Accuracy, efficiency, and transferability of a deep learning model for mapping retrogressive thaw slumps across the Canadian Arctic
Date
2022
Authors
Huang, Lingcao
Lantz, Trevor C.
Fraser, Robert H.
Tiampo, Kristy F.
Willis, Michael J.
Schaefer, Kevin
Journal Title
Journal ISSN
Volume Title
Publisher
Remote Sensing
Abstract
Deep learning has been used for mapping retrogressive thaw slumps and other periglacial
landforms but its application is still limited to local study areas. To understand the accuracy, efficiency,
and transferability of a deep learning model (i.e., DeepLabv3+) when applied to large areas or
multiple regions, we conducted several experiments using training data from three different regions
across the Canadian Arctic. To overcome the main challenge of transferability, we used a generative
adversarial network (GAN) called CycleGAN to produce new training data in an attempt to improve
transferability. The results show that (1) data augmentation can improve the accuracy of the deep
learning model but does not guarantee transferability, (2) it is necessary to choose a good combination
of hyper-parameters (e.g., backbones and learning rate) to achieve an optimal trade-off between
accuracy and efficiency, and (3) a GAN can significantly improve the transferability if the variation
between source and target is dominated by color or general texture. Our results suggest that future
mapping of retrogressive thaw slumps should prioritize the collection of training data from regions
where a GAN cannot improve the transferability.
Description
Keywords
DeepLab, domain adaptation, generative adversarial network, permafrost, thermokarst
Citation
Huang, L., Lantz, T., Fraser, R., Tiampo, K., Willis, M., & Schaefer, K. (2022). “Accuracy, efficiency, and transferability of a deep learning model for mapping retrogressive thaw slumps across the Canadian Arctic.” Remote Sensing, 14(12), 2747. https://doi.org/10.3390/rs14122747