder)
2. Preprocessing & Utilities (utils.py)
3. Network Definition (networks.py)
4. PINN Engine (pinns.py & pinns_draft_lbfgs.py)
5. Sampling Module (adapt_sampling.py)
6. Notebook Interface (part1_*.ipynb, part2_*.ipynb, solution_*.ipynb)
7. Slide Decks (slides/)
b. Relationships:
- Notebooks import utils, networks, pinns, and adapt_sampling
- utils loads data from data/ → preprocess → feeds inputs to PINN Engine
- networks defines f_θ(x) → PINN Engine applies physics‐informed losses
- adapt_sampling provides collocation‐points to PINN Engine
c. Architectural patterns:
- Layered modular design (data → utils → core modules → interface)
- Separation of concerns: network architecture, solver logic, sampling strategy
- Extensibility points: swap network architectures, sampling methods, optimizers
d. Key technologies:
- Python 3.x, NumPy, TensorFlow or PyTorch (in engines)
- Jupyter notebooks as primary UIs
- Adaptive sampling algorithms for PINNs

##### Detail but avoid over‐fragmentation
- Every Python script as a module block
- Import/use relationships rather than internal function calls
- That notebooks are the entry points orchestrating workflows

[Data Store] → [Utilities Module] →
↘
[PINN Engine] ← [Network Definition]
↑
[Sampling Module]
[Notebooks] ⟲ imports {Utilities, Network, PINN Engine, Sampling} → visualizes outputs
[Slides] (external docs)

## Diagram (Mermaid)

```mermaid
flowchart TD
    %% Data Layer
    DS[(Data Store)]:::data

    %% Preprocessing Layer
    U["Utilities Module\n(utils.py)"]:::utils

    %% Core Engine
    subgraph "Core Engine"
        direction TB
        P1["PINN Engine\n(pinns.py)"]:::core
        P2["PINN Engine Draft\n(pinns_draft_lbfgs.py)"]:::core
        N["Network Definition\n(networks.py)"]:::core
        S["Sampling Module\n(adapt_sampling.py)"]:::core
    end

    %% Interface Layer
    subgraph "Notebook Interface"
        direction TB
        NB1["part1_data_driven_ml.ipynb"]:::interface
        NB2["part2_pinns_scope_of_use.ipynb"]:::interface
        NB3["solution_part1.ipynb"]:::interface
        NB4["solution_part2.ipynb"]:::interface
    end

    %% Documentation
    Slides["Slides\n(slides/)"]:::docs

    %% Connections
    DS --> U
    U --> P1
    U --> P2
    N --> P1
    N --> P2
    S --> P1
    S --> P2
    P1 --> NB1
    P1 --> NB2
    P2 --> NB3
    P2 --> NB4
    NB1 --> U
    NB1 --> N
    NB1 --> P1
    NB1 --> S
    NB2 --> U
    NB2 --> N
    NB2 --> P1
    NB2 --> S
    NB3 --> U
    NB3 --> N
    NB3 --> P2
    NB3 --> S
    NB4 --> U
    NB4 --> N
    NB4 --> P2
    NB4 --> S

    %% Click Events
    click DS "https://github.com/nguyenkhoa0209/pinns_tutorial/tree/main/data/"
    click U "https://github.com/nguyenkhoa0209/pinns_tutorial/blob/main/utils.py"
    click N "https://github.com/nguyenkhoa0209/pinns_tutorial/blob/main/networks.py"
    click P1 "https://github.com/nguyenkhoa0209/pinns_tutorial/blob/main/pinns.py"
    click P2 "https://github.com/nguyenkhoa0209/pinns_tutorial/blob/main/pinns_draft_lbfgs.py"
    click S "https://github.com/nguyenkhoa0209/pinns_tutorial/blob/main/adapt_sampling.py"
    click NB1 "https://github.com/nguyenkhoa0209/pinns_tutorial/blob/main/part1_data_driven_ml.ipynb"
    click NB2 "https://github.com/nguyenkhoa0209/pinns_tutorial/blob/main/part2_pinns_scope_of_use.ipynb"
    click NB3 "https://github.com/nguyenkhoa0209/pinns_tutorial/blob/main/solution_part1.ipynb"
    click NB4 "https://github.com/nguyenkhoa0209/pinns_tutorial/blob/main/solution_part2.ipynb"
    click Slides "https://github.com/nguyenkhoa0209/pinns_tutorial/tree/main/slides/"

    %% Styles
    classDef data fill:#AED6F1,stroke:#1F618D,color:#1B2631;
    classDef utils fill:#ABEBC6,stroke:#239B56,color:#1B2631;
    classDef core fill:#F5CBA7,stroke:#CA6F1E,color:#1B2631;
    classDef interface fill:#D7BDE2,stroke:#884EA0,color:#1B2631;
    classDef docs fill:#D5DBDB,stroke:#626567,color:#1B2631;
```
