Individual Solar Panels
Detection solar panels on roofs needs high resolution imagery. Typically aerial or drone imagery. It is very difficult to achieve with 1.5m or even 50 cm imagery.
Here are a few articles about using machine learning for solar panel detection:
Solar farms may be easier to detect because that are so much larger. They are actually built by commercial companies who resell the produced energy.
This article present how Astrea built a solar farm detector on Sentinel-2 images. It indicates that the final model had a precision of 92% and a recall of 85% of its solar farm predictions. Unfortunatelly very few details are given except that “the most important factor in model improvement came from getting more training data — not from hyperparameter tuning or testing out different CNN architectures.”
some other article