Team develops tool for rooftop solar potential
Computer scientists from the University of Massachusetts Amherst have developed a tool that automatically estimates rooftops’ potential to generate solar energy.
The Clean Energy Council reported that at the end of 2018, 2 million Australians had a rooftop solar system, with an average of six solar panels installed every minute. The Australian Energy Market Operator estimates that this average will increase to 10–20 panels per minute if large-scale solar projects continue to be implemented.
Scientists at the University of Massachusetts Amherst College of Information and Computer Sciences (CICS) have suggested that the progress of rooftop installations is often slowed by a shortage of trained professionals who must use expensive tools to conduct labour-intensive structure assessments one by one.
According to the researchers, led by Prashant Shenoy and Subhransu Maji, current methods to automate the process require expensive three-dimensional aerial maps using LIDAR (light detection and ranging) technology, which is not widely available. The team is proposing a new, data-driven approach that uses machine learning techniques and widely available satellite images to identify roofs that have the most potential to produce cost-effective solar power.
Shenoy, Maji and colleagues will present their ‘DeepRoof’ tool at the 25th Association for Computing Machinery’s Special Interest Group on Knowledge Discovery and Data Mining (ACM SIGKDD) conference in Anchorage, Alaska.
“Solar potential estimation of a roof can substantially benefit home owners deciding to adopt solar,” said lead author and PhD student Stephen Lee. “But current automated tools work only for cities and towns where LIDAR data is available, thereby limiting their reach to just a few places in the world.”
The data-driven DeepRoof approach takes advantage of recent advances in computer vision techniques and uses satellite imagery to accurately determine roof geometry, nearby structures and trees that affect the solar potential of the roof.
“DeepRoof estimates can be used to identify ideal locations on the roof for installing solar panels,” Lee added.
Lee explained that the team trained DeepRoof using different roof shapes and sizes from six different cities to recognise and extract planar roof segments. Results show that the technology can identify the solar potential of roofs with 91% accuracy. Further, the tool can be scaled to automatically analyse satellite images of an entire city to identify all building roofs with the most solar potential.
Honeywell has introduced a suite of building integration and cyber solutions to help enterprises...
Quantify Technology's simple, modern and futureproof smart home solution is heading to the US...
A research team from Stanford University has designed a camera system that can reconstruct scenes...