# bsshreesha/physics_informed_neural_network architecture

> Architecture diagram of the GitHub repository bsshreesha/physics_informed_neural_network, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-05-25). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/bsshreesha/physics_informed_neural_network
- Repository: https://github.com/bsshreesha/physics_informed_neural_network

## Overview

##### Project type and purpose
- This repository is a collection of Jupyter notebooks demonstrating Physics-Informed Neural Networks (PINNs) implemented in TensorFlow to solve various partial differential equations (PDEs). It is not a traditional application with “frontend” and “backend” layers but rather an experimental ML research codebase focused on numerical PDE solutions.

##### File structure
- Top level contains only Jupyter notebooks (Integral_PINN.ipynb, MHD_Realistic.ipynb, etc.), one Word document (Equations.docx) and the README.
- Each notebook encapsulates a standalone experiment: data generation (domain sampling), model definition, training routine, and visualization.
- There are no separate “src” or “lib” directories—code and results live together in notebooks.

##### README for additional insights
- The README describes the core PINN architecture: an input layer (time/spatial coordinates), fully connected hidden layers, and an output layer predicting the PDE solution.
- The training loss combines data‐driven loss (if any measured data exist) and physics loss (enforcing the PDE residual).
- The technology stack is TensorFlow for model construction and training, and Jupyter for orchestration and visualization.

## Diagram (Mermaid)

```mermaid
flowchart TB
    %% Subgraph for Experiment Controller
    subgraph "Experiment Controller (Notebook Layer)" 
        direction TB
        FP["Final_Project.ipynb"]:::notebook
        ID["Integral_Differential.ipynb"]:::notebook
        IP["Integral_PINN.ipynb"]:::notebook
        IS["Integral_Small.ipynb"]:::notebook
        MR["MHD_Realistic.ipynb"]:::notebook
        RP["Realistic_PDE_System.ipynb"]:::notebook
        R1["Reinforcement.ipynb"]:::notebook
        R3["Reinforcement_v3.ipynb"]:::notebook
        SP["Solving_PDE.ipynb"]:::notebook
        TFH["TF_PINN_Higher_Order_PDEs.ipynb"]:::notebook
    end

    %% Core Pipeline Components
    PDE["PDE Definition & Domain Sampler"]:::data
    Model["Neural Network Module\n(TensorFlow Graph)"]:::compute
    Loss["Loss Computation\n(Data Loss + Physics Loss)"]:::compute
    Train["Training Loop & Optimizer"]:::compute
    IO["Model Checkpointing & Logging"]:::storage
    Viz["Post-processing & Visualization"]:::io

    %% Documentation
    subgraph "Project Documentation"
        README["README.md"]:::doc
        EQ["Equations.docx"]:::doc
    end

    %% Connections
    FP -->|orchestrates| PDE
    ID -->|orchestrates| PDE
    IP -->|orchestrates| PDE
    IS -->|orchestrates| PDE
    MR -->|orchestrates| PDE
    RP -->|orchestrates| PDE
    R1 -->|orchestrates| PDE
    R3 -->|orchestrates| PDE
    SP -->|orchestrates| PDE
    TFH -->|orchestrates| PDE

    PDE -->|"collocation points"| Model
    Model -->|"predicted solution"| Loss
    PDE -->|"PDE residual definitions"| Loss
    Loss -->|"loss gradients"| Train
    Train -->|"updated weights"| Model
    Train -->|"checkpoint & logs"| IO
    Model -->|"final solution"| Viz
    IO -->|"load/checkpoint"| Train
    Viz -->|reports| FP

    README -.->|documents| FP
    EQ -.->|equations reference| PDE

    %% Click Events
    click FP "https://github.com/bsshreesha/physics_informed_neural_network/blob/main/Final_Project.ipynb"
    click ID "https://github.com/bsshreesha/physics_informed_neural_network/blob/main/Integral_Differential.ipynb"
    click IP "https://github.com/bsshreesha/physics_informed_neural_network/blob/main/Integral_PINN.ipynb"
    click IS "https://github.com/bsshreesha/physics_informed_neural_network/blob/main/Integral_Small.ipynb"
    click MR "https://github.com/bsshreesha/physics_informed_neural_network/blob/main/MHD_Realistic.ipynb"
    click RP "https://github.com/bsshreesha/physics_informed_neural_network/blob/main/Realistic_PDE_System.ipynb"
    click R1 "https://github.com/bsshreesha/physics_informed_neural_network/blob/main/Reinforcement.ipynb"
    click R3 "https://github.com/bsshreesha/physics_informed_neural_network/blob/main/Reinforcement_v3.ipynb"
    click SP "https://github.com/bsshreesha/physics_informed_neural_network/blob/main/Solving_PDE.ipynb"
    click TFH "https://github.com/bsshreesha/physics_informed_neural_network/blob/main/TF_PINN_Higher_Order_PDEs.ipynb"
    click README "https://github.com/bsshreesha/physics_informed_neural_network/blob/main/README.md"
    click EQ "https://github.com/bsshreesha/physics_informed_neural_network/blob/main/Equations.docx"

    %% Styles
    classDef notebook fill:#f9f,stroke:#333,stroke-width:1px;
    classDef data fill:#bbf,stroke:#333,stroke-width:1px;
    classDef compute fill:#bfb,stroke:#333,stroke-width:1px;
    classDef storage fill:#ffb,stroke:#333,stroke-width:1px,shape:cylinder;
    classDef io fill:#fb8,stroke:#333,stroke-width:1px;
    classDef doc fill:#ddd,stroke:#333,stroke-width:1px,stroke-dasharray: 5 5;
```
