Monitoring spatial sustainable development: Semi-automated analysis of satellite and aerial images for energy transition and sustainability indicators

R. L. Curier, T. J. A. De Jong, Katharina Strauch, Katharina Cramer, Natalie Rosenski, Clara Schartner, M. Debusschere, Hannah Ziemons, Deniz Iren, Stefano Bromuri

Research output: Book/ReportTechnical report

Abstract

This document provides the reader with an overview of the various datasets which will be used throughout the project. The collection of satellite and aerial images as well as auxiliary information such as the location of buildings and roofs which is required to train, test and validate the machine learning algorithm that is being developed

Solar panels are installed by a large and growing number of households due to the convenience of having cheap and renewable energy to power house appliances. In contrast to other energy sources solar installations are distributed very decentralized and spread over hundred-thousands of locations. On a global level more than 25% of solar photovoltaic (PV) installations were decentralized. The effect of the quick energy transition from a carbon based economy to a green economy is though still very difficult to quantify. As a matter of fact the quick adoption of solar panels by households is difficult to track, with local registries that miss a large number of the newly built solar panels. This makes the task of assessing the impact of renewable energies an impossible task. Although models of the output of a region exist, they are often black box estimations. This project's aim is twofold: First automate the process to extract the location of solar panels from aerial or satellite images and second, produce a map of solar panels along with statistics on the number of solar panels. Further, this project takes place in a wider framework which investigates how official statistics can benefit from new digital data sources. At project completion, a method for detecting solar panels from aerial images via machine learning will be developed and the methodology initially developed for BE, DE and NL will be standardized for application to other EU countries. In practice, machine learning techniques are used to identify solar panels in satellite and aerial images for the province of Limburg (NL), Flanders (BE) and North Rhine-Westphalia (DE).
Original languageEnglish
Commissioning bodyEurostat
Number of pages24
Publication statusPublished - 26 Sep 2018

Publication series

NamearXiv
ISSN (Print)2331-8422

Fingerprint

Sustainable development
Satellites
Antennas
Learning systems
Monitoring
Statistics
Roofs
Learning algorithms
Carbon

Keywords

  • cs.CV
  • cs.LG
  • 00-02

Cite this

Curier, R. L. ; De Jong, T. J. A. ; Strauch, Katharina ; Cramer, Katharina ; Rosenski, Natalie ; Schartner, Clara ; Debusschere, M. ; Ziemons, Hannah ; Iren, Deniz ; Bromuri, Stefano. / Monitoring spatial sustainable development : Semi-automated analysis of satellite and aerial images for energy transition and sustainability indicators. 2018. 24 p. (arXiv ).
@book{a59132f7289542c9ad3e4596de7bb7ca,
title = "Monitoring spatial sustainable development: Semi-automated analysis of satellite and aerial images for energy transition and sustainability indicators",
abstract = "This document provides the reader with an overview of the various datasets which will be used throughout the project. The collection of satellite and aerial images as well as auxiliary information such as the location of buildings and roofs which is required to train, test and validate the machine learning algorithm that is being developedSolar panels are installed by a large and growing number of households due to the convenience of having cheap and renewable energy to power house appliances. In contrast to other energy sources solar installations are distributed very decentralized and spread over hundred-thousands of locations. On a global level more than 25{\%} of solar photovoltaic (PV) installations were decentralized. The effect of the quick energy transition from a carbon based economy to a green economy is though still very difficult to quantify. As a matter of fact the quick adoption of solar panels by households is difficult to track, with local registries that miss a large number of the newly built solar panels. This makes the task of assessing the impact of renewable energies an impossible task. Although models of the output of a region exist, they are often black box estimations. This project's aim is twofold: First automate the process to extract the location of solar panels from aerial or satellite images and second, produce a map of solar panels along with statistics on the number of solar panels. Further, this project takes place in a wider framework which investigates how official statistics can benefit from new digital data sources. At project completion, a method for detecting solar panels from aerial images via machine learning will be developed and the methodology initially developed for BE, DE and NL will be standardized for application to other EU countries. In practice, machine learning techniques are used to identify solar panels in satellite and aerial images for the province of Limburg (NL), Flanders (BE) and North Rhine-Westphalia (DE).",
keywords = "cs.CV, cs.LG, 00-02",
author = "Curier, {R. L.} and {De Jong}, {T. J. A.} and Katharina Strauch and Katharina Cramer and Natalie Rosenski and Clara Schartner and M. Debusschere and Hannah Ziemons and Deniz Iren and Stefano Bromuri",
note = "This document provides the reader with an overview of the various datasets which will be used throughout the project. The collection of satellite and aerial images as well as auxiliary information such as the location of buildings and roofs which is required to train, test and validate the machine learning algorithm that is being developed",
year = "2018",
month = "9",
day = "26",
language = "English",
series = "arXiv",

}

Curier, RL, De Jong, TJA, Strauch, K, Cramer, K, Rosenski, N, Schartner, C, Debusschere, M, Ziemons, H, Iren, D & Bromuri, S 2018, Monitoring spatial sustainable development: Semi-automated analysis of satellite and aerial images for energy transition and sustainability indicators. arXiv .

Monitoring spatial sustainable development : Semi-automated analysis of satellite and aerial images for energy transition and sustainability indicators. / Curier, R. L.; De Jong, T. J. A. ; Strauch, Katharina; Cramer, Katharina; Rosenski, Natalie; Schartner, Clara; Debusschere, M.; Ziemons, Hannah; Iren, Deniz; Bromuri, Stefano.

2018. 24 p. (arXiv ).

Research output: Book/ReportTechnical report

TY - BOOK

T1 - Monitoring spatial sustainable development

T2 - Semi-automated analysis of satellite and aerial images for energy transition and sustainability indicators

AU - Curier, R. L.

AU - De Jong, T. J. A.

AU - Strauch, Katharina

AU - Cramer, Katharina

AU - Rosenski, Natalie

AU - Schartner, Clara

AU - Debusschere, M.

AU - Ziemons, Hannah

AU - Iren, Deniz

AU - Bromuri, Stefano

N1 - This document provides the reader with an overview of the various datasets which will be used throughout the project. The collection of satellite and aerial images as well as auxiliary information such as the location of buildings and roofs which is required to train, test and validate the machine learning algorithm that is being developed

PY - 2018/9/26

Y1 - 2018/9/26

N2 - This document provides the reader with an overview of the various datasets which will be used throughout the project. The collection of satellite and aerial images as well as auxiliary information such as the location of buildings and roofs which is required to train, test and validate the machine learning algorithm that is being developedSolar panels are installed by a large and growing number of households due to the convenience of having cheap and renewable energy to power house appliances. In contrast to other energy sources solar installations are distributed very decentralized and spread over hundred-thousands of locations. On a global level more than 25% of solar photovoltaic (PV) installations were decentralized. The effect of the quick energy transition from a carbon based economy to a green economy is though still very difficult to quantify. As a matter of fact the quick adoption of solar panels by households is difficult to track, with local registries that miss a large number of the newly built solar panels. This makes the task of assessing the impact of renewable energies an impossible task. Although models of the output of a region exist, they are often black box estimations. This project's aim is twofold: First automate the process to extract the location of solar panels from aerial or satellite images and second, produce a map of solar panels along with statistics on the number of solar panels. Further, this project takes place in a wider framework which investigates how official statistics can benefit from new digital data sources. At project completion, a method for detecting solar panels from aerial images via machine learning will be developed and the methodology initially developed for BE, DE and NL will be standardized for application to other EU countries. In practice, machine learning techniques are used to identify solar panels in satellite and aerial images for the province of Limburg (NL), Flanders (BE) and North Rhine-Westphalia (DE).

AB - This document provides the reader with an overview of the various datasets which will be used throughout the project. The collection of satellite and aerial images as well as auxiliary information such as the location of buildings and roofs which is required to train, test and validate the machine learning algorithm that is being developedSolar panels are installed by a large and growing number of households due to the convenience of having cheap and renewable energy to power house appliances. In contrast to other energy sources solar installations are distributed very decentralized and spread over hundred-thousands of locations. On a global level more than 25% of solar photovoltaic (PV) installations were decentralized. The effect of the quick energy transition from a carbon based economy to a green economy is though still very difficult to quantify. As a matter of fact the quick adoption of solar panels by households is difficult to track, with local registries that miss a large number of the newly built solar panels. This makes the task of assessing the impact of renewable energies an impossible task. Although models of the output of a region exist, they are often black box estimations. This project's aim is twofold: First automate the process to extract the location of solar panels from aerial or satellite images and second, produce a map of solar panels along with statistics on the number of solar panels. Further, this project takes place in a wider framework which investigates how official statistics can benefit from new digital data sources. At project completion, a method for detecting solar panels from aerial images via machine learning will be developed and the methodology initially developed for BE, DE and NL will be standardized for application to other EU countries. In practice, machine learning techniques are used to identify solar panels in satellite and aerial images for the province of Limburg (NL), Flanders (BE) and North Rhine-Westphalia (DE).

KW - cs.CV

KW - cs.LG

KW - 00-02

M3 - Technical report

T3 - arXiv

BT - Monitoring spatial sustainable development

ER -