S2-Cloudless service specifications

This service generates cloud masks (CLM) and probabilities (CLP) using the s2cloudless algorithm developed at Sinergise. It supports both Sentinel-2 Level-1C and Level-2A Calibrated Datasets.

The tutorial of the S2-Cloudless service is available in this section.

Service Description

The Sentinel-2 Cloudless processor (S2-Cloudless) processing service provides cloud masks and probabilities computed using the s2cloudless algorithm developed at Sinergise¹. They are available as Sentinel-2 bands named CLP (cloud probabilities) and CLM (cloud masks). The classification is based on a single-scene pixel-based cloud detector developed by Sentinel Hub's research team and is described in more detail in the Sentinel Hub blog². The s2cloudless algorithm was part of an international collaborative effort aimed at intercomparing cloud detection algorithms. The S2-Cloudless algorithm³ was validated together with 9 other algorithms on 4 different test datasets and in all cases found to be on the Pareto front⁴. This service supports Calibrated Datasets from Sentinel-2 L1C and L2A data.

Inputs

The S2-Cloudless service requires as input a Calibrated Dataset (L1C or L2A) from the Sentinel-2 mission.

Parameters

The S2-Cloudless service requires a specified number of mandatory and optional parameters. Table 1 describes the service parameters.

Table 1 - Service parameters for the S2-Cloudless for L1C and L2A services.

Output

The result products of the S2-Cloudless service are the following single band or multi-band assets in COG format:

• input single band multispectral reflectance assets,

• Cloud Mask (CLM) single band asset (s2cloudless_clm): 0 (no clouds), 1 (clouds), 255 (no data),

• Cloud Mask (CLM) overview asset (s2cloudless_clm_overview): True Color Composite with True values of CLM in white superimposed,

• Cloud Probability (CLP) single band asset (s2cloudless_clp): probabilty in the [0-1] range,

• Cloud Probability (CLP) overview asset (s2cloudless_clp_overview): True Color Composite with CLP in a red to white color map superimposed,

The CLM no data value of 255 is also returned if a tile has missing CLM and CLP bands, for example due to errors. This ensures that values of 0 and 1 can be used with confidence for each pixel. CLP will in such a case return 0.

S2-Cloudless product specifications can be found in below Tables.

Filter and or Vectorize CLM single band asset

S2-Cloudless's cloud mask can be spatially filtered and / or converted to polygon using the FilterVectorize service.

To further post-process the s2cloudless_clm single band asset by removing small isolated clusters of pixel employ the FilterVectorize service in Filter mode by selecting a filter threshold size value.

The cloud mask can also be converted to polygons by using the FilterVectorize service in Vectorize mode and selecting only true values DN=1 (clouds).

To apply both spatial filtering and vectorization on CLM asset employ the FilterVectorize service in the Filter and Vectorize mode.