While object detection algorithms can be effective for detecting oil spills in satellite images, in this project a U-Net convolutional neural network was chosen for semantic segmentation, this approach produces binary masks that predict where an oil spill may be present.

See a use case carried out on CREODIAS, where Copernicus Sentinel-2 data was used for analysing wildfires in Los Angeles.

Looking forward to 2025, we anticipate more concrete advancements in Earth observation, particularly through the integration of AI foundation models and embeddings. Foundation models, powerful AI systems trained on extensive datasets are being adapted to interpret satellite imagery with promising results. 

With the growth of cities and industry, more and more pollutants have started to find their way into Polish waters. According to many reports, poor condition of water concerns 91.5% of river resources, around 88% of lakes and nearly 100% of transitional and coastal surface waters.

The most popular approach to monitoring vegetation involves analyzing optical data. However, this method has limitations - optical data cannot be used during high cloud cover or nighttime.

Flooding is one of the most destructive natural disasters, causing fatalities and damage in infrastructure and ecosystems. With observed intensification of extreme events with climate change, the need for effective flood monitoring becomes critical.

Read an article that analyses the surface changes of the Pizol glacier in Switzerland using Landsat-5 and Sentinel-2 satellite imagery, and in particular, Normalized Difference Snow Index (NDSI). A comparison of satellite images from different years shows how the area of the Pizol glacier has been gradually decreasing over the past 39 years.

In this article, we talk about how you can access products from the CREODIAS repository and obtain information analysing original data. We focus on Sentinel-2 images, aiming to get water-oriented data. 

Read an article where our expert describes how Copernicus Sentinel-1 data can be used for the analysis of urban sprawl through advanced processing techniques such as multi-spectral or multi-temporal analysis.