Replication Data for: Solar park detection from publicly available satellite imagery

Subsequently, we calculated for each object the mean, standard deviation, and median for all 10- and 20-meter resolution bands of Sentinel-1 and Sentinel-2, as well as for the VIIRS night-light intensity. These features are subsequently used to train and validate a range of RF models to select the most promising model setup. The training datasets consisted of subsampled presence/absence data, oversampled presence/absence data, and multiple land use categories.

The best-performing model used an oversampled dataset trained on all 10- and 20- meter resolution spectral bands and the radar backscatter properties of one period. Independent test results show an overall classification accuracy of 99.97% (Kappa: 0.90). For this result, the producer accuracy was 85.86% for solar park objects and of 99.999% for non-solar park objects.

The user accuracy was 92.39% for solar park objects and of 99.999% for non-solar park objects. These high classification accuracies indicate that our approach is suitable for transfer learning and is able to detect solar parks in new study areas.