Towards Scalable Economic Photovoltaic Potential Analysis Using Aerial Images and Deep Learning

Roof-mounted photovoltaic systems play a critical role in the global transition to renewable energy generation. An analysis of roof photovoltaic potential is an important tool for supporting decision-making and for accelerating new installations. State of the art uses 3D data to conduct potential analyses with high spatial resolution, limiting the study area to places with available 3D data. Recent advances in deep learning allow the required roof information from aerial images to be extracted. Furthermore, most publications consider the technical photovoltaic potential, and only a few publications determine the photovoltaic economic potential. Therefore, this paper extends state of the art by proposing and applying a methodology for scalable economic photovoltaic potential analysis using aerial images and deep learning. Two convolutional neural networks are trained for semantic segmentation of roof segments and superstructures and achieve an Intersection over Union values of 0.84 and 0.64, respectively. We calculated the internal rate of return of each roof segment for 71 buildings in a small study area. A comparison of this paper’s methodology with a 3D-based analysis discusses its benefits and disadvantages. The proposed methodology uses only publicly available data and is potentially scalable to the global level. However, this poses a variety of research challenges and opportunities, which are summarized with a focus on the application of deep learning, economic photovoltaic potential analysis, and energy system analysis.

[1]  D. Assouline,et al.  Quantifying rooftop photovoltaic solar energy potential: A machine learning approach , 2017 .

[2]  Ram Rajagopal,et al.  An Enriched Automated PV Registry: Combining Image Recognition and 3D Building Data , 2020, ArXiv.

[3]  Peter H. N. de With,et al.  Localization of buildings with a gable roof in very high-resolution aerial images , 2011, Electronic Imaging.

[4]  R. Margolis,et al.  Using GIS-based methods and lidar data to estimate rooftop solar technical potential in US cities , 2017 .

[5]  Xiaoxiang Zhu,et al.  Detection of Undocumented Building Constructions from Official Geodata Using a Convolutional Neural Network , 2020, Remote Sensing.

[6]  Shruti Jadon.  A survey of loss functions for semantic segmentation , 2020, 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB).

[7]  Miralem Hadžiselimović,et al.  Simplified Method for Analyzing the Availability of Rooftop Photovoltaic Potential , 2019, Energies.

[8]  Meng Lu,et al.  Toward Automatic Building Footprint Delineation From Aerial Images Using CNN and Regularization , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Keiichi Abe,et al.  Topological structural analysis of digitized binary images by border following , 1985, Comput. Vis. Graph. Image Process..

[10]  Christos N. Markides,et al.  Integrated optimisation of photovoltaic and battery storage systems for UK commercial buildings , 2017 .

[11]  Taehoon Hong,et al.  Development of a method for estimating the rooftop solar photovoltaic (PV) potential by analyzing the available rooftop area using Hillshade analysis , 2017 .

[12]  Xiao Xiang Zhu,et al.  Deep learning in remote sensing: a review , 2017, ArXiv.

[13]  Kai Mainzer,et al.  Analyse und Optimierung urbaner Energiesysteme - Entwicklung und Anwendung eines übertragbaren Modellierungswerkzeugs zur nachhaltigen Systemgestaltung , 2019 .

[14]  William J. Emery,et al.  Object-Based Convolutional Neural Network for High-Resolution Imagery Classification , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[15]  Volker Quaschning,et al.  Sizing of Residential PV Battery Systems , 2014 .

[16]  H. Manz,et al.  Empirical validation of models to compute solar irradiance on inclined surfaces for building energy simulation , 2007 .

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  Dirk Jordan,et al.  Compendium of photovoltaic degradation rates , 2016 .

[19]  Björn Müller,et al.  Degradation in PV Power Plants: Theory and Practice , 2019 .

[20]  R. Castello,et al.  Spatio-temporal modelling and uncertainty estimation of hourly global solar irradiance using Extreme Learning Machines , 2019, Energy Procedia.

[21]  Wolf Fichtner,et al.  Assessment of rooftop photovoltaic potentials at the urban level using publicly available geodata and image recognition techniques , 2017 .

[22]  Miguel Ângelo Santos,et al.  3D Solar Potential in the Urban Environment: A Case Study in Lisbon , 2019, Energies.

[23]  Pietro Asinari,et al.  Scalable methodology for the photovoltaic solar energy potential assessment based on available roof surface area: Further improvements by ortho-image analysis and application to Turin (Italy) , 2011 .

[24]  Yifan Wu,et al.  Aerial Imagery for Roof Segmentation: A Large-Scale Dataset towards Automatic Mapping of Buildings , 2018, ArXiv.

[25]  T. Santos,et al.  Photovoltaic potential in a Lisbon suburb using LiDAR data , 2012 .

[26]  Jean-Louis Scartezzini,et al.  Deep learning in the built environment: automatic detection of rooftop solar panels using Convolutional Neural Networks , 2019, Journal of Physics: Conference Series.

[27]  Yaohuan Huang,et al.  An Approach for Estimating Solar Photovoltaic Potential Based on Rooftop Retrieval from Remote Sensing Images , 2018, Energies.

[28]  Hyung Chul Kim,et al.  Life Cycle Greenhouse Gas Emissions of Crystalline Silicon Photovoltaic Electricity Generation , 2012 .

[29]  Maria A. Brovelli,et al.  A New Method for the Assessment of Spatial Accuracy and Completeness of OpenStreetMap Building Footprints , 2018, ISPRS Int. J. Geo Inf..

[30]  Wei Yao,et al.  Segmentation of Sloped Roofs from Airborne LiDAR Point Clouds Using Ridge-Based Hierarchical Decomposition , 2014, Remote. Sens..

[31]  Jian Liu,et al.  GIS-based approach for potential analysis of solar PV generation at the regional scale: A case study of Fujian Province , 2013 .

[32]  Isaac A. Meir,et al.  Object-Based Image Procedures for Assessing the Solar Energy Photovoltaic Potential of Heterogeneous Rooftops Using Airborne LiDAR and Orthophoto , 2020, Remote. Sens..

[33]  Yassine Ruichek,et al.  Building Roof Segmentation from Aerial Images Using a Line-and Region-Based Watershed Segmentation Technique , 2015, Sensors.

[34]  D. Stolten,et al.  Linking the Power and Transport Sectors—Part 1: The Principle of Sector Coupling , 2017 .

[35]  Dirk Neumann,et al.  DeepSolar for Germany: A deep learning framework for PV system mapping from aerial imagery , 2020, 2020 International Conference on Smart Energy Systems and Technologies (SEST).

[36]  Nicholas A. Engerer,et al.  Comparing the capability of low- and high-resolution LiDAR data with application to solar resource assessment, roof type classification and shading analysis , 2017 .

[37]  R. Margolis,et al.  Estimating rooftop solar technical potential across the US using a combination of GIS-based methods, lidar data, and statistical modeling , 2018 .

[38]  Thomas H. Kolbe,et al.  INTEGRATION OF SEMANTIC 3D CITY MODELS AND 3D MESH MODELS FOR ACCURACY IMPROVEMENTS OF SOLAR POTENTIAL ANALYSES , 2018, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

[39]  R. Margolis,et al.  Solar plus: Optimization of distributed solar PV through battery storage and dispatchable load in residential buildings , 2018 .

[40]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[41]  Zhaojian Huang,et al.  Urban solar utilization potential mapping via deep learning technology: A case study of Wuhan, China , 2019, Applied Energy.

[42]  Taehoon Hong,et al.  A bottom-up approach for estimating the economic potential of the rooftop solar photovoltaic system considering the spatial and temporal diversity , 2018, Applied Energy.

[43]  Jiafan Yu,et al.  DeepSolar: A Machine Learning Framework to Efficiently Construct a Solar Deployment Database in the United States , 2018, Joule.

[44]  Jutta Geldermann,et al.  What drives the profitability of household PV investments, self-consumption and self-sufficiency? , 2017 .

[45]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[46]  J. Kaňuk,et al.  Assessment of photovoltaic potential in urban areas using open-source solar radiation tools , 2009 .

[47]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[48]  M. Stefancich,et al.  Evaluating the factors that led to low-priced solar electricity projects in the Middle East , 2018, Nature Energy.

[49]  Thomas H. Kolbe,et al.  Representing and Exchanging 3D City Models with CityGML , 2009 .

[50]  Wouter Duyck,et al.  Variability of operator performance in remote-sensing image interpretation: the importance of human and external factors , 2014 .

[51]  D. Assouline,et al.  Large-scale rooftop solar photovoltaic technical potential estimation using Random Forests , 2018 .

[52]  Tobias Boström,et al.  Modeling of photovoltaic power generation and electric vehicles charging on city-scale : A review , 2018 .

[53]  M. Brito,et al.  The importance of facades for the solar PV potential of a Mediterranean city using LiDAR data , 2017 .

[54]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

[55]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[56]  Jaroslav Hofierka,et al.  A New GIS‐based Solar Radiation Model and Its Application to Photovoltaic Assessments , 2004, Trans. GIS.

[57]  J. Michalsky,et al.  Modeling daylight availability and irradiance components from direct and global irradiance , 1990 .

[58]  Joshua M. Pearce,et al.  A Review of Solar Photovoltaic Levelized Cost of Electricity , 2011 .

[59]  Jean-Louis Scartezzini,et al.  Estimation of Large-Scale Solar Rooftop PV Potential for Smart Grid Integration: A Methodological Review , 2018 .

[60]  Pierre Alliez,et al.  Can semantic labeling methods generalize to any city? the inria aerial image labeling benchmark , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[61]  Gabriela Csurka,et al.  What is a good evaluation measure for semantic segmentation? , 2013, BMVC.

[62]  Miguel Brito,et al.  Modelling solar potential in the urban environment: State-of-the-art review , 2015 .

[63]  C. Kost,et al.  LEVELIZED COST OF ELECTRICITY RENEWABLE ENERGY TECHNOLOGIES , 2016 .

[64]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[65]  M. Chiesa,et al.  What is going on with Middle Eastern solar prices, and what does it mean for the rest of us? , 2021, Progress in Photovoltaics: Research and Applications.

[66]  C. Reinhart,et al.  A method for predicting city-wide electricity gains from photovoltaic panels based on LiDAR and GIS data combined with hourly Daysim simulations , 2013 .

[67]  N. Fueyo,et al.  A method for estimating the geographical distribution of the available roof surface area for large-scale photovoltaic energy-potential evaluations , 2008 .

[68]  W. V. Sark,et al.  Technical potential for photovoltaics on buildings in the EU-27 , 2012 .

[69]  Clifford W. Hansen,et al.  Pvlib Python: a Python Package for Modeling Solar Energy Systems , 2018, J. Open Source Softw..

[70]  Taehoon Hong,et al.  Development of a rooftop solar photovoltaic rating system considering the technical and economic suitability criteria at the building level , 2018, Energy.

[71]  Subhransu Maji,et al.  DeepRoof: A Data-driven Approach For Solar Potential Estimation Using Rooftop Imagery , 2019, KDD.

[72]  Raul Miranda,et al.  Technical-economic potential of PV systems on Brazilian rooftops , 2015 .

[73]  Jordan M. Malof,et al.  Distributed solar photovoltaic array location and extent dataset for remote sensing object identification , 2016, Scientific Data.

[74]  Nuria Martín-Chivelet,et al.  Photovoltaic potential and land-use estimation methodology , 2016 .

[75]  Sofiane Abbar,et al.  Machine-assisted map editing , 2018, SIGSPATIAL/GIS.

[76]  Joshua M. Pearce,et al.  Incorporating Shading Losses in Solar Photovoltaic Potential Assessment at the Municipal Scale , 2012, Solar Energy.

[77]  H. Takebayashi,et al.  Study to examine the potential for solar energy utilization based on the relationship between urban morphology and solar radiation gain on building rooftops and wall surfaces , 2015 .

[78]  Shihong Du,et al.  Semantic classification of urban buildings combining VHR image and GIS data: An improved random forest approach , 2015 .

[79]  Norbert Pfeifer,et al.  Automatic Roof Plane Detection and Analysis in Airborne Lidar Point Clouds for Solar Potential Assessment , 2009, Sensors.

[80]  P. Nagabhushan,et al.  A simple and robust line detection algorithm based on small eigenvalue analysis , 2004, Pattern Recognit. Lett..

[81]  Wided Medjroubi,et al.  OpenStreetMap data in modelling the urban energy infrastructure: a first assessment and analysis , 2017 .

[82]  Xiao Xiang Zhu,et al.  Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources , 2017, IEEE Geoscience and Remote Sensing Magazine.

[83]  Julieta Schallenberg-Rodriguez,et al.  Photovoltaic techno-economical potential on roofs in regions and islands: The case of the Canary Islands. Methodological review and methodology proposal , 2013 .

[84]  R. Castello,et al.  Big data mining for the estimation of hourly rooftop photovoltaic potential and its uncertainty , 2020 .

[85]  Ursula Eicker,et al.  Assessment of the photovoltaic potential at urban level based on 3D city models: A case study and new methodological approach , 2017 .