TY - JOUR
T1 - Partial Label Learning With Focal Loss for Sea Ice Classification Based on Ice Charts
AU - Vahedi, Behzad
AU - Lucas, Benjamin
AU - Banaei-Kashani, Farnoush
AU - Barrett, Andrew P.
AU - Meier, Walter N.
AU - Khalsa, Siri Jodha Singh
AU - Karimzadeh, Morteza
N1 - Publisher Copyright:
© 2008-2012 IEEE.
PY - 2024
Y1 - 2024
N2 - Sea ice, crucial to the Arctic and Earth's climate, requires consistent monitoring and high-resolution mapping. Manual sea ice mapping, however, is time-consuming and subjective, prompting the need for automated deep learning-based classification approaches. However, training these algorithms is challenging because expert-generated ice charts, commonly used as training data, do not map single ice types but instead map polygons with multiple ice types. Moreover, the distribution of various ice types in these charts is frequently imbalanced, resulting in a performance bias toward the dominant class. In this article, we present a novel GeoAI approach to training sea ice classification by formalizing it as a partial label learning task with explicit confidence scores to address multiple labels and class imbalance. We treat the polygon-level labels as candidate partial labels, assign the corresponding ice concentrations as confidence scores to each candidate label, and integrate them with focal loss to train a convolutional neural network. Our proposed approach leads to enhanced performance for sea ice classification in Sentinel-1 dual-polarized SAR images, improving classification accuracy (from 87% to 92%) and weighted average F-1 score (from 90% to 93%) compared to the conventional training approach of using one-hot encoded labels and categorical cross-entropy loss. It also improves the F-1 score in four out of the six sea ice classes.
AB - Sea ice, crucial to the Arctic and Earth's climate, requires consistent monitoring and high-resolution mapping. Manual sea ice mapping, however, is time-consuming and subjective, prompting the need for automated deep learning-based classification approaches. However, training these algorithms is challenging because expert-generated ice charts, commonly used as training data, do not map single ice types but instead map polygons with multiple ice types. Moreover, the distribution of various ice types in these charts is frequently imbalanced, resulting in a performance bias toward the dominant class. In this article, we present a novel GeoAI approach to training sea ice classification by formalizing it as a partial label learning task with explicit confidence scores to address multiple labels and class imbalance. We treat the polygon-level labels as candidate partial labels, assign the corresponding ice concentrations as confidence scores to each candidate label, and integrate them with focal loss to train a convolutional neural network. Our proposed approach leads to enhanced performance for sea ice classification in Sentinel-1 dual-polarized SAR images, improving classification accuracy (from 87% to 92%) and weighted average F-1 score (from 90% to 93%) compared to the conventional training approach of using one-hot encoded labels and categorical cross-entropy loss. It also improves the F-1 score in four out of the six sea ice classes.
KW - Artificial intelligence
KW - convolution
KW - image classification
KW - losses
KW - machine vision
KW - sea ice
UR - http://www.scopus.com/inward/record.url?scp=85196759841&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85196759841&partnerID=8YFLogxK
U2 - 10.1109/JSTARS.2024.3413003
DO - 10.1109/JSTARS.2024.3413003
M3 - Article
AN - SCOPUS:85196759841
SN - 1939-1404
VL - 17
SP - 13616
EP - 13633
JO - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
JF - IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
ER -