TU Darmstadt / ULB / TUbiblio

Effective Risk Detection for Natural Gas Pipelines Using Low-Resolution Satellite Images

Ochs, Daniel ; Wiertz, Karsten ; Bußmann, Sebastian ; Kersting, Kristian ; Dhami, Devendra Singh (2024)
Effective Risk Detection for Natural Gas Pipelines Using Low-Resolution Satellite Images.
In: Remote Sensing, 2024, 16 (2)
doi: 10.26083/tuprints-00027169
Artikel, Zweitveröffentlichung, Verlagsversion

WarnungEs ist eine neuere Version dieses Eintrags verfügbar.

Kurzbeschreibung (Abstract)

Natural gas pipelines represent a critical infrastructure for most countries and thus their safety is of paramount importance. To report potential risks along pipelines, several steps are taken such as manual inspection and helicopter flights; however, these solutions are expensive and the flights are environmentally unfriendly. Deep learning has demonstrated considerable potential in handling a number of tasks in recent years as models rely on huge datasets to learn a specific task. With the increasing number of satellites orbiting the Earth, remote sensing data have become widely available, thus paving the way for automated pipeline monitoring via deep learning. This can result in effective risk detection, thereby reducing monitoring costs while being more precise and accurate. A major hindrance here is the low resolution of images obtained from the satellites, which makes it difficult to detect smaller changes. To this end, we propose to use transformers trained with low-resolution images in a change detection setting to detect pipeline risks. We collect PlanetScope satellite imagery (3 m resolution) that captures certain risks associated with the pipelines and present how we collected the data. Furthermore, we compare various state-of-the-art models, among which ChangeFormer, a transformer architecture for change detection, achieves the best performance with a 70% F1 score. As part of our evaluation, we discuss the specific performance requirements in pipeline monitoring and show how the model’s predictions can be shifted accordingly during training.

Typ des Eintrags: Artikel
Erschienen: 2024
Autor(en): Ochs, Daniel ; Wiertz, Karsten ; Bußmann, Sebastian ; Kersting, Kristian ; Dhami, Devendra Singh
Art des Eintrags: Zweitveröffentlichung
Titel: Effective Risk Detection for Natural Gas Pipelines Using Low-Resolution Satellite Images
Sprache: Englisch
Publikationsjahr: 13 Mai 2024
Ort: Darmstadt
Publikationsdatum der Erstveröffentlichung: 10 Januar 2024
Ort der Erstveröffentlichung: Basel
Verlag: MDPI
Titel der Zeitschrift, Zeitung oder Schriftenreihe: Remote Sensing
Jahrgang/Volume einer Zeitschrift: 16
(Heft-)Nummer: 2
Kollation: 13 Seiten
DOI: 10.26083/tuprints-00027169
URL / URN: https://tuprints.ulb.tu-darmstadt.de/27169
Zugehörige Links:
Herkunft: Zweitveröffentlichung DeepGreen
Kurzbeschreibung (Abstract):

Natural gas pipelines represent a critical infrastructure for most countries and thus their safety is of paramount importance. To report potential risks along pipelines, several steps are taken such as manual inspection and helicopter flights; however, these solutions are expensive and the flights are environmentally unfriendly. Deep learning has demonstrated considerable potential in handling a number of tasks in recent years as models rely on huge datasets to learn a specific task. With the increasing number of satellites orbiting the Earth, remote sensing data have become widely available, thus paving the way for automated pipeline monitoring via deep learning. This can result in effective risk detection, thereby reducing monitoring costs while being more precise and accurate. A major hindrance here is the low resolution of images obtained from the satellites, which makes it difficult to detect smaller changes. To this end, we propose to use transformers trained with low-resolution images in a change detection setting to detect pipeline risks. We collect PlanetScope satellite imagery (3 m resolution) that captures certain risks associated with the pipelines and present how we collected the data. Furthermore, we compare various state-of-the-art models, among which ChangeFormer, a transformer architecture for change detection, achieves the best performance with a 70% F1 score. As part of our evaluation, we discuss the specific performance requirements in pipeline monitoring and show how the model’s predictions can be shifted accordingly during training.

Freie Schlagworte: transformer, PlanetScope, pipeline monitoring, change detection
ID-Nummer: Artikel-ID: 266
Status: Verlagsversion
URN: urn:nbn:de:tuda-tuprints-271698
Sachgruppe der Dewey Dezimalklassifikatin (DDC): 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Künstliche Intelligenz und Maschinelles Lernen
Zentrale Einrichtungen
Zentrale Einrichtungen > Centre for Cognitive Science (CCS)
Zentrale Einrichtungen > hessian.AI - Hessisches Zentrum für Künstliche Intelligenz
Hinterlegungsdatum: 13 Mai 2024 12:39
Letzte Änderung: 16 Mai 2024 14:49
PPN:
Export:
Suche nach Titel in: TUfind oder in Google

Verfügbare Versionen dieses Eintrags

Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen