Predicting PV Areas in Aerial Images with Deep Learning

Matthias Zech, Joseph Ranalli

Research output: Chapter in Book/Report/Conference proceedingConference contribution

22 Scopus citations

Abstract

Data on the location of distributed photovoltaic installations are valuable to a variety of research activities. We have trained and applied a Fully Convolutional Neural Network to identify PV sites from aerial images of Oldenburg, Germany acquired from Google Maps. The architecture used was U-net, which was trained on a set of manually labelled images, and verified against a test dataset. The model is able to accurately estimate location and shape of PV plants in the north European town of Oldenburg. In addition, the model is able to estimate its own uncertainty, breaking the black box assumption of Deep Learning.

Original languageEnglish (US)
Title of host publication2020 47th IEEE Photovoltaic Specialists Conference, PVSC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages767-774
Number of pages8
ISBN (Electronic)9781728161150
DOIs
StatePublished - Jun 14 2020
Event47th IEEE Photovoltaic Specialists Conference, PVSC 2020 - Calgary, Canada
Duration: Jun 15 2020Aug 21 2020

Publication series

NameConference Record of the IEEE Photovoltaic Specialists Conference
Volume2020-June
ISSN (Print)0160-8371

Conference

Conference47th IEEE Photovoltaic Specialists Conference, PVSC 2020
Country/TerritoryCanada
CityCalgary
Period6/15/208/21/20

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Predicting PV Areas in Aerial Images with Deep Learning'. Together they form a unique fingerprint.

Cite this