Quantification of the suitable rooftop area for solar panel installation from overhead imagery using Convolutional Neural Networks

The integration of solar technology in the built environment is realized mainly through rooftop-installed panels. In this paper, we leverage state-of-the-art Machine Learning and computer vision techniques applied on overhead images to provide a geo-localization of the available rooftop surfaces for solar panel installation. We further exploit a 3D building database to associate them to the corresponding roof geometries by means of a geospatial post-processing approach. The stand-alone Convolutional Neural Network used to segment suitable rooftop areas reaches an intersection over union of 64% and an accuracy of 93%, while a post-processing step using building database improves the rejection of false positives. The model is applied to a case study area in the canton of Geneva and the results are compared with another recent method used in the literature to derive the realistic available area.

Deep learning in the built environment: automatic detection of rooftop solar panels using Convolutional Neural Networks

Roberto Castello, Martin Esguerra, Adrian Guerra, Jean-Louis Scartezzini

Mapping the location and size of solar installations in urban areas can be a valuable input for policymakers and for investing in distributed energy infrastructures. Machine Learning techniques, combined with satellite and aerial imagery, allow to overcome the limitations of surveys and sparse databases in providing this mapping at large scale. In this paper we apply a supervised method based on convolutional neural networks to delineate rooftop solar panels and to detect their sizes by means of pixel-wise image segmentation. As input to the algorithm, we rely on high resolution aerial photos provided by the Swiss Federal Office of Topography. We explore different data augmentation and we vary network parameters in order to maximize model performance. Preliminary results show that we are able to automatically detect in test images the area of a set of solar panels at pixel level with an accuracy of about 0.94 and an Intersection over Union index of up to 0.64. The scalability of the trained model allows to predict the existing solar panels deployment at the Swiss national scale. The correlation with local environmental and socio-economic variables would allow to extract predictive models to foster future adoption of solar technology in urban areas.

IOP Science2019

Colored solar façades for buildings

Jean-Christophe Hadorn, Nicolas Jolissaint, Andreas Schueler

Solar energy is a prime way to reach net zero energy buildings. Addressing buildings’ energy needs is a priority because buildings are the largest demander of energy (followed by industry then transport). However, harvesting energy from solar farms, implies covering large areas with standard black or blue solar modules, which is generally not well accepted by the stakeholders. If architectural coherence is to be preserved, building envelopes cannot simply be covered with black panels with visible cells and contact bars. Today, panels of different colors are available to integrate solar energy smoothly into the built environment. However, while a choice of colors is good news for architecture, it should not cause excessive energy losses. The Kromatix panels presented in this paper are covered by glass that combines effects of diffuse surfaces and interference filters. With a minimal loss of efficiency, these panels pave the way to new considerations in solar architecture.

Elsevier2017

Towards a pre-design method for low carbon architectural strategies

Marilyne Andersen, Arianna Brambilla, Stefano Cozza, Endrit Hoxha, Thomas Bernard Paul Jusselme

To face climate change, Switzerland proposes the 2050 energy strategy by fixing greenhouse gas (GHG) emission targets for the built environment. Designers will then have to increase operating performances while inimizing embodied impacts. This represents an issue for the building design process. In addition, there is a relationship between the design efficiency and the early integration of the knowledge about design. The purpose of this paper is to highlight the potential of a pre-design method to identify the building design parameters that reach the 2050 climate change objectives. To that end, four major steps are developed in this project. First, design parameters (e.g. wall thermal transmittance) which influence the building GHG emissions the most, are identified thanks to a literature review. Morris method (Saltelli et al, 2004) is used to create combinations of design parameters changing their values one by one. Secondly, these combinations are attributed to architectural feasibility studies (Sinclair, 2013) developed in the brief design phase to perform lifecycle analysis. Thirdly, KBOB database (KBOB et al., 2014) and lifetime of components proposed by PI-BAT were used for assessing GHG emissions. Lesosai software was used for primary energy assessment. Lastly, the combinations of design parameters and their relative GHG emissions are interpreted with data mining and visualization techniques. The smart living lab building has been chosen as a case study: this building aims at achieving the 2050 goals of the 2000-watt society vision and will be built by 2020 in Fribourg, Switzerland. Thanks to the preliminary results it is possible to rank the design parameters according to their GHG contribution, in order to highlight them during the early building design stage. The method offers combinations of design parameters allowing to reach the 2050 climate change objectives. Data mining and visualization enable designers to easily find the values of these parameters to fit into the architectural strategy. In order to offer a wider range of design parameter values, techniques to enhance the database should be further investigated.

2016

Towards a pre-design method for low carbon architectural strategies

Marilyne Andersen, Arianna Brambilla, Stefano Cozza, Endrit Hoxha, Thomas Bernard Paul Jusselme

2016