Posted in | News | Remote Monitoring

AI Algorithm Boosts Accuracy of Satellite-Based Oil Spill Monitoring

A hybrid satellite-AI system has been developed that detects oil spills and gauges their thickness and composition.

Oil spilling in to water, making the water a deep brown colour.
Study: Enhancing oil spill detection with controlled random sampling: A multimodal fusion approach using SAR and HSI imagery. Image credit: Anton Yulikov/Shutterstock.com

The study, published in Remote Sensing Applications: Society and Environment, is the first to employ artificial intelligence to integrate two types of satellite images to determine the location, thickness, and type of oil spill in oceans. It provides a game-changing tool for rapid and precise response planning.

This is a major step forward in oil spill detection, and it will allow us to detect spills more accurately and tell whether the oil is thick or thin. This is vital for giving decision makers a clearer picture than ever before when planning how to respond.

Quanwei Liu, Study Lead Researcher and PhD Candidate, James Cook University

When crude oil spills into water, it spreads according to the movement of currents, wind, and waves, exacerbating the pollution. For example, the 2010 Deep Horizon oil spill released millions of barrels of oil from 1.5 km beneath the sea surface, eventually covering around 12,000 km2 of ocean.

Detecting and monitoring oil spills with satellite images has proven critical in addressing and minimizing oil spill hazards. However, merging data from various satellite images for more precise detection has been difficult until recently.

We combined inputs from two types of satellite: the synthetic aperture radar (SAR) and the hyperspectral imaging satellite (HSI). SAR can detect the differences in waves and surface roughness of the ocean. If there’s oil on the surface of the water, it’ll make the surface smoother. But alone, it often confuses thin versus thick oil. HSI acts like a super-detailed color sensor that helps determine what the spilled oil material is, but it doesn’t generalize as widely.

Dr. Kevin Huang, Senior Lecturer, James Cook University

Huang suggests that this new fused approach is superior to other methods, since it combines cleaner spill outlines and stronger oil-type recognition.

The researchers pragmatically propose a straightforward response strategy: employ SAR for quick, wide-area detection after a spill, then utilize the SAR+HSI fusion inside the detected region to assess the type and thickness of oil and inform cleanup decisions.

Both scientists contend that this strategy is crucial for dealing with oil spills and might also be useful for future monitoring in various environmental settings.

We want to further apply our deep learning and remote sensing research to other monitoring applications, like water quality, forests, and disasters, to benefit societies and communities.

Dr. Kevin Huang. Senior Lecturer, James Cook University

Journal Reference:

Liu, Q. et.al. (2025) Enhancing oil spill detection with controlled random sampling: A multimodal fusion approach using SAR and HSI imagery. Remote Sensing Applications: Society and Environment. doi.org/10.1016/j.rsase.2025.101601

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

Sign in to keep reading

We're committed to providing free access to quality science. By registering and providing insight into your preferences you're joining a community of over 1m science interested individuals and help us to provide you with insightful content whilst keeping our service free.

or

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.