☆ 4.7 Article

A hybrid deep neural operator/finite element method for ice-sheet modeling

JOURNAL OF COMPUTATIONAL PHYSICS (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Interdisciplinary Applications

Self-adaptive physics-informed neural networks

Levi D. McClenny et al.

Summary: Physics-Informed Neural Networks (PINNs) are a promising application of deep neural networks for the numerical solution of nonlinear partial differential equations (PDEs). In this paper, a fundamentally new way to train PINNs adaptively is proposed, where fully trainable adaptation weights are applied to each training point individually, enabling the neural network to autonomously learn the difficult regions of the solution and focus on them. The self-adaptation weights provide a soft multiplicative soft attention mask resembling mechanisms used in computer vision. In numerical experiments, the proposed SA-PINN outperforms other state-of-the-art PINN algorithms in L2 error with fewer training epochs.

JOURNAL OF COMPUTATIONAL PHYSICS (2023)

Add to Collection

Article Geography, Physical

Inversion of a Stokes glacier flow model emulated by deep learning

Guillaume Jouvet

Summary: In this study, we address the challenge of data assimilation in high-order ice flow modeling by using a deep learning-based emulator. By substituting the ice flow equations with a convolutional neural network emulator, we simplify and accelerate the solving of the optimization problem, resulting in an accurate inference of ice thickness and ice flow parameter distributions.

JOURNAL OF GLACIOLOGY (2023)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Variational inference at glacier scale

Douglas J. Brinkerhoff

Summary: In this study, we use stochastic variational inference to characterize the joint Bayesian posterior distribution over spatially-varying basal traction and ice rheology of an ice sheet model. By controlling the prior assumptions on parameter smoothness and length scale and casting the problem in terms of eigenfunctions of a kernel, we achieve tractable inference. The method recovers known parameters, accounts for parameter indeterminacy, and shows computational scalability for catchment-sized problems.

JOURNAL OF COMPUTATIONAL PHYSICS (2022)

Add to Collection

Article Geography, Physical

The contribution of Humboldt Glacier, northern Greenland, to sea-level rise through 2100 constrained by recent observations of speedup and retreat

Trevor R. Hillebrand et al.

Summary: The retreat of the Humboldt Glacier in northern Greenland could contribute significantly to future sea-level rise. Using simulations based on a three-dimensional ice sheet model, we estimate that the sea level could rise by 5.2-8.7mm due to the continued retreat of the glacier. This prediction is higher than previous estimates and highlights the sensitivity of model predictions to basal shear stress and iceberg calving parameterizations.

CRYOSPHERE (2022)

Add to Collection

Article Geography, Physical

A new vertically integrated MOno-Layer Higher-Order (MOLHO) ice flow model

Thiago Dias dos Santos et al.

Summary: Numerical simulations of ice sheets rely on the momentum balance to determine ice velocities. This study presents a depth-integrated formulation of a higher-order model for ice sheet simulations. The results show that the new model provides comparable accuracy to the original model but with significantly lower computational time, making it suitable for long transient simulations.

CRYOSPHERE (2022)

Add to Collection

Article Geography, Physical

Constraining subglacial processes from surface velocity observations using surrogate-based Bayesian inference

Douglas Brinkerhoff et al.

Summary: The study highlights the importance of basal motion in Greenland ice flux, but notes the challenges in predicting it. By using a Bayesian approach and coupling models with observations, the study was able to infer parameter distributions. The findings show that surface velocity observations provide strong constraints on model parameters, but further data collection and model development are necessary for comprehensive understanding.

JOURNAL OF GLACIOLOGY (2021)

Add to Collection

Article Mechanics

A seamless multiscale operator neural network for inferring bubble dynamics

Chensen Lin et al.

Summary: The article introduces a seamless method based on the deep neural network DeepONet for modeling the bubble growth dynamics of multiscale systems. It can accurately predict the bubble growth process across a wide range of spatial and temporal scales.

JOURNAL OF FLUID MECHANICS (2021)

Add to Collection

Article Multidisciplinary Sciences

Projected land ice contributions to twenty-first-century sea level rise

Tamsin L. Edwards et al.

Summary: Efficient statistical emulation of melting land ice under various climate scenarios to 2100 indicates a contribution of at least 13 centimetres sea level equivalent. Limiting global warming to 1.5 degrees Celsius would halve the land ice contribution to twenty-first-century sea level rise, with glaciers responsible for half the sea level contribution. Uncertainties in the Antarctic contribution suggest a factor-of-three uncertainty in the land ice contribution until climate policies and the Antarctic response are further constrained.

NATURE (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators

Lu Lu et al.

Summary: This study extends the capabilities of neural networks with the introduction of the deep operator network (DeepONet), which can be used to learn various operators, including explicit and implicit operators. Different formulations of the input function space were studied and their effect on generalization error for 16 diverse applications was examined.

NATURE MACHINE INTELLIGENCE (2021)

Add to Collection

Article Geosciences, Multidisciplinary

Partitioning climate projection uncertainty with multiple large ensembles and CMIP5/6

Flavio Lehner et al.

EARTH SYSTEM DYNAMICS (2020)

Add to Collection

Article Geography, Physical

Brief communication: On calculating the sea-level contribution in marine ice-sheet models

Heiko Goelzer et al.

CRYOSPHERE (2020)

Add to Collection

Article Multidisciplinary Sciences

Contribution of the Greenland Ice Sheet to sea level over the next millennium

Andy Aschwanden et al.

SCIENCE ADVANCES (2019)

Add to Collection

Article Geography, Physical

Uncertainty quantification of the multi-centennial response of the Antarctic ice sheet to climate change

Kevin Bulthuis et al.

CRYOSPHERE (2019)

Add to Collection

Article Geosciences, Multidisciplinary

MPAS-Albany Land Ice (MALI): a variable-resolution ice sheet model for Earth system modeling using Voronoi grids

Matthew J. Hoffman et al.

GEOSCIENTIFIC MODEL DEVELOPMENT (2018)

Add to Collection

Article Mechanics

Mechanical error estimators for shallow ice flow models

G. Jouvet

JOURNAL OF FLUID MECHANICS (2016)

Add to Collection

Article Mathematics, Applied

OPTIMAL MODEL MANAGEMENT FOR MULTIFIDELITY MONTE CARLO ESTIMATION

Benjamin Peherstorfer et al.

SIAM JOURNAL ON SCIENTIFIC COMPUTING (2016)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Scalable and efficient algorithms for the propagation of uncertainty from data through inference to prediction for large-scale problems, with application to flow of the Antarctic ice sheet

Tobin Isaac et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2015)

Add to Collection

Article Geosciences, Multidisciplinary

Albany/FELIX: a parallel, scalable and robust, finite element, first-order Stokes approximation ice sheet solver built for advanced analysis

I. K. Tezaur et al.

GEOSCIENTIFIC MODEL DEVELOPMENT (2015)

Add to Collection

Article Engineering, Multidisciplinary

Numerical methods for the discretization of random fields by means of the Karhunen-Loeve expansion

Wolfgang Betz et al.

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING (2014)

Add to Collection

Article Geosciences, Multidisciplinary

Optimal initial conditions for coupling ice sheet models to Earth system models

Mauro Perego et al.

JOURNAL OF GEOPHYSICAL RESEARCH-EARTH SURFACE (2014)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Adaptive mesh, finite volume modeling of marine ice sheets

Stephen L. Cornford et al.

JOURNAL OF COMPUTATIONAL PHYSICS (2013)

Add to Collection

Article Geosciences, Multidisciplinary

Capabilities and performance of Elmer/Ice, a new-generation ice sheet model

O. Gagliardini et al.

GEOSCIENTIFIC MODEL DEVELOPMENT (2013)

Add to Collection

Article Geography, Physical

Data assimilation and prognostic whole ice sheet modelling with the variationally derived, higher order, open source, and fully parallel ice sheet model VarGlaS

D. J. Brinkerhoff et al.

CRYOSPHERE (2013)

Add to Collection

Article Geosciences, Multidisciplinary

A parallel high-order accurate finite element nonlinear Stokes ice sheet model and benchmark experiments

Wei Leng et al.

JOURNAL OF GEOPHYSICAL RESEARCH-EARTH SURFACE (2012)

Add to Collection

Article Geosciences, Multidisciplinary

Continental scale, high order, high spatial resolution, ice sheet modeling using the Ice Sheet System Model (ISSM)

E. Larour et al.

JOURNAL OF GEOPHYSICAL RESEARCH-EARTH SURFACE (2012)

Add to Collection

Article Geography, Physical

Parallel finite-element implementation for higher-order ice-sheet models

Mauro Perego et al.

JOURNAL OF GLACIOLOGY (2012)

Add to Collection

Article Geography, Physical

A variationally derived, depth-integrated approximation to a higher-order glaciological flow model

Daniel N. Goldberg

JOURNAL OF GLACIOLOGY (2011)

Add to Collection

Article Geography, Physical

Consistent approximations and boundary conditions for ice-sheet dynamics from a principle of least action

John K. Dukowicz et al.

JOURNAL OF GLACIOLOGY (2010)

Add to Collection

Article Geosciences, Multidisciplinary

Shallow shelf approximation as a sliding law'' in a thermomechanically coupled ice sheet model

Ed Bueler et al.

JOURNAL OF GEOPHYSICAL RESEARCH-EARTH SURFACE (2009)

Add to Collection

Article Computer Science, Artificial Intelligence

Universal approximation of multiple nonlinear operators by neural networks

AD Back et al.

NEURAL COMPUTATION (2002)

Add to Collection

© Peeref 2019-2024. All rights reserved.