Sentinel-1 New Anomalies AI4QC

This dataset was used in the AI4QC project (Artificial Intelligence for Quality Control), in the context of the detection of new anomalies through unsupervised learning (unlabeled data). It consists of 6344 Sentinel-1 images (quick-looks in png format). The dataset was divided into training and testing folders (80% training and 20% testing). Two criterias were considered for the train/test split: seasonality and geographic location.  

An additional folder, "S1_additional_data" contains 14 more products which were collected from the region around Hawaii, which tends to give products containing RFIs. This data is not included in the train/test folders but can be used if one wishes to increase the amount of S1 products.