Published June 11, 2025 | Version 1.0.0
Other Restricted

An Automated Graph Theory Framework for Reconstructing Missing Data in Stormwater Networks

Authors/Creators

  • 1. Unit of Environmental Engineering, Department of Infrastructure Engineering, University of Innsbruck, Innsbruck, Austria

Contributors

  • 1. Unit of Environmental Engineering, Department of Infrastructure Engineering, University of Innsbruck, 6020, Innsbruck, Austria

Description

This repository contains MATLAB code implementing a graph-based framework to reconstruct missing data in Urban Stormwater Networks (USNs), as proposed in the paper:

“Filling data gaps in urban stormwater networks: An automated graph theory framework for data collection and reconstruction”  

Authors: Mohsen Hajibabaei, Sina Hesarkazzazi, Robert Sitzenfrei 

📘 Overview

The framework reconstructs missing:
- Pipe diameters
- Invert elevations (slopes)
It uses a series of modular steps based on graph theory, topology, and hydrodynamic modeling to infer missing data in stormwater networks.
---

📂 Folder Structure

 
├── Data_Reconstruction_Framework.m          % Main script to run the framework
├── README.md                                              % Project documentation
├── /Functions                                                   % Contains modular scripts and support files (e.g., run_uniformity_module.m)
├── /Network                                                     % Contains the SWMM input file (e.g., Toy-Example.inp)
├── /Result                                                        % Stores SWMM files after reconstruction
├── /SWMM                                                      % SWMM configuration
---

 ⚙️ Module Descriptions

Module         Purpose                         Description                                                                                                 Paper Section
Uniformity Diameter reconstruction Identifies uniform diameter patterns across pipes to infer missing values 2.2.1        
Hierarchy Diameter reconstruction Utilizes network hierarchy and a customized graph metric to assign diameters 2.2.2   
Completion Diameter reconstruction Completes remaining unknown diameters that earlier modules could not reconstruct 2.2.3        
Elevation Invert elevation reconstruction Estimates missing elevations (slopes) using topological slope consistency and minimum recommended slopes 2.2.4        
Hydrodynamic Functional validation Validates reconstructed networks using SWMM simulations to ensure hydraulic feasibility 2.2.5        
 

🧪 Example Network

The `/Network` folder contains `Toy-Example.inp`, a synthetic complete dataset used for testing.  
Missing data is introduced synthetically within the script using the array `r = [...]` (see Step 2 in the main script).
---

📈 Output

After running the main script (`Data_Reconstruction_Framework.m`), the framework outputs:
- Reconstructed diameters and invert elevations
- Confidence levels for each reconstructed value
- Performance metrics:
  - **MAPE**: Mean Absolute Percentage Error (diameters)
  - **MAE**: Mean Absolute Error (elevations)
- A `Final_results` cell array summarizing all outputs
---
 

📬 Contact

For questions, collaborations, or feedback, please contact:  
📧 mohsen.hajibabaei@uibk.ac.at

 

Files

Restricted

The record is publicly accessible, but files are restricted. Log in to check if you have access.

Additional details

Identifiers

Other
Filling data gaps in urban stormwater networks: An automated graph theory framework for data collection and reconstruction

Related works

References
10.1016/j.scs.2023.105114 (DOI)

Funding

FWF Austrian Science Fund
RESTORE P 36737

Dates

Submitted
2025-11-06

References

  • Hajibabaei, M., Hesarkazzazi, S.,Sitzenfrei, R., (Submitted). Filling data gaps in urban stormwater networks: An automated graph theory framework for data collection and reconstruction. Submitted in Water Res.