Direct approach

• Ice-penetrating radar surveys, accurate but limited spatial coverage

  • E.g. from British Antarctic Survey, Operation Icebridge field missions, etc
  

Figure showing Radio-echo-sounding datasets around Antarctica from Gardner et al. 2018

Indirect approach

• Inverse model on satellite captured ice surface data, less accurate but widely applicable
  • E.g. Our DeepBedMap model, BedMachine Antarctica using mass conservation, etc

Hillshade Map of the Reference Elevation Model of Antarctica (REMA) from Howat et al. 2018

The idea - get the best of both worlds

• Train neural network on areas with high resolution grid data.

  • Given high resolution surface datasets + prior knowledge of bed, model learns to predict high resolution bed topography

  • High resolution groundtruth areas provide 'answer' to train the neural network.

    ​​​​​​​​    X(Surface inputs) -- function(X) --> Y(Groundtruth bed)
    

Towards Generative Adversarial Network (GAN) models

Why? Because GANs can drive the reconstruction towards a more 'natural' look, compared to standard ConvNets that simply reduce the Mean Squared Error (MSE) loss.

Generative Adversarial Network intuition

Two competing neural networks working to improve image's finer details

Generator (artist) learns to produce better image to convince Discriminator, Discriminator (teacher) points out where image is incorrect

https://towardsdatascience.com/intuitive-introduction-to-generative-adversarial-networks-gans-230e76f973a9

2016-2017: Super Resolution Generative Adversarial Network (SRGAN) by Ledig et al., 2017

Generator-Discriminator GAN models have parallels with Actor-Critic models in Reinforcement Learning.

2018-2019: Enhanced Super Resolution Generative Adversarial Network (ESRGAN) by Wang et al., 2019

Extra help - use 'Network Conditioning' to get more info

• Since we're not working with 'typical' photographs, we don't need to do Single Image Super Resolution.
• Additional context (i.e. geographical layers) can be added to produce better Super-Resolution results!

Pan-sharpening is a classic (remote-sensing) example. Given a high resolution panchromatic band and low resolution RGB bands -> produce a 'super resolution' RGB image.

Figure showing pan-sharpened results using PSGAN from Liu et al., 2018

DeepBedMap Generator Model Architecture

Model adapted from ESRGAN and built using Chainer (Python deep learning library)

Super Resolution results (4x upsampling)

Example over Pine Island Glacier.

Along transect elevation and roughness

DeepBedMap_DEM (purple) features more fine-scale (<10km) bumps and troughs, and higher roughness values (mean standard deviation of about 40m), similar to the ground truth (orange)

Hyperparameter Tuning

To optimize the ESRGAN model's performance, a Bayesian approach (Tree-Structured Parzen Estimator) was used to narrow down our hyperparameter search space.

Grid Search

Random Search

Bayesian Optimization

HyperBand used to prune unpromising trials.
Main 'hyperparameters' tuned (in rough order of priority) were:
Learning rate (1.7e-4, 2e-4 to 1e-4); Residual scaling factor (0.2, 0.1 to 0.5); Training epochs (~140, 90 to 150); Number of Residual-in-Residual Dense Blocks (12, 8 to 14); Mini-batch size (128, 64 or 128)

References (1)

• Fretwell, P., Pritchard, H. D., Vaughan, D. G., Bamber, J. L., Barrand, N. E., Bell, R., … Zirizzotti, A. (2013). Bedmap2: improved ice bed, surface and thickness datasets for Antarctica. The Cryosphere, 7(1), 375–393. https://doi.org/10.5194/tc-7-375-2013

• Gardner, A. S., Moholdt, G., Scambos, T., Fahnstock, M., Ligtenberg, S., van den Broeke, M., & Nilsson, J. (2018). Increased West Antarctic and unchanged East Antarctic ice discharge over the last 7 years. The Cryosphere, 12(2), 521–547. https://doi.org/10.5194/tc-12-521-2018

• Howat, Ian, Morin, Paul, Porter, Claire, & Noh, Myong-Jong. (2018). The Reference Elevation Model of Antarctica [Data set]. Harvard Dataverse. https://doi.org/10.7910/DVN/SAIK8B

References (2)

• Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., & Shi, W. (2017). Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 105–114. https://doi.org/10.1109/CVPR.2017.19

• Leong, W. J., & Horgan, H. J. (2020). DeepBedMap: A deep neural network for resolving the bed topography of Antarctica. The Cryosphere, 14(11), 3687–3705. https://doi.org/10.5194/tc-14-3687-2020

References (3)

• Morlighem, M., Rignot, E., Binder, T., Blankenship, D., Drews, R., Eagles, G., Eisen, O., Ferraccioli, F., Forsberg, R., Fretwell, P., Goel, V., Greenbaum, J. S., Gudmundsson, G. H., Guo, J., Helm, V., Hofstede, C., Howat, I., Humbert, A., Jokat, W., … Young, D. A. (2019). Deep glacial troughs and stabilizing ridges unveiled beneath the margins of the Antarctic ice sheet. Nature Geoscience, 13(2), 132–137. https://doi.org/10.1038/s41561-019-0510-8

• Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., … Tang, X. (2018). ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks. ArXiv:1809.00219 [Cs]. Retrieved from http://arxiv.org/abs/1809.00219