Home

Clay Announcements
Discuss Anything
GTM Career Advice
Introduce Yourself
Member Spotlight
Share Content and Events
Share Full-time Jobs
Share Part Time Jobs
Share Tables, Tools, and Workflows

Community Guidelines

Hire GTME Talent
Explore Events

Powered by Tightknit

Discuss Anything

Analyzing Google Maps Images for Solar Panel Detection with Clay | Clay

Discuss Anything

Analyzing Google Maps Images for Solar Panel Detection with Clay

·Dec 12, 2025 12:32 PM·

Hi all, I'm trying to figure out how I can use clay to analyse google maps images to see where solar panels are installed. Anyone have experience with this or know the most accurate way?

9 comments

· Sorted by Oldest

Rod A.
·
·
Hey dude Google has a Solar API but it's not definitive: https://developers.google.com/maps/documentation/solar/overview Better option is to scrape or API local solar permit data
Max M.
·
·
Thanks Rod that's exactly what i was looking into, was also struggling with the full coverage but i think it makes for a good start
Rod A.
·
·
You bet. Good luck brother!
Max M.
·
·
thanks man, appreciate it!
Umer I.
·
·
I saw a workflow that used the Google Earth API plus an LLM trained to recognize specific objects like solar panels. Not sure who built it but it might help you to get an idea.
Aaron J.
·
·
Max M. this touches on a workflow we are exploring in the AI cohort. You can pass latitude and longitude into the following URL format (https://www.google.com/maps/@(LATITUDE),(LONGITUDE),200m/data=!3m1!1e3) where 200m indicates a viewspace of 200 meters. Then you can use 'capture screenshot' enrichment based on that url to get a screenshot of google maps. Then use 'analyze image' enrichment with specific instructions to identify solar panels in the image (estimate sq meters maybe?). You may need to pass that output into an AI text model (GPT 4.1 mini for example) to parse out specific results. I would recommend you find an example or two where solar panels are visible on google maps, and use those as a test case to refine your prompts until its giving you consistent accurate results.
Aaron J.
·
·
Izzy (. FYI this might be an interesting case study for future cohorts
Rod A.
·
·
Aaron J. Super interesting. I love this community, always something new to learn. Thanks for sharing!
2
Willy H.
·
·
Haha love this Aaron man! Aaron J.
2