cff-version: 1.2.0
abstract: "<p>Repository of the code for the GNN based metamodel of SWMM. This code is linked to the paper "Transferable and Data Efficient Metamodeling of Storm Water System Nodal Depths Using Auto-Regressive Graph Neural Networks" by Alexander Garzón, Zoran Kapelan, Jeroen Langeveld, and Riccardo Taormina.</p><p></p><p>This repository contains the code for developing machine learning metamodels of SWMM.</p><p>In brief, this code allows to create a dataset from SWMM simulations, train a machine learning model, and evaluate the model. The code is designed to work with SWMM simulations of storm water systems. The code is based on PyTorch and PyTorch Geometric.</p><p></p><p>This work is supported by the TU Delft AI Labs programme.</p><p>This repository was supported by the Digital Competence Centre, Delft University of Technology.</p>"
authors:
  - family-names: Garzón
    given-names: Alexander
    orcid: "https://orcid.org/0000-0002-0012-7293"
  - family-names: Kapelan
    given-names: Zoran 
    orcid: "https://orcid.org/0000-0002-0934-4470"
  - family-names: Langeveld
    given-names: Jeroen
    orcid: "https://orcid.org/0000-0002-0170-6721"
  - family-names: Taormina
    given-names: Riccardo
    orcid: "https://orcid.org/0000-0002-1550-504X"
title: "SWMM GNN metamodel – Code for paper: Transferable and Data Efficient Metamodeling of Storm Water System Nodal Depths Using Auto-Regressive Graph Neural Networks"
keywords:
version: 1
identifiers:
  - type: doi
    value: 10.4121/989a0d3d-3b4d-47c7-8677-31c5975f9dec.v1
license: MIT
date-released: 2024-09-12