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

Pipeline Detection Using Uncertainty-Driven Machine Learning

Tetens, Hendrik-Pieter (2021) Pipeline Detection Using Uncertainty-Driven Machine Learning. Master's, Carl von Ossietzky Universität.

[img] PDF


The pipeline detection model developed in (Dasenbrock et al., 2021) has proven to be capable of generalizing well from training data originating from Great Britain to Northern Germany. The thesis at hand used a similar model but applied it to a more differing and heterogeneous region compared to the training data in order to test its generalizability: Spain. Insufficient IoU scores showed that the model is not able to satisfyingly detect pipeline pathways in Spain. It will be of great importance when applying the model to new regions that it is also specifically trained for the new regions. While the model is permanently applied to new regions and consequently more training data is added, the need for new training data will diminish with time. This is because the knowledge of the model will become broader, and the differences between new regions and the regions already shown to the model will likely decrease. To speed up this process and to train more sample efficient, the potential of an active learning approach was investigated.

Item URL in elib:https://elib.dlr.de/148468/
Document Type:Thesis (Master's)
Title:Pipeline Detection Using Uncertainty-Driven Machine Learning
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Tetens, Hendrik-PieterUNSPECIFIEDhttps://orcid.org/0000-0002-1747-5497UNSPECIFIED
Date:10 December 2021
Refereed publication:No
Open Access:Yes
Number of Pages:100
Keywords:Pipeline Detection, Remote Sensing, Machine Learning
Institution:Carl von Ossietzky Universität
Department:Institut für Chemie und Biologie des Meeres
HGF - Research field:Energy
HGF - Program:Energy System Design
HGF - Program Themes:Energy System Transformation
DLR - Research area:Energy
DLR - Program:E SY - Energy System Technology and Analysis
DLR - Research theme (Project):E - Systems Analysis and Technology Assessment
Location: Oldenburg
Institutes and Institutions:Institute of Networked Energy Systems > Energy Systems Analysis
Deposited By: Pluta, Adam
Deposited On:24 Jan 2022 12:27
Last Modified:24 Jan 2022 12:27

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.