DeepBedMap: Using a deep neural network to better resolve the bed topography of Antarctica

Leong, Wei Ji; Horgan, Huw

doi:10.5194/tc-2020-74

Cited by 4 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the Structural Similarity Index Measure (SSIM) method to measure the perceived quality, which compares the image quality of the generated high-resolution image with the measured high-resolution image. The SSIM method considers the luminance (brightness), contrast, and structural information while comparing the data (Leong & Horgan, 2020). In our case, the luminance and contrast are represented by the actual ground measurement instead of the digital number, so the SSIM is expected to show very high similarity (almost 1 for all cases)…”

Section: Super-resolution Evaluation Methodsmentioning

confidence: 99%

“…Liu et al (2018) used Super-Resolution for the lunar surface reconstruction using the improved sparse representation. Some works on DEM Super-Resolution used Convolution Neural Network (CNN) (Moon & Choi, 2016;Xu et al, 2019) and approaches based on Generative Adversarial Networks (GAN) (Demiray et al, 2020;Leong & Horgan, 2020;Shin & Spittle, 2019a). However, the major problem with those approaches is that they apply the super-resolution techniques on DEMs obtained from the same source and at the same location (Kubade et al, 2020(Kubade et al, , 2021Shin & Spittle, 2019b;Xu et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning-Based Super-Resolution of Digital Elevation Models in Data Poor Regions.

Dahal¹,

Bout²,

Westen³

et al. 2022

Preprint

View full text Add to dashboard Cite

In order to develop reliable models, the geoscientific community requires high-resolution data sets. However, the collection of such data is a persistent challenge due to the limitations of resources. The concept of super-resolution, a method from the field of machine learning, can be used to predict a high-resolution version of a low-resolution dataset to improve usability in geoscientific applications. However, thus far, super-resolution is predominantly used in image data with few cases on improving the scientific data but focusing on improving quality of same downsampled data. More importantly, it is unknown whether models that are developed and trained with high-resolution data of specific locations can also be applied to data-poor regions. To address these gaps, this study investigated the use of deep learning-based super-resolution to improve the resolution of digital elevation data, focusing on the question whether models trained with high resolution data can also be applied to regions for which only low-resolution data are available. We focused on Digital Elevation Models (DEMs), as these are among the most important datasets for many geoscientific applications and used two of the most advanced Super-Resolution models (EBRN and ESRGAN) from different groups of deep learning architecture. We trained those models extensively using high-resolution LiDAR DEM data from Austria, and found that, for the Austrian study sites, these models performed better than commonly used interpolation techniques such as bicubic interpolation. To test model applicability to different terrain conditions, we applied the models developed and trained with Austrian data to globally available free datasets on/for Colombia and Dominica. A novel loss function, training technique and evaluation metrics were developed to train and evaluate the results focusing on improving DEM data. Our results show that super-resolution can improve the accuracy of global datasets by 30-50% relative to bicubic interpolation, thus providing a promising solution for locations for which only low-resolution DEM data are available.

show abstract

Section: Super-resolution Evaluation Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Super-Resolution of Digital Elevation Models in Data Poor Regions.

Dahal¹,

Bout²,

Westen³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Baumhoer et al (2019); Mohajerani et al (2019)). Nonetheless, progress has been made with surrogate models for ice flow modelling (Riel et al, 2021;Jouvet et al, 2021), subglacial processes (Brinkerhoff et al, 2020), glacier mass balance modelling (Bolibar et al, 2020a, b;Anilkumar et al, 2022;Guidicelli et al, 2023) or super-resolution applications to downscale glacier ice thickness (Leong and Horgan, 2020). In terms of modelling glacier processes regionally or globally, it is still very challenging to move from small-scale detailed observations and physical processes to large-scale observations and parametrizations.…”

Section: Introductionmentioning

confidence: 99%

Universal Differential Equations for glacier ice flow modelling

Bolíbar

Sapienza

Maussion

et al. 2023

Preprint

View full text Add to dashboard Cite

Abstract. Geoscientific models are facing increasing challenges to exploit growing datasets coming from remote sensing. Universal Differential Equations (UDEs), aided by differentiable programming, provide a new scientific modelling paradigm enabling both complex functional inversions to potentially discover new physical laws and data assimilation from heterogeneous and sparse observations. We demonstrate an application of UDEs as a proof of concept to learn the creep component of ice flow, i.e. a nonlinear diffusivity differential equation, of a glacier evolution model. By combining a mechanistic model based on a 2D Shallow Ice Approximation Partial Differential Equation with an embedded neural network, i.e. a UDE, we can learn parts of an equation as nonlinear functions that then can be translated into mathematical expressions. We implemented this modelling framework as ODINN.jl, a package in the Julia programming language, providing high performance, source-to-source automatic differentiation (AD) and seamless integration with tools and global datasets from the Open Global Glacier Model in Python. We demonstrate this concept for 17 different glaciers around the world, for which we successfully recover a prescribed artificial law describing ice creep variability by solving ca 500,000 Ordinary Differential Equations in parallel. Furthermore, we investigate which are the best tools in the scientific machine learning ecosystem in Julia to differentiate and optimize large nonlinear diffusivity UDEs. This study represents a proof of concept for a new modelling framework aiming at discovering empirical laws for large-scale glacier processes, such as the variability of ice creep and basal sliding for ice flow, and new hybrid surface mass balance models.

show abstract

“…The use of artificial neural networks (ANNs) for estimating basal conditions – and the bedrock location in particular – is not new (Clarke and others, 2009). Recently, Leong and Horgan (2020) used a generative model based on a neural network to downscale existing reconstructed basal topography of Antarctica in high-resolution. Haq and others (2021) used an ANN trained from a digital elevation model and glacier extent data to estimate the ice thickness of individual glaciers.…”

Section: Introductionmentioning

confidence: 99%

Inversion of a Stokes glacier flow model emulated by deep learning

Jouvet

2022

J. Glaciol.

View full text Add to dashboard Cite

Data assimilation in high-order ice flow modeling is a challenging and computationally costly task, yet crucial to find ice thickness and ice flow parameter distributions that are consistent with ice flow mechanics and mass balance while best matching observations. Failing to find these distributions that are required as initial conditions leads to a disequilibrium between mass balance and ice flow, resulting in nonphysical transient effects in the prognostic model. Here we tackle this problem by inverting an emulator of the Stokes ice flow model based on deep learning. By substituting the ice flow equations using a convolutional neural network emulator, we simplify, make more robust and dramatically speed up the solving of the underlying optimization problem thanks to automatic differentiation, stochastic gradient methods and implementation of graphics processing unit (GPU). We demonstrate this process by simultaneously inferring the ice thickness distribution, ice flow parametrization and ice surface of ten of the largest glaciers in Switzerland. As a result, we obtain a high degree of assimilation while guaranteeing an equilibrium between mass-balance and ice flow mechanics. The code runs very efficiently (optimizing one large-size glacier at 100 m takes < 1 min on a laptop) while it is open-source and publicly available.

show abstract

DeepBedMap: Using a deep neural network to better resolve the bed topography of Antarctica

Cited by 4 publications

References 23 publications

Deep Learning-Based Super-Resolution of Digital Elevation Models in Data Poor Regions.

Deep Learning-Based Super-Resolution of Digital Elevation Models in Data Poor Regions.

Universal Differential Equations for glacier ice flow modelling

Inversion of a Stokes glacier flow model emulated by deep learning

Contact Info

Product

Resources

About