https://github.com/bamresearch/srgdm
Super-Resolution for Gas Distribution Mapping
Science Score: 36.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
✓DOI references
Found 2 DOI reference(s) in README -
✓Academic publication links
Links to: sciencedirect.com -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (13.5%) to scientific vocabulary
Repository
Super-Resolution for Gas Distribution Mapping
Basic Info
- Host: GitHub
- Owner: BAMresearch
- License: mit
- Language: Jupyter Notebook
- Default Branch: master
- Size: 19.3 MB
Statistics
- Stars: 2
- Watchers: 3
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Super-Resolution for Gas Distribution Mapping
Introduction
This repository contains the code for our paper Super-resolution for Gas Distribution Mapping, in which we provide:
- Gas Distribution Decoder (GDD): A CNN-based method for spatiotemporal interpolation of spatially sparse sensor measurements.
- An extensive dataset of synthetic gas distribution maps based on actual airflow measurements. As generating ground truth maps is nearly impossible, this dataset provides a valuable resource for researchers in this field. It is available online, along with the code for our neural network model.
- A detailed comparative evaluation of GDD with state-of-the-art models on synthesized and real gas distribution data.
Usage
GDD and the implementations of the state-of-the-art models can be found in the folder "models". Pre-trained GDD models are saved as PyTorch *.pth files. Model parameters can be found in the associated *.yaml file.
Our datasets can be found in the folder "data". Each file contains the gas distribution maps in a Tensor object and can be loaded with torch.load(file). Additionally, you can use the specified PyTorch dataset and PyTorch Lightning datamodule to conveniently load samples. Their usage can be found in the different Jupyter notebook files (*.ipynb).
License
This software is released under the MIT license. See the LICENSE file for more details.
Acknowledgements
This research was funded by BAM, SAF€RA (project RASEM) and JSPS (KAKENHI 474 Grant Number 22H04952 and 22K12124).
- The GMRF implementation is heavily based on the MAPIRlab's implementation
- The Kernel DM+V implementation is heavily based on the Stephan Müller's implementation
Contact Information
Please contact us either via Github or via mro[at]bam.de
If you find this code useful, please cite our paper:
@article{winkler2024super,
title = {Super-resolution for Gas Distribution Mapping},
journal = {Sensors and Actuators B: Chemical},
volume = {419},
pages = {136267},
year = {2024},
issn = {0925-4005},
doi = {https://doi.org/10.1016/j.snb.2024.136267},
url = {https://www.sciencedirect.com/science/article/pii/S0925400524009973},
author = {Nicolas P. Winkler and Oleksandr Kotlyar and Erik Schaffernicht and Haruka Matsukura and Hiroshi Ishida and Patrick P. Neumann and Achim J. Lilienthal},
}
Owner
- Name: Bundesanstalt für Materialforschung und -prüfung
- Login: BAMresearch
- Kind: organization
- Email: oss@bam.de
- Location: Berlin/Germany
- Website: www.bam.de
- Repositories: 36
- Profile: https://github.com/BAMresearch
German Federal scientific research institute for materials testing and research
GitHub Events
Total
- Watch event: 4
- Fork event: 2
Last Year
- Watch event: 4
- Fork event: 2