GeoAI for detection of solar photovoltaic installations in the Netherlands
National mapping agencies are responsible for creating and maintaining country wide geospatial datasets that are highly accurate and homogenous. The Netherlands’ Cadastre, Land Registry and Mapping Agency, in short, the Kadaster, has created a database of information related to solar installations,...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2021-12-01
|
Series: | Energy and AI |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666546821000604 |
id |
doaj-a88596d01e19481087beaab9e5252ef1 |
---|---|
record_format |
Article |
spelling |
doaj-a88596d01e19481087beaab9e5252ef12021-09-05T04:41:57ZengElsevierEnergy and AI2666-54682021-12-016100111GeoAI for detection of solar photovoltaic installations in the NetherlandsBala Bhavya Kausika0Diede Nijmeijer1Iris Reimerink2Peter Brouwer3Vera Liem4Copernicus Institute of Sustainable Development, Utrecht University, Princetonlaan 8A, Utrecht 3584 CB, the Netherland; The Kadaster, Koggelaan 59, Zwolle 8017 JN, the Netherland; Corresponding author at: The Kadaster, Koggelaan 59, Zwolle 8017 JN, the NetherlandThe Kadaster, Koggelaan 59, Zwolle 8017 JN, the NetherlandThe Kadaster, Koggelaan 59, Zwolle 8017 JN, the NetherlandThe Kadaster, Koggelaan 59, Zwolle 8017 JN, the NetherlandThe Kadaster, Koggelaan 59, Zwolle 8017 JN, the NetherlandNational mapping agencies are responsible for creating and maintaining country wide geospatial datasets that are highly accurate and homogenous. The Netherlands’ Cadastre, Land Registry and Mapping Agency, in short, the Kadaster, has created a database of information related to solar installations, using GeoAI. Deep Learning techniques were employed to detect small and medium-scale solar installations on buildings from very high-resolution aerial images for the whole of the Netherlands. The impact of data pre-processing and post-processing are addressed and evaluated. The process was automatized to deal with enormous data and the method was scaled-up nation-wide with the help of cloud solutions. In order to make this information visible, consistent and usable, we built-upon the existing TernausNet; a convolution neural network (CNN) architecture. Model metrics were evaluated after post-processing. The algorithm when used in combination with automated or custom post-processing improves the results. The precision and recall rates of the model for 3 different regions were evaluated and are on average about 0.93 and 0.92 respectively after implementation of post-processing. Use of custom post-processing improves the results by removing the false positives by at least 50%. The final results were compared with the existing national PV register. Overall, the results are not only useful for policy makers to assist them to take the necessary steps in achieving the energy transition goals but also serves as a register for infrastructure planning.http://www.sciencedirect.com/science/article/pii/S2666546821000604GeoAISolar installationsDeep learningTernausnetHigh-resolutionScaling-up |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Bala Bhavya Kausika Diede Nijmeijer Iris Reimerink Peter Brouwer Vera Liem |
spellingShingle |
Bala Bhavya Kausika Diede Nijmeijer Iris Reimerink Peter Brouwer Vera Liem GeoAI for detection of solar photovoltaic installations in the Netherlands Energy and AI GeoAI Solar installations Deep learning Ternausnet High-resolution Scaling-up |
author_facet |
Bala Bhavya Kausika Diede Nijmeijer Iris Reimerink Peter Brouwer Vera Liem |
author_sort |
Bala Bhavya Kausika |
title |
GeoAI for detection of solar photovoltaic installations in the Netherlands |
title_short |
GeoAI for detection of solar photovoltaic installations in the Netherlands |
title_full |
GeoAI for detection of solar photovoltaic installations in the Netherlands |
title_fullStr |
GeoAI for detection of solar photovoltaic installations in the Netherlands |
title_full_unstemmed |
GeoAI for detection of solar photovoltaic installations in the Netherlands |
title_sort |
geoai for detection of solar photovoltaic installations in the netherlands |
publisher |
Elsevier |
series |
Energy and AI |
issn |
2666-5468 |
publishDate |
2021-12-01 |
description |
National mapping agencies are responsible for creating and maintaining country wide geospatial datasets that are highly accurate and homogenous. The Netherlands’ Cadastre, Land Registry and Mapping Agency, in short, the Kadaster, has created a database of information related to solar installations, using GeoAI. Deep Learning techniques were employed to detect small and medium-scale solar installations on buildings from very high-resolution aerial images for the whole of the Netherlands. The impact of data pre-processing and post-processing are addressed and evaluated. The process was automatized to deal with enormous data and the method was scaled-up nation-wide with the help of cloud solutions. In order to make this information visible, consistent and usable, we built-upon the existing TernausNet; a convolution neural network (CNN) architecture. Model metrics were evaluated after post-processing. The algorithm when used in combination with automated or custom post-processing improves the results. The precision and recall rates of the model for 3 different regions were evaluated and are on average about 0.93 and 0.92 respectively after implementation of post-processing. Use of custom post-processing improves the results by removing the false positives by at least 50%. The final results were compared with the existing national PV register. Overall, the results are not only useful for policy makers to assist them to take the necessary steps in achieving the energy transition goals but also serves as a register for infrastructure planning. |
topic |
GeoAI Solar installations Deep learning Ternausnet High-resolution Scaling-up |
url |
http://www.sciencedirect.com/science/article/pii/S2666546821000604 |
work_keys_str_mv |
AT balabhavyakausika geoaifordetectionofsolarphotovoltaicinstallationsinthenetherlands AT diedenijmeijer geoaifordetectionofsolarphotovoltaicinstallationsinthenetherlands AT irisreimerink geoaifordetectionofsolarphotovoltaicinstallationsinthenetherlands AT peterbrouwer geoaifordetectionofsolarphotovoltaicinstallationsinthenetherlands AT veraliem geoaifordetectionofsolarphotovoltaicinstallationsinthenetherlands |
_version_ |
1717814479190753280 |