OpenSAR Insight

SAR imagery

This dataset uses Synthetic Aperture Radar (SAR) images from the European Space Agency's (ESA) Copernicus Sentinel-1 mission, which come from two satellites (Sentinel-1A and Sentinel-1B) in polar orbit that operate in all weather conditions, both day and night. The selected Level 1 SAR products are Ground Range Detection (GRD) in wide interferometric mode (IW) and Single Look Complex (SLC) burst products. An important new feature of this dataset is the availability of Level 0 data (L0, RAW data) extracted from the Level 1 data (L1) used.

SAR images location

The SAR data composing the database have the following geographical coverage:

SAR Data & labeling

The dataset is structured as a series of SAR scenes. In this case study, a total of 21 different SAR scenes were selected. The data provided by Aresys has been used to carry out the selection of SAR products. This reference database provides information on radio frequency interference (RFI) maps and classification, derived from C-band measurements acquired by Sentinel-1. The data are generated for each Sentinel-1 orbit cycle, which has a repeat period of 12 days. The available data spans the period between June 2019 and September 2023.

Due to the complexity of processing SLC images, which are organized by bursts, it was necessary to modify the patch generation algorithm compared to the other use cases. In this case, square divisions were made by considering the start and end of each burst that forms each band of the SLC product. The dataset provided keeps these in the 1400x1400 to 1600x1600 range, though they can be pooled or compressed as needed to accommodate ML model input sizes.

All the patches generated are identified by patch number, product type, and polarization.

The labelling strategy is based on XML (Extensible Markup Language) format. The following Table considers tags, levels, and descendants for all RFI files (including metadata, data, and labels).

Level	Tag Name	Descendants	Tag Contents
0	Scene_Info	Scene_ID; Date; Version; CaseStudy	-
1	Scene_ID	N/A	Naming of the SAR scene into the database
1	Date	N/A	YYYYMMDD
1	Version	N/A	Version of the SAR scene
1	CaseStudy	N/A	RFIDetection
0	SARData	SAR_Mission; SARProduct; SLCSwath; Time_interval	-
1	SAR_Mission	N/A	S1A-SA1B
1	SARProduct	N/A	Name of the SLC product SAR
1	SLCSwath	N/A	Number of swath
1	Time_Interval	Start; Stop	-
2	Start	N/A	YYYYMMDD_HHMMSS
2	Stop	N/A	YYYYMMDD_HHMMSS
0	ProcessingData	Corner_Coord; Corner_Coord_Mask; StatisticsReport	-
1	Corner_Coord	SARData_Sample; SARData_Line; Scene_Sample; Scene_Line; Latitude; Longitude	-
2	SARData_Sample	N/A	Number of columns of 512 pixels in the geocoded image.
2	SARData_Line	N/A	Number of rows of 512 pixels in the geocoded image.
2	Scene_Sample	N/A
2	Scene_Line	N/A
2	Latitude	N/A	Latitudes of corners
2	Longitude	N/A	Longitudes of corners
1	Corner_Coord_Mask	Sample; Line	-
2	Sample	N/A	Number of columns of patch mask
2	Line	N/A	Number of rows of patch mask
1	StatisticsReport	RFIDetection	-
2	RFIDetection	N/A	Whether an RFI event may be detected in the patch.

Data partitions

The data relating to this case study are organised as follows:

RFI use-case	XML labels	Masks	L0 patches	SLC patches	GRD patches
Train set	824	824	1648	1648	1648
Val set	129	129	258	258	258
Test set	94	94	188	188	188
Total	1047	1047	2094	2094	2094

Note: XMLs denote the number of unique patches. For this use-case, masks are included. L0, SLC, and GRD are doubled as they include both VV and VH polarisations.