Back to Search
Start Over
Regression Networks For Calculating Englacial Layer Thickness
- Source :
- IGARSS
- Publication Year :
- 2021
-
Abstract
- Ice thickness estimation is an important aspect of ice sheet studies. In this work, we use convolutional neural networks with multiple output nodes to regress and learn the thickness of internal ice layers in Snow Radar images collected in northwest Greenland. We experiment with some state-of-the-art networks and find that with the residual connections of ResNet50, we could achieve a mean absolute error of 1.251 pixels over the test set. Such regression-based networks can further be improved by embedding domain knowledge and radar information in the neural network in order to reduce the requirement of manual annotations.
- Subjects :
- FOS: Computer and information sciences
010504 meteorology & atmospheric sciences
Computer science
Computer Science - Artificial Intelligence
Computer Science::Neural and Evolutionary Computation
0211 other engineering and technologies
02 engineering and technology
01 natural sciences
Convolutional neural network
Physics::Geophysics
law.invention
law
Radar imaging
FOS: Electrical engineering, electronic engineering, information engineering
Radar
Physics::Atmospheric and Oceanic Physics
021101 geological & geomatics engineering
0105 earth and related environmental sciences
geography
geography.geographical_feature_category
Artificial neural network
Pixel
Image and Video Processing (eess.IV)
Electrical Engineering and Systems Science - Image and Video Processing
Snow
Artificial Intelligence (cs.AI)
Test set
Ice sheet
Algorithm
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- IGARSS
- Accession number :
- edsair.doi.dedup.....35d4c7840b47ea83badd612959fb3149