Dasenbrock, Jan und Pluta, Adam und Zech, Matthias und Medjroubi, Wided (2021) Detecting Pipeline Pathways in Landsat 5 Satellite Images With Deep Learning. Energies. Multidisciplinary Digital Publishing Institute (MDPI). ISSN 1996-1073. (eingereichter Beitrag)
Es ist eine neuere Version dieses Eintrags verfügbar. |
PDF
- Nur DLR-intern zugänglich
- Preprintversion (eingereichte Entwurfsversion)
2MB |
Kurzfassung
We present a detection model for the automatic recognition of pipeline pathways using a Convolutional Neural Network (CNN). The model was trained with historic low-resolution satellite images of the construction phase of British gas transport pipelines, made with the Landsat 5 Thematic Mapper instrument. The satellite images have been automatically labeled with the help of high-resolution pipeline route data provided by the respective Transmission System Operator (TSO). We have used data augmentation on the training data and subsequently trained our model with 4 different initial learning rates. The model and the different learning rates have been validated with 5-fold cross-validation using the Intersection over Union (IoU) metric. We show that our model is capable of reliably identifying pipeline pathways despite the comparably low resolution of the used satellite images. Further, we have successfully tested the model's capability to generalize to other geographic regions with the deployment of satellite images of the NEL pipeline located in Northern Germany.
elib-URL des Eintrags: | https://elib.dlr.de/143108/ | ||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dokumentart: | Zeitschriftenbeitrag | ||||||||||||||||||||
Titel: | Detecting Pipeline Pathways in Landsat 5 Satellite Images With Deep Learning | ||||||||||||||||||||
Autoren: |
| ||||||||||||||||||||
Datum: | 2021 | ||||||||||||||||||||
Erschienen in: | Energies | ||||||||||||||||||||
Referierte Publikation: | Ja | ||||||||||||||||||||
Open Access: | Ja | ||||||||||||||||||||
Gold Open Access: | Ja | ||||||||||||||||||||
In SCOPUS: | Ja | ||||||||||||||||||||
In ISI Web of Science: | Ja | ||||||||||||||||||||
Verlag: | Multidisciplinary Digital Publishing Institute (MDPI) | ||||||||||||||||||||
ISSN: | 1996-1073 | ||||||||||||||||||||
Status: | eingereichter Beitrag | ||||||||||||||||||||
Stichwörter: | pipeline detection, CNN, Landsat 5, U-Net, gas transport network | ||||||||||||||||||||
HGF - Forschungsbereich: | Energie | ||||||||||||||||||||
HGF - Programm: | Energiesystemdesign | ||||||||||||||||||||
HGF - Programmthema: | Digitalisierung und Systemtechnologie | ||||||||||||||||||||
DLR - Schwerpunkt: | Energie | ||||||||||||||||||||
DLR - Forschungsgebiet: | E SY - Energiesystemtechnologie und -analyse | ||||||||||||||||||||
DLR - Teilgebiet (Projekt, Vorhaben): | E - Energiesystemtechnologie | ||||||||||||||||||||
Standort: | Oldenburg | ||||||||||||||||||||
Institute & Einrichtungen: | Institut für Vernetzte Energiesysteme > Energiesystemanalyse, OL | ||||||||||||||||||||
Hinterlegt von: | Dasenbrock, Jan | ||||||||||||||||||||
Hinterlegt am: | 19 Jul 2021 16:25 | ||||||||||||||||||||
Letzte Änderung: | 19 Jul 2021 16:25 |
Verfügbare Versionen dieses Eintrags
- Detecting Pipeline Pathways in Landsat 5 Satellite Images With Deep Learning. (deposited 19 Jul 2021 16:25) [Gegenwärtig angezeigt]
Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags