G. Agugiaro
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
11 records found
1
Semantic urban river space delineation and typology
Defining and analyzing the space around the urban river in the Netherlands
The urban river space is the area in the city surrounding a river, distinguishing itself from other parts of the city by this relationship with the water. Urban river spaces around the world are increasingly under development and being regenerated. Urban planning solutions necessitate a comprehensive overview of this space, their boundaries and their characteristics. However, the concept of the urban river space is ambiguously defined, with varying definitions across studies. This thesis addresses the need for a standardized approach through semantic urban river space delineation to facilitate cross-case analysis. Three delineation methods are proposed and applied to urban areas in the Netherlands: the first building line based on visible building nodes, the visible space derived from viewshed analysis, and the floodable area, based on 100-year flood depth data. As urban river spaces are often represented as cross-sectional segments in research, this segment is used as unit to develop a typology of urban river spaces in the Netherlands. Properties of the segment, such as elevation, landuse, vegetation, flood risk, and visibility are quantified and used as input for the k-means clustering algorithm. 10 clusters are derived, each representing a semantic type of river space, resulting in a data-driven typology that enhances the understanding of urban river spaces in the Netherlands.
...
...
The urban river space is the area in the city surrounding a river, distinguishing itself from other parts of the city by this relationship with the water. Urban river spaces around the world are increasingly under development and being regenerated. Urban planning solutions necessitate a comprehensive overview of this space, their boundaries and their characteristics. However, the concept of the urban river space is ambiguously defined, with varying definitions across studies. This thesis addresses the need for a standardized approach through semantic urban river space delineation to facilitate cross-case analysis. Three delineation methods are proposed and applied to urban areas in the Netherlands: the first building line based on visible building nodes, the visible space derived from viewshed analysis, and the floodable area, based on 100-year flood depth data. As urban river spaces are often represented as cross-sectional segments in research, this segment is used as unit to develop a typology of urban river spaces in the Netherlands. Properties of the segment, such as elevation, landuse, vegetation, flood risk, and visibility are quantified and used as input for the k-means clustering algorithm. 10 clusters are derived, each representing a semantic type of river space, resulting in a data-driven typology that enhances the understanding of urban river spaces in the Netherlands.
Implementing a Dutch building energy simulation tool
Energy model testing for Rijssen-Holten
Lowering energy demand in buildings is high on the political agenda considering household energy consumption accounts for 22% of the total final energy usage in the Netherlands. Tools that can run these types of simulations for an entire city are required for effective policy design to lower energy consumption within the built environment. This thesis explores how to build such a tool that allows for space heating demand to be computed that follows the NTA 8800 norm. Therefore, the main research question is: “To what extent can a heat demand model be developed that adapts and implements the NTA 8800 to be coupled with CityGML-based semantic 3D city models?”. The thesis uses a mixed-method research approach of qualitative concept mapping and quantitative modelling to build a space heating demand model for urban analysis. The final product is a Python-based model with database interactions, compatible with CityGML-based semantic 3D city models, following the NTA 8800 computation methods.
Initial testing on two buildings highlighted areas for model development, including the underestimating of ventilation losses and the omission of windows and doors in transmission estimates. Improved window quality could result in significant energy savings, according to the solar gain analysis. The model’s capacity to mimic anticipated trends in space heating demand was verified using benchmark data, although it deviated from previous consumption patterns, indicating the need for additional research. The model was tested for Rijssen-Holten and produced rapid results within 5 minutes. Despite limitations due to data availability and model assumptions, the thesis model underscores the utility of Geomatics in urban energy management and the results can help design energy policy design for sustainable development. ...
Initial testing on two buildings highlighted areas for model development, including the underestimating of ventilation losses and the omission of windows and doors in transmission estimates. Improved window quality could result in significant energy savings, according to the solar gain analysis. The model’s capacity to mimic anticipated trends in space heating demand was verified using benchmark data, although it deviated from previous consumption patterns, indicating the need for additional research. The model was tested for Rijssen-Holten and produced rapid results within 5 minutes. Despite limitations due to data availability and model assumptions, the thesis model underscores the utility of Geomatics in urban energy management and the results can help design energy policy design for sustainable development. ...
Lowering energy demand in buildings is high on the political agenda considering household energy consumption accounts for 22% of the total final energy usage in the Netherlands. Tools that can run these types of simulations for an entire city are required for effective policy design to lower energy consumption within the built environment. This thesis explores how to build such a tool that allows for space heating demand to be computed that follows the NTA 8800 norm. Therefore, the main research question is: “To what extent can a heat demand model be developed that adapts and implements the NTA 8800 to be coupled with CityGML-based semantic 3D city models?”. The thesis uses a mixed-method research approach of qualitative concept mapping and quantitative modelling to build a space heating demand model for urban analysis. The final product is a Python-based model with database interactions, compatible with CityGML-based semantic 3D city models, following the NTA 8800 computation methods.
Initial testing on two buildings highlighted areas for model development, including the underestimating of ventilation losses and the omission of windows and doors in transmission estimates. Improved window quality could result in significant energy savings, according to the solar gain analysis. The model’s capacity to mimic anticipated trends in space heating demand was verified using benchmark data, although it deviated from previous consumption patterns, indicating the need for additional research. The model was tested for Rijssen-Holten and produced rapid results within 5 minutes. Despite limitations due to data availability and model assumptions, the thesis model underscores the utility of Geomatics in urban energy management and the results can help design energy policy design for sustainable development.
Initial testing on two buildings highlighted areas for model development, including the underestimating of ventilation losses and the omission of windows and doors in transmission estimates. Improved window quality could result in significant energy savings, according to the solar gain analysis. The model’s capacity to mimic anticipated trends in space heating demand was verified using benchmark data, although it deviated from previous consumption patterns, indicating the need for additional research. The model was tested for Rijssen-Holten and produced rapid results within 5 minutes. Despite limitations due to data availability and model assumptions, the thesis model underscores the utility of Geomatics in urban energy management and the results can help design energy policy design for sustainable development.
Urban Energy Modeling (UEM) provides a comprehensive approach to urban planning, helping to create sustainable, resilient, and energy-efficient cities that meet the needs of current and future generations. The key inputs for UEM methodologies and tools are the geometry of the building stock and its thermophysical properties. In the Netherlands, the 3DBAG provides the building stock geometry, while the thermophysical properties can be approximated using energy consumption estimates specific to each residential building type from the IEE project TABULA. However, a challenge arises as open data on residential building types at a national level is currently not readily available, necessitating the development of a method to infer this information from other accessible data sources.
In response to similar successful studies, this thesis also focuses on utilising machine learning to address this challenge. Support Vector Machine (SVM) and Random Forest (RF) algorithms were tested and compared. These algorithms were trained using data on the residential building types obtained from the Rijssen-Holten energy testbed and EP-online, with the latter requiring preprocessing to obtain the relevant information. Additionally, 25 features derived from cadastral data and building geometry underwent a selection process to identify the essential features for accurate classification of building types.
Eight models were trained and applied across eight case studies, containing subsets of the Netherlands representative for the whole country. The combined results were analyzed to determine necessary features, required data, and the most suitable machine learning approach for this research.
The results revealed that features such as adjacency to other buildings, width, and volume in LoD2.2 correlated the most with Dutch residential building types. However, critical features like the number of storeys, the presence of an open porch, or galleries were not available as open data, even though they directly relate to the definition of certain residential building types.
This thesis presented successful models, demonstrating accuracies between 61.1% and 98.5%, and balanced accuracies ranging from 51.6% to 94.2%. Importantly, performance differences were observed in various case studies, particularly in distinguishing accuracy between multi-dwelling and single-dwelling houses. Despite the longer tuning and training time, the suitability and accuracy of the RF models generally outperformed the SVM models.
These findings highlights the capacity of machine learning to attain robust classification outcomes for the Dutch building stock when trained on representative datasets. Nevertheless, it is emphasized that the accuracy of results is contingent on data quality, and difficulties may arise in scenarios involving intricate buildings with multiple components and ambiguous classification rules. ...
In response to similar successful studies, this thesis also focuses on utilising machine learning to address this challenge. Support Vector Machine (SVM) and Random Forest (RF) algorithms were tested and compared. These algorithms were trained using data on the residential building types obtained from the Rijssen-Holten energy testbed and EP-online, with the latter requiring preprocessing to obtain the relevant information. Additionally, 25 features derived from cadastral data and building geometry underwent a selection process to identify the essential features for accurate classification of building types.
Eight models were trained and applied across eight case studies, containing subsets of the Netherlands representative for the whole country. The combined results were analyzed to determine necessary features, required data, and the most suitable machine learning approach for this research.
The results revealed that features such as adjacency to other buildings, width, and volume in LoD2.2 correlated the most with Dutch residential building types. However, critical features like the number of storeys, the presence of an open porch, or galleries were not available as open data, even though they directly relate to the definition of certain residential building types.
This thesis presented successful models, demonstrating accuracies between 61.1% and 98.5%, and balanced accuracies ranging from 51.6% to 94.2%. Importantly, performance differences were observed in various case studies, particularly in distinguishing accuracy between multi-dwelling and single-dwelling houses. Despite the longer tuning and training time, the suitability and accuracy of the RF models generally outperformed the SVM models.
These findings highlights the capacity of machine learning to attain robust classification outcomes for the Dutch building stock when trained on representative datasets. Nevertheless, it is emphasized that the accuracy of results is contingent on data quality, and difficulties may arise in scenarios involving intricate buildings with multiple components and ambiguous classification rules. ...
Urban Energy Modeling (UEM) provides a comprehensive approach to urban planning, helping to create sustainable, resilient, and energy-efficient cities that meet the needs of current and future generations. The key inputs for UEM methodologies and tools are the geometry of the building stock and its thermophysical properties. In the Netherlands, the 3DBAG provides the building stock geometry, while the thermophysical properties can be approximated using energy consumption estimates specific to each residential building type from the IEE project TABULA. However, a challenge arises as open data on residential building types at a national level is currently not readily available, necessitating the development of a method to infer this information from other accessible data sources.
In response to similar successful studies, this thesis also focuses on utilising machine learning to address this challenge. Support Vector Machine (SVM) and Random Forest (RF) algorithms were tested and compared. These algorithms were trained using data on the residential building types obtained from the Rijssen-Holten energy testbed and EP-online, with the latter requiring preprocessing to obtain the relevant information. Additionally, 25 features derived from cadastral data and building geometry underwent a selection process to identify the essential features for accurate classification of building types.
Eight models were trained and applied across eight case studies, containing subsets of the Netherlands representative for the whole country. The combined results were analyzed to determine necessary features, required data, and the most suitable machine learning approach for this research.
The results revealed that features such as adjacency to other buildings, width, and volume in LoD2.2 correlated the most with Dutch residential building types. However, critical features like the number of storeys, the presence of an open porch, or galleries were not available as open data, even though they directly relate to the definition of certain residential building types.
This thesis presented successful models, demonstrating accuracies between 61.1% and 98.5%, and balanced accuracies ranging from 51.6% to 94.2%. Importantly, performance differences were observed in various case studies, particularly in distinguishing accuracy between multi-dwelling and single-dwelling houses. Despite the longer tuning and training time, the suitability and accuracy of the RF models generally outperformed the SVM models.
These findings highlights the capacity of machine learning to attain robust classification outcomes for the Dutch building stock when trained on representative datasets. Nevertheless, it is emphasized that the accuracy of results is contingent on data quality, and difficulties may arise in scenarios involving intricate buildings with multiple components and ambiguous classification rules.
In response to similar successful studies, this thesis also focuses on utilising machine learning to address this challenge. Support Vector Machine (SVM) and Random Forest (RF) algorithms were tested and compared. These algorithms were trained using data on the residential building types obtained from the Rijssen-Holten energy testbed and EP-online, with the latter requiring preprocessing to obtain the relevant information. Additionally, 25 features derived from cadastral data and building geometry underwent a selection process to identify the essential features for accurate classification of building types.
Eight models were trained and applied across eight case studies, containing subsets of the Netherlands representative for the whole country. The combined results were analyzed to determine necessary features, required data, and the most suitable machine learning approach for this research.
The results revealed that features such as adjacency to other buildings, width, and volume in LoD2.2 correlated the most with Dutch residential building types. However, critical features like the number of storeys, the presence of an open porch, or galleries were not available as open data, even though they directly relate to the definition of certain residential building types.
This thesis presented successful models, demonstrating accuracies between 61.1% and 98.5%, and balanced accuracies ranging from 51.6% to 94.2%. Importantly, performance differences were observed in various case studies, particularly in distinguishing accuracy between multi-dwelling and single-dwelling houses. Despite the longer tuning and training time, the suitability and accuracy of the RF models generally outperformed the SVM models.
These findings highlights the capacity of machine learning to attain robust classification outcomes for the Dutch building stock when trained on representative datasets. Nevertheless, it is emphasized that the accuracy of results is contingent on data quality, and difficulties may arise in scenarios involving intricate buildings with multiple components and ambiguous classification rules.
Geometric algorithms are usually designed based on the assumption of using arbitraryprecision representations. However, in modern computer systems floating-point arithmetic and finite-precision approximation are often used as implementing exact computations would require large computational resources and would be rather slow in the applications. Snap rounding (SR) is a widely used technique to transform representations of infinite precision into fixed-precision formats. It slightly modifies the original geometry of the input in order
to obtain a better organized geometric object arrangement and avoid the issues caused by applying floating-point arithmetic in geometric algorithms. The existing implementations of SR primarily focus on processing sets of line segments, while in practice polygons are of great significance as well yet has not received adequate attention so far. In this thesis, a new method is proposed to perform SR on 2-dimensional polygons. Firstly the input polygons are embedded into a triangulation. Subsequently, the triangulation is tagged with the ID information of polygons and the polygon boundaries are extracted and
stored in a container. The boundaries and the triangulation are then dynamically processed according to the identification of close polygonal vertices and close vertex and boundaries (under a predefined tolerance). After having snapped all the close elements the rounded polygons will be reconstructed from the processed boundaries. The testing results show the proposed method is capable of eliminating small gaps between elements (i.e. vertices and
boundaries) and is adaptable to various inputs. The topological and geometrical properties of polygons are preserved as much as possible. Finally, an overview of the limitations is provided, along with potential directions for future research. ...
to obtain a better organized geometric object arrangement and avoid the issues caused by applying floating-point arithmetic in geometric algorithms. The existing implementations of SR primarily focus on processing sets of line segments, while in practice polygons are of great significance as well yet has not received adequate attention so far. In this thesis, a new method is proposed to perform SR on 2-dimensional polygons. Firstly the input polygons are embedded into a triangulation. Subsequently, the triangulation is tagged with the ID information of polygons and the polygon boundaries are extracted and
stored in a container. The boundaries and the triangulation are then dynamically processed according to the identification of close polygonal vertices and close vertex and boundaries (under a predefined tolerance). After having snapped all the close elements the rounded polygons will be reconstructed from the processed boundaries. The testing results show the proposed method is capable of eliminating small gaps between elements (i.e. vertices and
boundaries) and is adaptable to various inputs. The topological and geometrical properties of polygons are preserved as much as possible. Finally, an overview of the limitations is provided, along with potential directions for future research. ...
Geometric algorithms are usually designed based on the assumption of using arbitraryprecision representations. However, in modern computer systems floating-point arithmetic and finite-precision approximation are often used as implementing exact computations would require large computational resources and would be rather slow in the applications. Snap rounding (SR) is a widely used technique to transform representations of infinite precision into fixed-precision formats. It slightly modifies the original geometry of the input in order
to obtain a better organized geometric object arrangement and avoid the issues caused by applying floating-point arithmetic in geometric algorithms. The existing implementations of SR primarily focus on processing sets of line segments, while in practice polygons are of great significance as well yet has not received adequate attention so far. In this thesis, a new method is proposed to perform SR on 2-dimensional polygons. Firstly the input polygons are embedded into a triangulation. Subsequently, the triangulation is tagged with the ID information of polygons and the polygon boundaries are extracted and
stored in a container. The boundaries and the triangulation are then dynamically processed according to the identification of close polygonal vertices and close vertex and boundaries (under a predefined tolerance). After having snapped all the close elements the rounded polygons will be reconstructed from the processed boundaries. The testing results show the proposed method is capable of eliminating small gaps between elements (i.e. vertices and
boundaries) and is adaptable to various inputs. The topological and geometrical properties of polygons are preserved as much as possible. Finally, an overview of the limitations is provided, along with potential directions for future research.
to obtain a better organized geometric object arrangement and avoid the issues caused by applying floating-point arithmetic in geometric algorithms. The existing implementations of SR primarily focus on processing sets of line segments, while in practice polygons are of great significance as well yet has not received adequate attention so far. In this thesis, a new method is proposed to perform SR on 2-dimensional polygons. Firstly the input polygons are embedded into a triangulation. Subsequently, the triangulation is tagged with the ID information of polygons and the polygon boundaries are extracted and
stored in a container. The boundaries and the triangulation are then dynamically processed according to the identification of close polygonal vertices and close vertex and boundaries (under a predefined tolerance). After having snapped all the close elements the rounded polygons will be reconstructed from the processed boundaries. The testing results show the proposed method is capable of eliminating small gaps between elements (i.e. vertices and
boundaries) and is adaptable to various inputs. The topological and geometrical properties of polygons are preserved as much as possible. Finally, an overview of the limitations is provided, along with potential directions for future research.
Master thesis
(2022)
-
Konstantinos Pantelios, Camilo León Sánchez, Giorgio Agugiaro, Claus Nagel, Zhihang Yao, Martijn Meijers
Today, in the urban planning, energy modelling and other fields, semantic 3D city models are used in various applications like visualization, data exploration, analysis and more. As a result, standard data practices needed to be set in order to facilitate the storage and exchange of these city models. For this purpose, the Open Geospatial Consortium ( OGC ) adopted CityGML as an international standard for effective use of 3D city models. Generally, the models are encoded in Extensible Markup Language ( XML ) files, however, other file encodings can also be used like JavaScript Object Notation ( JSON ) files with CityJSON. Moreover, CityGML can also be adapted for a database encoding like the 3D City Database ( 3DCityDB ), on which this thesis is based upon. The benefit of using a database encoding is that databases are built to handle and organize large amount of data, which 3D city models usually consist of. The 3DCityDB is an open source project developed for PostgreSQL and Oracle databases. It is supported by other software in the 3DCityDB suite that facilitate its use in different applications. The 3DCityDB tries to simplify the complexity of CityGML, however, its approach remains difficult for users to access data directly without technical knowledge of databases, Structured Query Language ( SQL ), CityGML and/or 3DCityDB structure. Derived frm thios limitation, the primary objective of this research is to develop an approach that could simplify user interaction with the 3DCityDB from within a Q Geographical Information System ( QGIS ) environment. To achieve this, ”3DCityDB-Loader”, a QGIS plugin, is developed to handle complex server operations in the background, whilst providing a user-friendly workspace environment. The complete functionality of the plugin is segmented into client and server-side parts. This thesis focuses on the client-side development but both parts were jointly developed in a common iterative process of requirement identification, development, testing and assessment. The most important requirements for the plugin is to have layers that can interact with 3DCityDB data, be able to work with multiple users with different privileges, allow for multiple scenarios (database schemas), allow to edit attributes, handle different Levels Of Detail ( LOD ) and geometry representations and finally be able to operate from a Graphical User Interface ( GUI ) in QGIS . Regarding the client-side part of the plugin, it can manage database connections, manage the server-side installation, manage and create layers for multiple scenarios from a GUI , include CityGML generic attributes, enumerations and codelists and automatically set their relations, automatically structure a hierarchical QGIS Table Of Contents ( TOC ) and finally automatically apply standard colors on different features. At the time of writing this document, the plugin is at version 0.4. The limitations are mostly related to functionalities that are not yet supported, with future development being tracked from the project’s GitHub repository. All in all, ”3DCityDB-Loader” facilitates the use of 3DCityDB for users of different fields and expertise with the common denominator being the well-accustomed QGIS environment.
...
Today, in the urban planning, energy modelling and other fields, semantic 3D city models are used in various applications like visualization, data exploration, analysis and more. As a result, standard data practices needed to be set in order to facilitate the storage and exchange of these city models. For this purpose, the Open Geospatial Consortium ( OGC ) adopted CityGML as an international standard for effective use of 3D city models. Generally, the models are encoded in Extensible Markup Language ( XML ) files, however, other file encodings can also be used like JavaScript Object Notation ( JSON ) files with CityJSON. Moreover, CityGML can also be adapted for a database encoding like the 3D City Database ( 3DCityDB ), on which this thesis is based upon. The benefit of using a database encoding is that databases are built to handle and organize large amount of data, which 3D city models usually consist of. The 3DCityDB is an open source project developed for PostgreSQL and Oracle databases. It is supported by other software in the 3DCityDB suite that facilitate its use in different applications. The 3DCityDB tries to simplify the complexity of CityGML, however, its approach remains difficult for users to access data directly without technical knowledge of databases, Structured Query Language ( SQL ), CityGML and/or 3DCityDB structure. Derived frm thios limitation, the primary objective of this research is to develop an approach that could simplify user interaction with the 3DCityDB from within a Q Geographical Information System ( QGIS ) environment. To achieve this, ”3DCityDB-Loader”, a QGIS plugin, is developed to handle complex server operations in the background, whilst providing a user-friendly workspace environment. The complete functionality of the plugin is segmented into client and server-side parts. This thesis focuses on the client-side development but both parts were jointly developed in a common iterative process of requirement identification, development, testing and assessment. The most important requirements for the plugin is to have layers that can interact with 3DCityDB data, be able to work with multiple users with different privileges, allow for multiple scenarios (database schemas), allow to edit attributes, handle different Levels Of Detail ( LOD ) and geometry representations and finally be able to operate from a Graphical User Interface ( GUI ) in QGIS . Regarding the client-side part of the plugin, it can manage database connections, manage the server-side installation, manage and create layers for multiple scenarios from a GUI , include CityGML generic attributes, enumerations and codelists and automatically set their relations, automatically structure a hierarchical QGIS Table Of Contents ( TOC ) and finally automatically apply standard colors on different features. At the time of writing this document, the plugin is at version 0.4. The limitations are mostly related to functionalities that are not yet supported, with future development being tracked from the project’s GitHub repository. All in all, ”3DCityDB-Loader” facilitates the use of 3DCityDB for users of different fields and expertise with the common denominator being the well-accustomed QGIS environment.
Master thesis
(2022)
-
I. Apra, G.A.K. Arroyo Ohori, G. Agugiaro, Sebastian Krapf, Bruno Willenborg, S. Du
Automated reconstruction of detailed semantic 3D city models is challenging due to the need for high-resolution (HR) and large-scale input datasets, the ambiguous definition of the ensuing model, the intricacy of the processing pipeline, and its costs. Furthermore, existing methods mainly focus on geometry rather than semantics. Detailed semantic models may include roof installations whose size and function vary: dormers, windows, chimneys, etc. All elements visible on the roof from an aerial view are called ‘‘superstructures”. Deep Learning techniques can facilitate their modelization. This work inscribes itself in a project developed at the Technical University of Munich. The existing pipeline employs a convolutional neural network (CNN) on aerial images segmenting roof superstructures. These results can then be vectorized, extruded in 3D with their semantic description, and added to a simple 3D model.
This thesis demonstrates that building height data fused to a CNN on RGB aerial images improves the semantic segmentation of roof superstructures for classes with relief. Fusion of absolute and relative height data with different interpolation methods applied to LiDAR point cloud data is achieved through a fusion network from the state-of-the-art (FuseNet). First, experiments prove that detection accuracies increase by 11% on average for dormers and 12% for chimneys compared to U-Net output on the same dataset. Best performance is reached with the fusion of absolute height (rather than normalized) and IDW or NN interpolation technique (rather than none). However, although superstructure types are better recognized, their boundaries are fuzzier due to data input mismatches, and more background pixels are classified. Secondly, the predictions and modelization of both a Bavarian and Dutch test set prove the technique scalability. However, a training set annotated for Bavaria and applied to a test set in the Netherlands yields inaccurate results due to local architectural typologies and different input data characteristics. ...
This thesis demonstrates that building height data fused to a CNN on RGB aerial images improves the semantic segmentation of roof superstructures for classes with relief. Fusion of absolute and relative height data with different interpolation methods applied to LiDAR point cloud data is achieved through a fusion network from the state-of-the-art (FuseNet). First, experiments prove that detection accuracies increase by 11% on average for dormers and 12% for chimneys compared to U-Net output on the same dataset. Best performance is reached with the fusion of absolute height (rather than normalized) and IDW or NN interpolation technique (rather than none). However, although superstructure types are better recognized, their boundaries are fuzzier due to data input mismatches, and more background pixels are classified. Secondly, the predictions and modelization of both a Bavarian and Dutch test set prove the technique scalability. However, a training set annotated for Bavaria and applied to a test set in the Netherlands yields inaccurate results due to local architectural typologies and different input data characteristics. ...
Automated reconstruction of detailed semantic 3D city models is challenging due to the need for high-resolution (HR) and large-scale input datasets, the ambiguous definition of the ensuing model, the intricacy of the processing pipeline, and its costs. Furthermore, existing methods mainly focus on geometry rather than semantics. Detailed semantic models may include roof installations whose size and function vary: dormers, windows, chimneys, etc. All elements visible on the roof from an aerial view are called ‘‘superstructures”. Deep Learning techniques can facilitate their modelization. This work inscribes itself in a project developed at the Technical University of Munich. The existing pipeline employs a convolutional neural network (CNN) on aerial images segmenting roof superstructures. These results can then be vectorized, extruded in 3D with their semantic description, and added to a simple 3D model.
This thesis demonstrates that building height data fused to a CNN on RGB aerial images improves the semantic segmentation of roof superstructures for classes with relief. Fusion of absolute and relative height data with different interpolation methods applied to LiDAR point cloud data is achieved through a fusion network from the state-of-the-art (FuseNet). First, experiments prove that detection accuracies increase by 11% on average for dormers and 12% for chimneys compared to U-Net output on the same dataset. Best performance is reached with the fusion of absolute height (rather than normalized) and IDW or NN interpolation technique (rather than none). However, although superstructure types are better recognized, their boundaries are fuzzier due to data input mismatches, and more background pixels are classified. Secondly, the predictions and modelization of both a Bavarian and Dutch test set prove the technique scalability. However, a training set annotated for Bavaria and applied to a test set in the Netherlands yields inaccurate results due to local architectural typologies and different input data characteristics.
This thesis demonstrates that building height data fused to a CNN on RGB aerial images improves the semantic segmentation of roof superstructures for classes with relief. Fusion of absolute and relative height data with different interpolation methods applied to LiDAR point cloud data is achieved through a fusion network from the state-of-the-art (FuseNet). First, experiments prove that detection accuracies increase by 11% on average for dormers and 12% for chimneys compared to U-Net output on the same dataset. Best performance is reached with the fusion of absolute height (rather than normalized) and IDW or NN interpolation technique (rather than none). However, although superstructure types are better recognized, their boundaries are fuzzier due to data input mismatches, and more background pixels are classified. Secondly, the predictions and modelization of both a Bavarian and Dutch test set prove the technique scalability. However, a training set annotated for Bavaria and applied to a test set in the Netherlands yields inaccurate results due to local architectural typologies and different input data characteristics.
Geofront
Directly accessible GIS tools using a web-based visual programming language
In the field of Geographical Information Science (GIS), geodata transformation and analysis tools often take the shape of software libraries written in system level programming languages.
However, the societal impact of these tools is often limited, as most end users only access these libraries via indirect means: Through bindings in other languages, through plugin in applications, or both.
Additionally, the tools end users end up with are often not composable, and may contain other hurdles like installation or configuration.
The goal of this study is to make core GIS libraries more directly available and composable to end users.
This study presents and prototypes a novel method, centered around a visual programming language to host the functionalities of GIS libraries from within an application, and in a composable manner.
Additionally, the visual language is used to connect these libraries to a user-definable Graphical User Interface (GUI).
This prototype is implemented as a static web application, so that these libraries are directly accessible to end users without installation.
GIS libraries are compiled to WebAssembly, making the library usable in any language, including
this web based visual language by using a ’no boilerplate’ plugin system.
Finally, both scalability to handle sizable datasets, and a rich GUI (3D viewers, file inputs, sliders), are primary design considerations and assessment criteria.
The results show that this specific web based VPL appears to be a feasible method for providing direct access to some native GIS libraries, and does offer a unique set of features not found in comparable visual languages.
The significance of this method, compared to other web based geometry VPLs, lies in the fact that it offers a lenient plugin system, in combination with a range of different GUI nodes, certain "dataflow VPL" properties, and a proposed zero cost abstraction runtime.
All of these features combined lead to a VPL which is able to directly connect GUI components with native GIS libraries, all while remaining scalable in principle.
On a practical level, more work remains to proof this feasibility.
The methodology developed by this study is only theoretically accessible and composable, based on achieved features.
User testing is required to confirm if this method indeed improves workflows, and actually saves time and energy of developers and end users.
Moreover, the prototypical software implementation used is limited and not production ready. Both the fact that the ’no boilerplate’ plugin system cannot be used with C / C++ GIS libraries, and that backend execution is not possible yet, must be improved upon in future work.
Despite this, visual programing, distribution using WebAssembly, and Rust based geocomputation, all proved to be valuable directions of future GIS research. ...
However, the societal impact of these tools is often limited, as most end users only access these libraries via indirect means: Through bindings in other languages, through plugin in applications, or both.
Additionally, the tools end users end up with are often not composable, and may contain other hurdles like installation or configuration.
The goal of this study is to make core GIS libraries more directly available and composable to end users.
This study presents and prototypes a novel method, centered around a visual programming language to host the functionalities of GIS libraries from within an application, and in a composable manner.
Additionally, the visual language is used to connect these libraries to a user-definable Graphical User Interface (GUI).
This prototype is implemented as a static web application, so that these libraries are directly accessible to end users without installation.
GIS libraries are compiled to WebAssembly, making the library usable in any language, including
this web based visual language by using a ’no boilerplate’ plugin system.
Finally, both scalability to handle sizable datasets, and a rich GUI (3D viewers, file inputs, sliders), are primary design considerations and assessment criteria.
The results show that this specific web based VPL appears to be a feasible method for providing direct access to some native GIS libraries, and does offer a unique set of features not found in comparable visual languages.
The significance of this method, compared to other web based geometry VPLs, lies in the fact that it offers a lenient plugin system, in combination with a range of different GUI nodes, certain "dataflow VPL" properties, and a proposed zero cost abstraction runtime.
All of these features combined lead to a VPL which is able to directly connect GUI components with native GIS libraries, all while remaining scalable in principle.
On a practical level, more work remains to proof this feasibility.
The methodology developed by this study is only theoretically accessible and composable, based on achieved features.
User testing is required to confirm if this method indeed improves workflows, and actually saves time and energy of developers and end users.
Moreover, the prototypical software implementation used is limited and not production ready. Both the fact that the ’no boilerplate’ plugin system cannot be used with C / C++ GIS libraries, and that backend execution is not possible yet, must be improved upon in future work.
Despite this, visual programing, distribution using WebAssembly, and Rust based geocomputation, all proved to be valuable directions of future GIS research. ...
In the field of Geographical Information Science (GIS), geodata transformation and analysis tools often take the shape of software libraries written in system level programming languages.
However, the societal impact of these tools is often limited, as most end users only access these libraries via indirect means: Through bindings in other languages, through plugin in applications, or both.
Additionally, the tools end users end up with are often not composable, and may contain other hurdles like installation or configuration.
The goal of this study is to make core GIS libraries more directly available and composable to end users.
This study presents and prototypes a novel method, centered around a visual programming language to host the functionalities of GIS libraries from within an application, and in a composable manner.
Additionally, the visual language is used to connect these libraries to a user-definable Graphical User Interface (GUI).
This prototype is implemented as a static web application, so that these libraries are directly accessible to end users without installation.
GIS libraries are compiled to WebAssembly, making the library usable in any language, including
this web based visual language by using a ’no boilerplate’ plugin system.
Finally, both scalability to handle sizable datasets, and a rich GUI (3D viewers, file inputs, sliders), are primary design considerations and assessment criteria.
The results show that this specific web based VPL appears to be a feasible method for providing direct access to some native GIS libraries, and does offer a unique set of features not found in comparable visual languages.
The significance of this method, compared to other web based geometry VPLs, lies in the fact that it offers a lenient plugin system, in combination with a range of different GUI nodes, certain "dataflow VPL" properties, and a proposed zero cost abstraction runtime.
All of these features combined lead to a VPL which is able to directly connect GUI components with native GIS libraries, all while remaining scalable in principle.
On a practical level, more work remains to proof this feasibility.
The methodology developed by this study is only theoretically accessible and composable, based on achieved features.
User testing is required to confirm if this method indeed improves workflows, and actually saves time and energy of developers and end users.
Moreover, the prototypical software implementation used is limited and not production ready. Both the fact that the ’no boilerplate’ plugin system cannot be used with C / C++ GIS libraries, and that backend execution is not possible yet, must be improved upon in future work.
Despite this, visual programing, distribution using WebAssembly, and Rust based geocomputation, all proved to be valuable directions of future GIS research.
However, the societal impact of these tools is often limited, as most end users only access these libraries via indirect means: Through bindings in other languages, through plugin in applications, or both.
Additionally, the tools end users end up with are often not composable, and may contain other hurdles like installation or configuration.
The goal of this study is to make core GIS libraries more directly available and composable to end users.
This study presents and prototypes a novel method, centered around a visual programming language to host the functionalities of GIS libraries from within an application, and in a composable manner.
Additionally, the visual language is used to connect these libraries to a user-definable Graphical User Interface (GUI).
This prototype is implemented as a static web application, so that these libraries are directly accessible to end users without installation.
GIS libraries are compiled to WebAssembly, making the library usable in any language, including
this web based visual language by using a ’no boilerplate’ plugin system.
Finally, both scalability to handle sizable datasets, and a rich GUI (3D viewers, file inputs, sliders), are primary design considerations and assessment criteria.
The results show that this specific web based VPL appears to be a feasible method for providing direct access to some native GIS libraries, and does offer a unique set of features not found in comparable visual languages.
The significance of this method, compared to other web based geometry VPLs, lies in the fact that it offers a lenient plugin system, in combination with a range of different GUI nodes, certain "dataflow VPL" properties, and a proposed zero cost abstraction runtime.
All of these features combined lead to a VPL which is able to directly connect GUI components with native GIS libraries, all while remaining scalable in principle.
On a practical level, more work remains to proof this feasibility.
The methodology developed by this study is only theoretically accessible and composable, based on achieved features.
User testing is required to confirm if this method indeed improves workflows, and actually saves time and energy of developers and end users.
Moreover, the prototypical software implementation used is limited and not production ready. Both the fact that the ’no boilerplate’ plugin system cannot be used with C / C++ GIS libraries, and that backend execution is not possible yet, must be improved upon in future work.
Despite this, visual programing, distribution using WebAssembly, and Rust based geocomputation, all proved to be valuable directions of future GIS research.
Data on the number of floors is required for a variety of applications, ranging from energy demand estimation to flood response plans. Despite this, open data on the number of floors is currently not available at a nationwide level in the Netherlands. This means that it must be inferred from other available data. Automatic methods usually involve dividing the estimated height of a building by an assumed storey height. In some cases, this simple approach limits the accuracy of the results. Therefore, the goal of this thesis is to develop an alternative method to automatically infer the number of floors.
Three different machine learning algorithms are tested and compared: Random Forest, Gradient Boosting and Support Vector Regression. These algorithms are trained using data on the number of floors obtained from four municipalities in the Netherlands. In addition, 25 features are derived from cadastral attributes, building geometry and neighbourhood census data. These features are tested in different combinations in order to determine whether a specific subset yielded better results. Furthermore, a comparison is made between features derived from 3D building models at different levels of detail.
The results show that building height, particularly 70th percentile height, is most related to the number of floors. Other 3D geometric features are also found to be quite closely related to the number of floors, specifically roof area and volume. However, a higher level of detail did not improve the results. Cadastral features are also found to be relevant; mainly net internal area and, to a lesser extent, construction year. Furthermore, models based on a combination of different features performed better than models based on single categories of features.
The best predictive model achieved an accuracy of 94.5% and a Mean Absolute Error (MAE) of 0.06 for buildings with 5 floors or less. This represented a substantial improvement on the results of the geometric approach, which had an accuracy of 69.9% and MAE of 0.31. However, above 5 floors, model performance was substantially lower. Machine learning provided only a slight improvement on the geometric approach for these buildings. In this case, the best model had an accuracy of 52.3% and MAE of 0.62, whereas the geometric approach was 47.5% accurate and had a MAE of 0.70. A comparison of the cumulative error distributions showed that the best model mainly improved the fraction of buildings that were predicted with an error of less than 1 floor. Overall, these results show that machine learning partially provided a better estimate of the number of floors than a purely geometric approach. ...
Three different machine learning algorithms are tested and compared: Random Forest, Gradient Boosting and Support Vector Regression. These algorithms are trained using data on the number of floors obtained from four municipalities in the Netherlands. In addition, 25 features are derived from cadastral attributes, building geometry and neighbourhood census data. These features are tested in different combinations in order to determine whether a specific subset yielded better results. Furthermore, a comparison is made between features derived from 3D building models at different levels of detail.
The results show that building height, particularly 70th percentile height, is most related to the number of floors. Other 3D geometric features are also found to be quite closely related to the number of floors, specifically roof area and volume. However, a higher level of detail did not improve the results. Cadastral features are also found to be relevant; mainly net internal area and, to a lesser extent, construction year. Furthermore, models based on a combination of different features performed better than models based on single categories of features.
The best predictive model achieved an accuracy of 94.5% and a Mean Absolute Error (MAE) of 0.06 for buildings with 5 floors or less. This represented a substantial improvement on the results of the geometric approach, which had an accuracy of 69.9% and MAE of 0.31. However, above 5 floors, model performance was substantially lower. Machine learning provided only a slight improvement on the geometric approach for these buildings. In this case, the best model had an accuracy of 52.3% and MAE of 0.62, whereas the geometric approach was 47.5% accurate and had a MAE of 0.70. A comparison of the cumulative error distributions showed that the best model mainly improved the fraction of buildings that were predicted with an error of less than 1 floor. Overall, these results show that machine learning partially provided a better estimate of the number of floors than a purely geometric approach. ...
Data on the number of floors is required for a variety of applications, ranging from energy demand estimation to flood response plans. Despite this, open data on the number of floors is currently not available at a nationwide level in the Netherlands. This means that it must be inferred from other available data. Automatic methods usually involve dividing the estimated height of a building by an assumed storey height. In some cases, this simple approach limits the accuracy of the results. Therefore, the goal of this thesis is to develop an alternative method to automatically infer the number of floors.
Three different machine learning algorithms are tested and compared: Random Forest, Gradient Boosting and Support Vector Regression. These algorithms are trained using data on the number of floors obtained from four municipalities in the Netherlands. In addition, 25 features are derived from cadastral attributes, building geometry and neighbourhood census data. These features are tested in different combinations in order to determine whether a specific subset yielded better results. Furthermore, a comparison is made between features derived from 3D building models at different levels of detail.
The results show that building height, particularly 70th percentile height, is most related to the number of floors. Other 3D geometric features are also found to be quite closely related to the number of floors, specifically roof area and volume. However, a higher level of detail did not improve the results. Cadastral features are also found to be relevant; mainly net internal area and, to a lesser extent, construction year. Furthermore, models based on a combination of different features performed better than models based on single categories of features.
The best predictive model achieved an accuracy of 94.5% and a Mean Absolute Error (MAE) of 0.06 for buildings with 5 floors or less. This represented a substantial improvement on the results of the geometric approach, which had an accuracy of 69.9% and MAE of 0.31. However, above 5 floors, model performance was substantially lower. Machine learning provided only a slight improvement on the geometric approach for these buildings. In this case, the best model had an accuracy of 52.3% and MAE of 0.62, whereas the geometric approach was 47.5% accurate and had a MAE of 0.70. A comparison of the cumulative error distributions showed that the best model mainly improved the fraction of buildings that were predicted with an error of less than 1 floor. Overall, these results show that machine learning partially provided a better estimate of the number of floors than a purely geometric approach.
Three different machine learning algorithms are tested and compared: Random Forest, Gradient Boosting and Support Vector Regression. These algorithms are trained using data on the number of floors obtained from four municipalities in the Netherlands. In addition, 25 features are derived from cadastral attributes, building geometry and neighbourhood census data. These features are tested in different combinations in order to determine whether a specific subset yielded better results. Furthermore, a comparison is made between features derived from 3D building models at different levels of detail.
The results show that building height, particularly 70th percentile height, is most related to the number of floors. Other 3D geometric features are also found to be quite closely related to the number of floors, specifically roof area and volume. However, a higher level of detail did not improve the results. Cadastral features are also found to be relevant; mainly net internal area and, to a lesser extent, construction year. Furthermore, models based on a combination of different features performed better than models based on single categories of features.
The best predictive model achieved an accuracy of 94.5% and a Mean Absolute Error (MAE) of 0.06 for buildings with 5 floors or less. This represented a substantial improvement on the results of the geometric approach, which had an accuracy of 69.9% and MAE of 0.31. However, above 5 floors, model performance was substantially lower. Machine learning provided only a slight improvement on the geometric approach for these buildings. In this case, the best model had an accuracy of 52.3% and MAE of 0.62, whereas the geometric approach was 47.5% accurate and had a MAE of 0.70. A comparison of the cumulative error distributions showed that the best model mainly improved the fraction of buildings that were predicted with an error of less than 1 floor. Overall, these results show that machine learning partially provided a better estimate of the number of floors than a purely geometric approach.
In many countries digital maps are created and provided by the national cadastres: Usually they consist of multiple polygons, each with an exact location and shape, describing which kind of surface can be found at the position of the polygon (e. g. building, street, vegetation). They must be accurate and well maintained, as they are used by companies or authorities for purposes like urban planning or demographic statistics. However, especially cities are in a constant change. Old buildings are torn down, new buildings are built, and complete streets and neighbourhoods are changed. Monitoring these changes is difficult and identifying and updating the virtual maps is still done mostly manually today. A method is developed to detect changes on the ground and identify changes for the virtual maps automatically using machine learning approaches. As input data the virtual map, their corresponding aerial images and point clouds from different years are needed. As a case study for this thesis, this method is developed and applied to the BGT, the Dutch virtual map with a resolution of 20cm. The research area is the city of Haarlem for 2017 and 2018. High resolution aerial images are used in combination with point clouds created by Photogrammetry. The output is again a digital map of the area where every polygon has a probability score of how likely its category (for example building, street, etc..) changed. This can support the manual updating process eminently, as a minor percentage of polygons (for which the algorithm was unsure) must be checked manually. The research question of this thesis is to check whether this change detection is feasible even for highly heterogeneous structures like cities. Many visual changes in the aerial images are happening that are not relevant for the virtual map. In the one year, a street can be full of colourful cars, in the other year, the street is empty and completely grey. Many scenes are easy for humans to distinguish but are challenging for an algorithm. The goal is to detect a high amount of true changes while keeping the number of false positives low to reduce the manual work as much as possible. To achieve good change detection and answer the research questions, the machine learning library of XGBoost is used. It provides a gradient boosting framework for many different environments, including Python. Many weak learners, each classifying a change only with a very low detection rate (for example minimum height of all points inside the polygon), are combined to get a strong learner. This learner should be able to classify polygons with a high accuracy into polygons that change and polygons that do not change. With this method it is possible to detect a high amount of changes. 80% of all changes can be found within a reasonable number of False positives. Especially for buildings almost all changes can be identified. It is furthermore possible to localize the changes in larger polygons. However, not all changes can be identified, so that this approach should be seen as an aid for manual change detection and not to replace it.
...
In many countries digital maps are created and provided by the national cadastres: Usually they consist of multiple polygons, each with an exact location and shape, describing which kind of surface can be found at the position of the polygon (e. g. building, street, vegetation). They must be accurate and well maintained, as they are used by companies or authorities for purposes like urban planning or demographic statistics. However, especially cities are in a constant change. Old buildings are torn down, new buildings are built, and complete streets and neighbourhoods are changed. Monitoring these changes is difficult and identifying and updating the virtual maps is still done mostly manually today. A method is developed to detect changes on the ground and identify changes for the virtual maps automatically using machine learning approaches. As input data the virtual map, their corresponding aerial images and point clouds from different years are needed. As a case study for this thesis, this method is developed and applied to the BGT, the Dutch virtual map with a resolution of 20cm. The research area is the city of Haarlem for 2017 and 2018. High resolution aerial images are used in combination with point clouds created by Photogrammetry. The output is again a digital map of the area where every polygon has a probability score of how likely its category (for example building, street, etc..) changed. This can support the manual updating process eminently, as a minor percentage of polygons (for which the algorithm was unsure) must be checked manually. The research question of this thesis is to check whether this change detection is feasible even for highly heterogeneous structures like cities. Many visual changes in the aerial images are happening that are not relevant for the virtual map. In the one year, a street can be full of colourful cars, in the other year, the street is empty and completely grey. Many scenes are easy for humans to distinguish but are challenging for an algorithm. The goal is to detect a high amount of true changes while keeping the number of false positives low to reduce the manual work as much as possible. To achieve good change detection and answer the research questions, the machine learning library of XGBoost is used. It provides a gradient boosting framework for many different environments, including Python. Many weak learners, each classifying a change only with a very low detection rate (for example minimum height of all points inside the polygon), are combined to get a strong learner. This learner should be able to classify polygons with a high accuracy into polygons that change and polygons that do not change. With this method it is possible to detect a high amount of changes. 80% of all changes can be found within a reasonable number of False positives. Especially for buildings almost all changes can be identified. It is furthermore possible to localize the changes in larger polygons. However, not all changes can be identified, so that this approach should be seen as an aid for manual change detection and not to replace it.
3D city models are continuously becoming more popular among practitioners due to the volume and versatility of information they contain, which makes them suitable to be used in various applications. However, there is no mechanism to allow maintaining them updated at the same pace that cities evolve, or when error correction is necessary, eventually diminishing their value. Many cities around the world already possess such models which are mostly used for experimentation and research purposes. Such an example is also the city of Rotterdam, whose 3D city model is not regularly updated and has to be outsourced for that purpose. This thesis investigates into addressing this issue by proposing and implementing an integrative maintenance workflow. The workflow is designed to fulfill what the maintenance needs of a typical municipality are expected to be. Those needs were identified after conducting an analysis of the current situation and collecting information from practitioners within the municipality through interviews. The workflow is a combination of 3D city model versioning and visual editing capabilities with the aim to effectively maintain CityJSON encoded models in an intuitive way. Its implementation includes two prototype software implementations: a versioning component, which is utilized to create a workflow inspired by git flow and allows concurrent maintenance and alternative scenario testing in a non-linear and distributed way, and a visual editing component capable of editing CityJSON encoded 3D city models by extending Blender’s functionality. Following the implementation, the workflow was tested by simulating real world maintenance scenarios. The tests demonstrate the feasibility of maintaining 3D city models with such a workflow and more specifically the suitability of git based workflows. At the same time some key parameters of the versioning mechanism are identified which if tuned properly they can optimize the performance, behavior and robustness of 3D city model versioning. With both components being prototype solutions the workflow is far from operational and there is certainly a lot of space for improvement regarding both components. Utilizing the workflow in practice would be the ideal way for collecting useful feedback. Besides that, there are already extensions of Blender that combined with the visual updating component of the workflow can offer advanced integration of editing and analysis capabilities.
...
3D city models are continuously becoming more popular among practitioners due to the volume and versatility of information they contain, which makes them suitable to be used in various applications. However, there is no mechanism to allow maintaining them updated at the same pace that cities evolve, or when error correction is necessary, eventually diminishing their value. Many cities around the world already possess such models which are mostly used for experimentation and research purposes. Such an example is also the city of Rotterdam, whose 3D city model is not regularly updated and has to be outsourced for that purpose. This thesis investigates into addressing this issue by proposing and implementing an integrative maintenance workflow. The workflow is designed to fulfill what the maintenance needs of a typical municipality are expected to be. Those needs were identified after conducting an analysis of the current situation and collecting information from practitioners within the municipality through interviews. The workflow is a combination of 3D city model versioning and visual editing capabilities with the aim to effectively maintain CityJSON encoded models in an intuitive way. Its implementation includes two prototype software implementations: a versioning component, which is utilized to create a workflow inspired by git flow and allows concurrent maintenance and alternative scenario testing in a non-linear and distributed way, and a visual editing component capable of editing CityJSON encoded 3D city models by extending Blender’s functionality. Following the implementation, the workflow was tested by simulating real world maintenance scenarios. The tests demonstrate the feasibility of maintaining 3D city models with such a workflow and more specifically the suitability of git based workflows. At the same time some key parameters of the versioning mechanism are identified which if tuned properly they can optimize the performance, behavior and robustness of 3D city model versioning. With both components being prototype solutions the workflow is far from operational and there is certainly a lot of space for improvement regarding both components. Utilizing the workflow in practice would be the ideal way for collecting useful feedback. Besides that, there are already extensions of Blender that combined with the visual updating component of the workflow can offer advanced integration of editing and analysis capabilities.
With cities getting more densely populated and more energy demanding, infrastructure integrated PV technology has gained more interest from researchers, companies and governmental institutions. Among the many urban surfaces that have been studied to be used to generate solar energy, roads are one of the most enticing but controversial as well. It is first of all crucial to understand if their energy potential will be sufficient to make solar road installations a reasonable investment to begin with. As rooftop irradiation maps start to become the hotspot in the branch of solar energy modelling, the same attention should be directed to solar roads. This research aims to develop a modelling methodology to easily and quickly estimate the potential of solar roads and provide the first irradiation and DC yield potential map of solar highways in the Netherlands. The map could serve as a useful tool for advisory of research, private industry and governmental projects that helps to individuate optimal sites for solar road installation in the Netherlands. The average irradiation along highways is found to be around 880 KWh/ m2/y, 35% less then the potential of an optimally tilted conventional PV installation in South Holland. The most irradiated highways result to be A31, A5 and A200, with an average irradiation between 980 and 1000 KWh/ m2/y. The analysis of the sky view factor along the highways, discloses that in most of the cases highways are in almost free horizon conditions. This makes them an appealing location for PV installations. The DC yield potential of solar highways is obtained assuming three different technologies: mono crystalline silicon, poly crystalline silicon and CIGS. The scenario of having the entire Dutch highways network renovated into solar roads is considered unrealistic. Therefore, a glueable solar road technology is assumed. Solar highways can generate on average a DC yield of 138 kWh/m2/y in the Netherlands if poly crystalline silicon is assumed. This value can increase up to 174 kWh/ m2/y if mono crystalline silicon technology is implemented. In total, covering the entire Dutch highways network with solar road modules could generate between 3.4 and 6.6 TWh/y of electricity. This could be used to power 36% of the national street lighting demand. In addition to that, a model is developed that aims to address another compelling question regarding solar road feasibility: what is the impact of traffic? Two case studies are conducted on two of the four busiest roads in the Netherlands, the A12 and A16, based on real traffic data. It is found that traffic accounts for an average of 3% reduction of solar road irradiation potential, with maximum reduction of 7% in particular locations, such as bridges and in the nearby of ramp roads. The value does not drastically impact on the output power but still needs to be taken into consideration when designing the PV system of a solar road.
...
With cities getting more densely populated and more energy demanding, infrastructure integrated PV technology has gained more interest from researchers, companies and governmental institutions. Among the many urban surfaces that have been studied to be used to generate solar energy, roads are one of the most enticing but controversial as well. It is first of all crucial to understand if their energy potential will be sufficient to make solar road installations a reasonable investment to begin with. As rooftop irradiation maps start to become the hotspot in the branch of solar energy modelling, the same attention should be directed to solar roads. This research aims to develop a modelling methodology to easily and quickly estimate the potential of solar roads and provide the first irradiation and DC yield potential map of solar highways in the Netherlands. The map could serve as a useful tool for advisory of research, private industry and governmental projects that helps to individuate optimal sites for solar road installation in the Netherlands. The average irradiation along highways is found to be around 880 KWh/ m2/y, 35% less then the potential of an optimally tilted conventional PV installation in South Holland. The most irradiated highways result to be A31, A5 and A200, with an average irradiation between 980 and 1000 KWh/ m2/y. The analysis of the sky view factor along the highways, discloses that in most of the cases highways are in almost free horizon conditions. This makes them an appealing location for PV installations. The DC yield potential of solar highways is obtained assuming three different technologies: mono crystalline silicon, poly crystalline silicon and CIGS. The scenario of having the entire Dutch highways network renovated into solar roads is considered unrealistic. Therefore, a glueable solar road technology is assumed. Solar highways can generate on average a DC yield of 138 kWh/m2/y in the Netherlands if poly crystalline silicon is assumed. This value can increase up to 174 kWh/ m2/y if mono crystalline silicon technology is implemented. In total, covering the entire Dutch highways network with solar road modules could generate between 3.4 and 6.6 TWh/y of electricity. This could be used to power 36% of the national street lighting demand. In addition to that, a model is developed that aims to address another compelling question regarding solar road feasibility: what is the impact of traffic? Two case studies are conducted on two of the four busiest roads in the Netherlands, the A12 and A16, based on real traffic data. It is found that traffic accounts for an average of 3% reduction of solar road irradiation potential, with maximum reduction of 7% in particular locations, such as bridges and in the nearby of ramp roads. The value does not drastically impact on the output power but still needs to be taken into consideration when designing the PV system of a solar road.