Assessment of Sentinel-2 spatial and temporal coverage based on the scene classification layer

TL;DR

This paper introduces a method to evaluate Sentinel-2 satellite data coverage using scene classification layer information, which correlates with ML model performance and aids in assessing data quality for various regions.

Contribution

The paper presents a novel technique to quantify and assess the spatial and temporal coverage of Sentinel-2 data based on scene classification labels, enhancing data quality evaluation.

Findings

Coverage assessment correlates with ML model accuracy.

Low coverage regions yield poorer classification results.

Technique applied globally across LandCoverNet dataset.

Abstract

Since the launch of the Sentinel-2 (S2) satellites, many ML models have used the data for diverse applications. The scene classification layer (SCL) inside the S2 product provides rich information for training, such as filtering images with high cloud coverage. However, there is more potential in this. We propose a technique to assess the clean optical coverage of a region, expressed by a SITS and calculated with the S2-based SCL data. With a manual threshold and specific labels in the SCL, the proposed technique assigns a percentage of spatial and temporal coverage across the time series and a high/low assessment. By evaluating the AI4EO challenge for Enhanced Agriculture, we show that the assessment is correlated to the predictive results of ML models. The classification results in a region with low spatial and temporal coverage is worse than in a region with high coverage. Finally, we applied the technique across all continents of the global dataset LandCoverNet.