DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Detecting Pipeline Pathways in Landsat 5 Satellite Images With Deep Learning

Dasenbrock, Jan and Pluta, Adam and Zech, Matthias and Medjroubi, Wided (2021) Detecting Pipeline Pathways in Landsat 5 Satellite Images With Deep Learning. Energies. Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/en14185642. ISSN 1996-1073.

[img] PDF - Published version


Energy system modeling is essential in analyzing present and future system configurations motivated by the energy transition. Energy models need various input data sets at different scales, including detailed information about energy generation and transport infrastructure. However, accessing such data sets is not straightforward and often restricted, especially for energy infrastructure data. We present a detection model for the automatic recognition of pipeline pathways using a Convolutional Neural Network (CNN) to address this lack of energy infrastructure data sets. The model was trained with historical 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 trained our model with four different initial learning rates. The models trained with the different learning rates have been validated with 5-fold cross-validation using the Intersection over Union (IoU) metric. We show that our model can reliably identify pipeline pathways despite the comparably low resolution of the used satellite images. Further, we have successfully tested the model's capability in other geographic regions by deploying satellite images of the NEL pipeline in Northern Germany.

Item URL in elib:https://elib.dlr.de/144069/
Document Type:Article
Title:Detecting Pipeline Pathways in Landsat 5 Satellite Images With Deep Learning
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Dasenbrock, Janjan.dasenbrock (at) dlr.dehttps://orcid.org/0000-0003-1212-0117
Pluta, AdamAdam.Pluta (at) dlr.dehttps://orcid.org/0000-0002-3423-3246
Zech, MatthiasMatthias.Zech (at) dlr.dehttps://orcid.org/0000-0003-4420-5238
Medjroubi, WidedWided.Medjroubi (at) dlr.dehttps://orcid.org/0000-0002-2274-4209
Date:8 September 2021
Journal or Publication Title:Energies
Refereed publication:Yes
Open Access:Yes
Gold Open Access:Yes
In ISI Web of Science:Yes
DOI :10.3390/en14185642
Publisher:Multidisciplinary Digital Publishing Institute (MDPI)
Keywords:pipeline detection, CNN, Landsat 5, U-Net, gas transport network
HGF - Research field:Energy
HGF - Program:Energy System Design
HGF - Program Themes:Digitalization and System Technology
DLR - Research area:Energy
DLR - Program:E SY - Energy System Technology and Analysis
DLR - Research theme (Project):E - Energy System Technology
Location: Oldenburg
Institutes and Institutions:Institute of Networked Energy Systems > Energy Systems Analysis, OL
Deposited By: Dasenbrock, Jan
Deposited On:05 Oct 2021 15:51
Last Modified:28 Jan 2022 11:48

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.