Automatic detection of solar photovoltaic arrays in high resolution aerial imagery

Thumbnail Image




Malof, JM
Bradbury, K
Collins, LM
Newell, RG

Journal Title

Journal ISSN

Volume Title

Repository Usage Stats


Citation Stats

Attention Stats


© 2016 Elsevier Ltd The quantity of small scale solar photovoltaic (PV) arrays in the United States has grown rapidly in recent years. As a result, there is substantial interest in high quality information about the quantity, power capacity, and energy generated by such arrays, including at a high spatial resolution (e.g., cities, counties, or other small regions). Unfortunately, existing methods for obtaining this information, such as surveys and utility interconnection filings, are limited in their completeness and spatial resolution. This work presents a computer algorithm that automatically detects PV panels using very high resolution color satellite imagery. The approach potentially offers a fast, scalable method for obtaining accurate information on PV array location and size, and at much higher spatial resolutions than are currently available. The method is validated using a very large (135 km 2 ) collection of publicly available (Bradbury et al., 2016) aerial imagery, with over 2700 human annotated PV array locations. The results demonstrate the algorithm is highly effective on a per-pixel basis. It is likewise effective at object-level PV array detection, but with significant potential for improvement in estimating the precise shape/size of the PV arrays. These results are the first of their kind for the detection of solar PV in aerial imagery, demonstrating the feasibility of the approach and establishing a baseline performance for future investigations.


Journal article





Solar energy, Detection, Object recognition, Satellite imagery, Photovoltaic, Energy information


Published Version (Please cite this version)


Publication Info

Malof, JM, K Bradbury, LM Collins and RG Newell (2016). Automatic detection of solar photovoltaic arrays in high resolution aerial imagery. Applied Energy, 183. 10.1016/j.apenergy.2016.08.191 Retrieved from

This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.



Jordan Milton Malof

Adjunct Assistant Professor in the Department of Electrical and Computer Engineering

I work with domain experts across different fields to solve challenging real-world problems through the application or development of advanced signal processing, computer vision, machine learning (especially deep learning) methods to real-world problems.  Recently, my work has spanned topics such as remote sensing, energy systems, and materials science.   My work has recently been featured in premiere machine learning conferences (e.g., NeurIps, ICLR) and computer vision conferences (e.g., WACV).


Kyle Bradbury

Assistant Research Professor in the Department of Electrical and Computer Engineering

Kyle Bradbury is the Managing Director of the Energy Data Analytics Lab at the Duke University Energy Initiative. He brings experience in machine learning and statistical modeling to energy problems. He completed his Ph.D. at Duke University, with research focused on modeling the reliability and cost trade-offs of energy storage systems for integrating wind and solar power into the grid. Kyle holds a M.S. in Electrical Engineering from Duke University where he specialized in statistical signal processing and machine learning, and a B.S. in Electrical Engineering from Tufts University. He has worked for ISO New England, MIT Lincoln Laboratories, and Dominion.


Leslie M. Collins

Professor of Electrical and Computer Engineering

Leslie M. Collins earned the BSEE degree from the University of Kentucky, and the MSEE, and PhD degrees from the University of Michigan, Ann Arbor. From 1986 through 1990 she was a Senior Engineer at Westinghouse Research and Development Center in Pittsburgh, PA. She joined Duke in 1995 as an Assistant Professor and was promoted to Associate Professor in 2002 and to Professor in 2007. Her research interests include physics-based statistical signal processing, subsurface sensing, auditory prostheses and pattern recognition. She is a member of the Tau Beta Pi, Sigma Xi, and Eta Kappa Nu honor societies. Dr. Collins has been a member of the team formed to transition MURI-developed algorithms and hardware to the Army HSTAMIDS and GSTAMIDS landmine detection systems. She has been the principal investigator on research projects from ARO, NVESD, SERDP, ESTCP, NSF, and NIH. Dr. Collins was the PI on the DoD UXO Cleanup Project of the Year in 2000. As of 2015, Dr. Collins has graduated 15 PhD students.

Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.