Code for thesis chapter "Suitability assessment of GNN-based metamodels for BGI allocation"
Wat erin zit
This software supports Chapter 5, Suitability assessment of GNN-based metamodels for BGI allocation, of the PhD thesis Metamodeling of Urban Drainage Systems with Graph Neural Networks (Delft University of Technology), by Alexander Garzón, Zoran Kapelan, Jeroen Langeveld and Riccardo Taormina. The chapter assesses whether graph neural network (GNN) metamodels are suitable surrogates of SWMM for optimising the allocation of Blue-Green Infrastructure (BGI) in an urban drainage system. Suitability is assessed along two dimensions, accuracy and ranking preservation, for the total combined sewer overflow (CSO) volume of the Loenen (NL) system under a climate-adjusted (2085) design storm with a 2-year return period. This repository contains the Python code (.py) of the workflow, chained by a Snakemake workflow (Snakefile). The scripts generate BGI proposals, run the SWMM and GNN simulations, calculate CSO volumes, rankings and metrics, and plot the figures. It also contains Jupyter notebooks (.ipynb), unit tests, the environment specification (pyproject.toml, uv.lock) and documentation (README.md).
Bestanden en diensten
- DataCite REST API (JSON)api.datacite.orgOpenen