TY - GEN
T1 - A deep convolutional neural network and a random forest classifier for solar photovoltaic array detection in aerial imagery
AU - Malof, Jordan M.
AU - Collins, Leslie M.
AU - Bradbury, Kyle
AU - Newell, Richard G.
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016
Y1 - 2016
N2 - Power generation from distributed solar photovoltaic PV arrays has grown rapidly in recent years. As a result, there is interest in collecting information about the quantity, power capacity, and energy generated by such arrays; and to do so over small geo-spatial regions (e.g., counties, cities, or even smaller regions). Unfortunately, existing sources of such information are dispersed, limited in geospatial resolution, and otherwise incomplete or publically unavailable. As result, we recently proposed a new approach for collecting such distributed PV information that relies on computer algorithms to automatically detect PV arrays in high resolution aerial imagery [1], Here we build on this work by investigating two machine learning algorithms for PV array detection: a Random Forest classifier (RF) [2] and a deep convolutional neural network (CNN) [3]. We use the RF algorithm as a benchmark, or baseline, for comparison with a CNN model. The two models are developed and tested using a large collection of publicly available [4] aerial imagery, covering 135 km2, and including over 2,700 manually annotated distributed PV array locations. The results indicate that the CNN substantially improves over the RF. The CNN is capable of excellent performance, detecting nearly 80% of true panels with a precision measure of 72%.
AB - Power generation from distributed solar photovoltaic PV arrays has grown rapidly in recent years. As a result, there is interest in collecting information about the quantity, power capacity, and energy generated by such arrays; and to do so over small geo-spatial regions (e.g., counties, cities, or even smaller regions). Unfortunately, existing sources of such information are dispersed, limited in geospatial resolution, and otherwise incomplete or publically unavailable. As result, we recently proposed a new approach for collecting such distributed PV information that relies on computer algorithms to automatically detect PV arrays in high resolution aerial imagery [1], Here we build on this work by investigating two machine learning algorithms for PV array detection: a Random Forest classifier (RF) [2] and a deep convolutional neural network (CNN) [3]. We use the RF algorithm as a benchmark, or baseline, for comparison with a CNN model. The two models are developed and tested using a large collection of publicly available [4] aerial imagery, covering 135 km2, and including over 2,700 manually annotated distributed PV array locations. The results indicate that the CNN substantially improves over the RF. The CNN is capable of excellent performance, detecting nearly 80% of true panels with a precision measure of 72%.
KW - Convolutional neural networks
KW - Deep learning
KW - Detection
KW - Energy
KW - Photovoltaic
KW - Solar
UR - http://www.scopus.com/inward/record.url?scp=85017279022&partnerID=8YFLogxK
U2 - 10.1109/ICRERA.2016.7884415
DO - 10.1109/ICRERA.2016.7884415
M3 - Conference contribution
AN - SCOPUS:85017279022
T3 - 2016 IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2016
SP - 650
EP - 654
BT - 2016 IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2016
Y2 - 20 November 2016 through 23 November 2016
ER -