Cloud to Street: Sentinel Satellite Chips for Flood and Cloud Detection

Cloud to Street - Microsoft Flood and Clouds Dataset consists of Sentinel-1 and Sentinel-2 satellite data chips. Each chip contains corresponding labels for water and clouds, with data organized by unique event identifiers. The dataset is hosted on AWS Open Data and is provided by the Radiant Earth Foundation under a CC-BY-4.0 license.

Use Cases

• Train flood detection models based on labeled water masks from Sentinel-1 synthetic aperture radar data.
• Develop cloud segmentation algorithms based on labeled cloud masks from Sentinel-2 optical imagery.
• Conduct multi-sensor analysis by comparing flood and cloud labels across Sentinel-1 and Sentinel-2 data for the same event.
• Build geospatial deep learning pipelines using the organized chip folder structure and overview images.

Strengths

• Contains labeled data for both water and clouds, enabling supervised learning tasks.
• Includes data from both Sentinel-1 (SAR) and Sentinel-2 (optical) satellites, allowing for multi-modal analysis.
• Data is organized by event and source image, providing a structured hierarchy for analysis.
• All satellite bands, labels, and overview images are provided within each chip folder.

Limitations

• Row count and total dataset size are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Radiant Earth Foundation

Collection Method

Chips derived from Sentinel-1 and Sentinel-2 satellite data.

Time Range

null

Freshness

Last updated date is unknown.

Geography

null