Searching for Oil Spills on Sea Surfaces

Oil spills rapidly spread on sea surfaces covering wide areas, assuming different appearances and thicknesses.

The faster the actions to detect, stop, and contain the released oil from spreading, the higher the Oil Spill Response (OSR) success rate.

Since, clean-up effectiveness is higher over thicker layers of oil - referred to as actionable oil - detecting these regions is crucial to enhance oil recovery efficiency, thus minimizing environmental and socio-economic impacts.

The objective of ""Searching for Oil Spills on Sea Surfaces"" (SOSeas) project is to develop an artificial intelligence-based system to extract relative oil thicknesses by using multifrequency and multiresolution Synthetic Aperture Radars (SAR). Aerial reconnaissance is currently the most common method to estimate the extent, thickness, and volume of oil spills.

However, it is subjective, biased and imprecise, demanding well-trained experts to visually estimate the extent of an oil slick and distinguish different oil appearances.

Conversely, SAR are key-operational sensors for oil pollution monitoring, offering a synoptic view over affected sites, acquiring images during day and night regardless of weather conditions.

The use of SAR data to detect the location and extent of oil pollution, as well as to discriminate it from false alarms has been well-researched.

However, oil slicks characterization is under-explored, but a promising, new, and highly innovative research area, owing to the increasing availability of free SAR data, the development of powerful learning algorithms combined with high-performance computing advances.

An automatic system well-trained to recognize patterns related to qualitative thickness ranging will indicate the actionable oil regions.

These outputs can offer a less subjective and more precise oil pollution assessment than that of visual reconnaissance, improving situational awareness in time to guide trustworthy decision-making during clean-up operations.