GOM NASA UAVSAR: Oil Classification from Remote Sensing, 2016-2018

Data collected for NOAA's Deepwater Horizon Lessons Learned Studies on detecting oil thickness and emulsion mixtures. The research involved synoptic collection of satellite and airborne imagery, surface oil characterization, and subsurface data at the MC20 site, which has a chronic oil discharge. This field research was primarily funded by the U.S. Department of the Interior and NOAA through an interagency agreement.

Use Cases

• Training machine learning models for oil slick classification based on satellite and airborne imagery mentioned in the description.
• Developing methods to estimate oil thickness and emulsion mixtures based on the synoptic data collection described.
• Monitoring chronic oil discharge sites like MC20 using remote sensing platforms.
• Supporting environmental response management applications (ERMA) with field-validated remote sensing data.

Strengths

• Data is part of a formal NOAA study on oil spill detection funded by U.S. Department of the Interior and BSEE.
• Research involved multiple data collection methods including satellite, airborne, surface, and subsurface characterization.
• Field research was conducted over multiple years (2016, 2017, and 2018).

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Available file formats are PDF and HTML, which may not be directly machine-readable for analysis.

Provenance

Source

National Oceanic and Atmospheric Administration (NOAA), Department of Commerce.

Collection Method

Synoptic collection of satellite imagery, airborne imagery, surface oil characterization, oil and water chemistry, and subsurface oil slick data.

Time Range

Field research undertaken in 2016, 2017, and 2018.

Freshness

Last updated 2026-03 13 22:22:57.473118; freshness should be verified.

Geography

Mississippi Canyon lease block #20 (MC20) in the Gulf of Mexico.