Gas Distribution Mapping With Radius-Based, Bi-directional Graph Neural Networks (RABI-GNN)

Nicolas P. Winkler, Patrick P. Neumann, Erik Schaffernicht, Achim J. Lilienthal

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Gas Distribution Mapping (GDM) is essential in monitoring hazardous environments, where uneven sampling and spatial sparsity of data present significant challenges. Traditional methods for GDM often fall short in accuracy and expressiveness. Modern learning-based approaches employing Convolutional Neural Networks (CNNs) require regular-sized input data, limiting their adaptability to irregular and sparse datasets typically encountered in GDM. This study addresses these shortcomings by showcasing Graph Neural Networks (GNNs) for learning-based GDM on irregular and spatially sparse sensor data. Our Radius-Based, Bi-Directionally connected GNN (RABI-GNN) was trained on a synthetic gas distribution dataset on which it outperforms our previous CNN-based model while overcoming its constraints. We demonstrate the flexibility of RABI-GNN by applying it to real-world data obtained in an industrial steel factory, highlighting promising opportunities for more accurate GDM models.

Original languageEnglish
Title of host publicationISOEN 2024 - International Symposium on Olfaction and Electronic Nose, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350348651
DOIs
StatePublished - 2024
Event2024 IEEE International Symposium on Olfaction and Electronic Nose, ISOEN 2024 - Grapevine, United States
Duration: 12 May 202415 May 2024

Publication series

NameISOEN 2024 - International Symposium on Olfaction and Electronic Nose, Proceedings

Conference

Conference2024 IEEE International Symposium on Olfaction and Electronic Nose, ISOEN 2024
Country/TerritoryUnited States
CityGrapevine
Period12/05/2415/05/24

Keywords

  • gas distribution mapping
  • graph neural networks
  • mobile robot olfaction
  • spatial interpolation

Fingerprint

Dive into the research topics of 'Gas Distribution Mapping With Radius-Based, Bi-directional Graph Neural Networks (RABI-GNN)'. Together they form a unique fingerprint.

Cite this