# compphysvienna/n2p2 architecture

> Architecture diagram of the GitHub repository compphysvienna/n2p2, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-01-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/compphysvienna/n2p2
- Repository: https://github.com/compphysvienna/n2p2

## Overview

a. Data Flow:
- Input Data → Symmetry Functions → Neural Network → Predictions

b. Library Dependencies:
- Applications → libnnp
- Interfaces → libnnpif → libnnp
- Python Bindings → libnnp

a. Neural Network Core (within libnnp):
- Symmetry Functions
- Cutoff Functions
- Network Architecture
- Prediction Engine

b. Training System (within libnnptrain):
- Dataset Management
- Gradient Descent
- Kalman Filter
- Training Coordination

##### Important Details

a. Configuration Components:
- Settings Management
- Element Mapping
- Structure Handling

b. Key Features:
- High-dimensional Neural Network Potentials
- Symmetry Function Processing
- Multiple Training Methods

##### Implementation Notes
- MPI support for parallel processing
- File format compatibility
- Testing infrastructure

##### The modular nature of the system with clear separation between
- Core functionality (libnnp)
- Training capabilities (libnnptrain)
- Interface implementations (libnnpif)
- User-facing tools

##### The data flow from input structures through
- Symmetry function calculation
- Neural network processing
- Force and energy prediction

##### The integration capabilities with
- LAMMPS
- CabanaMD
- Python ecosystem

This design captures both the high-level architecture and the detailed components while maintaining clarity about the system's primary purpose as a neural network potential package for computational physics and chemistry.

## Diagram (Mermaid)

```mermaid
graph TB
    %% Style definitions
    classDef core fill:#3498db,stroke:#2980b9,color:white
    classDef interface fill:#2ecc71,stroke:#27ae60,color:white
    classDef application fill:#e67e22,stroke:#d35400,color:white
    classDef external fill:#f1c40f,stroke:#f39c12,color:black
    classDef dataflow fill:#95a5a6,stroke:#7f8c8d,color:white

    %% Core Libraries
    subgraph CoreLibraries
        libnnp["Core Neural Network (libnnp)"]:::core
        libnnptrain["Training Infrastructure (libnnptrain)"]:::core
        libnnpif["Interface Implementations (libnnpif)"]:::core
        pynnp["Python Bindings (pynnp)"]:::core

        %% Neural Network Core Components
        subgraph NNCore
            symFunctions["Symmetry Functions"]:::core
            cutoffFn["Cutoff Functions"]:::core
            nnArch["Network Architecture"]:::core
            predEngine["Prediction Engine"]:::core
        end

        %% Training System Components
        subgraph TrainingSystem
            datasetMgmt["Dataset Management"]:::core
            gradDescent["Gradient Descent"]:::core
            kalmanFilter["Kalman Filter"]:::core
            trainCoord["Training Coordination"]:::core
        end
    end

    %% Applications
    subgraph Applications
        nnpTrain["Training Tool (nnp-train)"]:::application
        nnpPredict["Prediction Tool (nnp-predict)"]:::application
        nnpDataset["Dataset Tool (nnp-dataset)"]:::application
        nnpConvert["Conversion Tool (nnp-convert)"]:::application
        nnpNorm["Normalization Tool (nnp-norm)"]:::application
    end

    %% Interfaces
    subgraph Interfaces
        lammps["LAMMPS Integration"]:::interface
        cabanaMD["CabanaMD Integration"]:::interface
    end

    %% External Systems
    subgraph ExternalSystems
        mdEngine["LAMMPS MD Engine"]:::external
        fileIO["File I/O Systems"]:::external
        pythonEnv["Python Environment"]:::external
    end

    %% Relationships
    libnnp --> NNCore
    libnnptrain --> TrainingSystem
    libnnpif --> lammps
    libnnpif --> cabanaMD
    pynnp --> pythonEnv
    
    Applications --> libnnp
    Applications --> libnnptrain
    
    lammps --> mdEngine
    cabanaMD --> mdEngine
    
    %% Data Flow
    fileIO --> datasetMgmt
    datasetMgmt --> symFunctions
    symFunctions --> nnArch
    nnArch --> predEngine

    %% Click Events
    click libnnp "https://github.com/CompPhysVienna/n2p2/tree/master/src/libnnp/"
    click libnnptrain "https://github.com/CompPhysVienna/n2p2/tree/master/src/libnnptrain/"
    click libnnpif "https://github.com/CompPhysVienna/n2p2/tree/master/src/libnnpif/"
    click pynnp "https://github.com/CompPhysVienna/n2p2/tree/master/src/pynnp/"
    click nnpTrain "https://github.com/CompPhysVienna/n2p2/blob/master/src/application/nnp-train.cpp"
    click nnpPredict "https://github.com/CompPhysVienna/n2p2/blob/master/src/application/nnp-predict.cpp"
    click nnpDataset "https://github.com/CompPhysVienna/n2p2/blob/master/src/application/nnp-dataset.cpp"
    click nnpConvert "https://github.com/CompPhysVienna/n2p2/blob/master/src/application/nnp-convert.cpp"
    click nnpNorm "https://github.com/CompPhysVienna/n2p2/blob/master/src/application/nnp-norm.cpp"
    click lammps "https://github.com/CompPhysVienna/n2p2/tree/master/src/interface/LAMMPS/src/ML-HDNNP/"
    click cabanaMD "https://github.com/CompPhysVienna/n2p2/tree/master/src/libnnpif/CabanaMD/"
    click nnArch "https://github.com/CompPhysVienna/n2p2/blob/master/src/libnnp/NeuralNetwork.cpp"
    click symFunctions "https://github.com/CompPhysVienna/n2p2/blob/master/src/libnnp/SymFnc.cpp"
    click trainCoord "https://github.com/CompPhysVienna/n2p2/blob/master/src/libnnptrain/Training.cpp"
    click gradDescent "https://github.com/CompPhysVienna/n2p2/blob/master/src/libnnptrain/GradientDescent.cpp"
    click kalmanFilter "https://github.com/CompPhysVienna/n2p2/blob/master/src/libnnptrain/KalmanFilter.cpp"
```
