BEGIN seminar – Dr Martin Rogers
Date: Tuesday, 24th of June 2025, at 14:00 (UK Time)
Location: Online (MS Teams)
Machine learning for Antarctic sea ice detection in satellite imagery
Abstract:
The rapid and accurate detection of Antarctic sea ice is important for the safe navigation of polar ships, understanding ecosystem dynamics, and determining seasonal to decadal scale changes in sea ice response to a warming climate. While Antarctic sea ice can be detected within passive microwave, multispectral and synthetic aperture radar (SAR) satellite imagery, each image type has limitations, such as cloud cover in multispectral imagery and noise or speckle in radar imagery.
Machine learning offers powerful techniques for integrating and analysing diverse satellite datasets to improve detection accuracy and resolution. This talk presents two machine-learning approaches for detecting Antarctic sea ice using concurrent passive microwave, multispectral and SAR satellite imagery. It will explore whether combining multiple data sources can overcome the limitations of using a single satellite data product, while also highlighting the additional challenges posed by this approach.
Recording:
Bio:
Martin Rogers is a machine learning researcher in the Artificial Intelligence (AI) Lab at the British Antarctic Survey (BAS). His research primarily focusses on the application of machine learning techniques to detect features in satellite imagery, including multispectral visible and Synthetic Aperture Radar (SAR) datasets. He has recently trained a convolutional neural network, ViSual_IceD for the detection of sea ice in concurrent multispectral and SAR imagery. He holds a PhD from the University of Cambridge, where he applied AI techniques, including convolutional neural networks, to automatically detect coastal features and land covers in satellite imagery.
