Graph Neural Networks as Fast and High-fidelity Emulators for
Finite-Element Ice Sheet Modeling
- URL: http://arxiv.org/abs/2402.05291v1
- Date: Wed, 7 Feb 2024 22:10:36 GMT
- Title: Graph Neural Networks as Fast and High-fidelity Emulators for
Finite-Element Ice Sheet Modeling
- Authors: Maryam Rahnemoonfar, Younghyun Koo
- Abstract summary: We develop graph neural networks (GNNs) as fast surrogate models to preserve the finite element structure of the Ice-sheet and Sea-level System Model (ISSM)
GNNs reproduce ice thickness and velocity with better accuracy than the classic convolutional neural network (CNN) and multi-layer perception (MLP)
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Although the finite element approach of the Ice-sheet and Sea-level System
Model (ISSM) solves ice dynamics problems governed by Stokes equations quickly
and accurately, such numerical modeling requires intensive computation on
central processing units (CPU). In this study, we develop graph neural networks
(GNN) as fast surrogate models to preserve the finite element structure of
ISSM. Using the 20-year transient simulations in the Pine Island Glacier (PIG),
we train and test three GNNs: graph convolutional network (GCN), graph
attention network (GAT), and equivariant graph convolutional network (EGCN).
These GNNs reproduce ice thickness and velocity with better accuracy than the
classic convolutional neural network (CNN) and multi-layer perception (MLP). In
particular, GNNs successfully capture the ice mass loss and acceleration
induced by higher basal melting rates in the PIG. When our GNN emulators are
implemented on graphic processing units (GPUs), they show up to 50 times faster
computational time than the CPU-based ISSM simulation.
Related papers
- CondensNet: Enabling stable long-term climate simulations via hybrid deep learning models with adaptive physical constraints [12.564238759484962]
Current general circulation models (GCMs) face challenges in capturing unresolved physical processes, such as cloud and convection.
Cloud resolving models, also referred to as super paramtetrizations, remain computationally prohibitive.
We introduce CondensNet, a novel neural network architecture that embeds a self-adaptive physical constraint to correct unphysical condensation processes.
arXiv Detail & Related papers (2025-02-18T11:11:17Z) - Learning Effective Dynamics across Spatio-Temporal Scales of Complex Flows [4.798951413107239]
We propose a novel framework, Graph-based Learning of Effective Dynamics (Graph-LED), that leverages graph neural networks (GNNs) and an attention-based autoregressive model.
We evaluate the proposed approach on a suite of fluid dynamics problems, including flow past a cylinder and flow over a backward-facing step over a range of Reynolds numbers.
arXiv Detail & Related papers (2025-02-11T22:14:30Z) - Graph Neural Network as Computationally Efficient Emulator of Ice-sheet and Sea-level System Model (ISSM) [0.0]
We design a graph convolutional network (GCN) as a fast emulator for the Ice-sheet and Sea-level System Model (ISSM)
GCN shows 34 times faster computational speed than the CPU-based ISSM modeling.
arXiv Detail & Related papers (2024-06-26T16:13:11Z) - Graph Neural Networks for Emulation of Finite-Element Ice Dynamics in Greenland and Antarctic Ice Sheets [0.0]
equivariant graph convolutional network (EGCN) is an emulator for the ice sheet dynamics modeling.
EGCN reproduces ice thickness and velocity changes in the Helheim Glacier, Greenland, and Pine Island Glacier, Antarctica, with 260 times and 44 times faster computation time, respectively.
arXiv Detail & Related papers (2024-06-26T15:18:49Z) - Machine Learning Parameterization of the Multi-scale Kain-Fritsch (MSKF)
Convection Scheme [6.912451798457824]
Warm-sector heavy rainfall often occurs along the coast of South China.
The turbulent eddies in the atmospheric boundary layer are only partially resolved and parameterized to some extent in the gray zone.
In recent years, there has been an increasing application of machine learning (ML) models to various domains of atmospheric sciences.
arXiv Detail & Related papers (2023-11-07T01:47:16Z) - Graph Neural Networks for Temperature-Dependent Activity Coefficient
Prediction of Solutes in Ionic Liquids [58.720142291102135]
We present a GNN to predict temperature-dependent infinite dilution ACs of solutes in ILs.
We train the GNN on a database including more than 40,000 AC values and compare it to a state-of-the-art MCM.
The GNN and MCM achieve similar high prediction performance, with the GNN additionally enabling high-quality predictions for ACs of solutions that contain ILs and solutes not considered during training.
arXiv Detail & Related papers (2022-06-23T15:27:29Z) - Space-Time Graph Neural Networks [104.55175325870195]
We introduce space-time graph neural network (ST-GNN) to jointly process the underlying space-time topology of time-varying network data.
Our analysis shows that small variations in the network topology and time evolution of a system does not significantly affect the performance of ST-GNNs.
arXiv Detail & Related papers (2021-10-06T16:08:44Z) - Machine learning for rapid discovery of laminar flow channel wall
modifications that enhance heat transfer [56.34005280792013]
We present a combination of accurate numerical simulations of arbitrary, flat, and non-flat channels and machine learning models predicting drag coefficient and Stanton number.
We show that convolutional neural networks (CNN) can accurately predict the target properties at a fraction of the time of numerical simulations.
arXiv Detail & Related papers (2021-01-19T16:14:02Z) - Temporal Attention-Augmented Graph Convolutional Network for Efficient
Skeleton-Based Human Action Recognition [97.14064057840089]
Graphal networks (GCNs) have been very successful in modeling non-Euclidean data structures.
Most GCN-based action recognition methods use deep feed-forward networks with high computational complexity to process all skeletons in an action.
We propose a temporal attention module (TAM) for increasing the efficiency in skeleton-based action recognition.
arXiv Detail & Related papers (2020-10-23T08:01:55Z) - Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid
Flow Prediction [79.81193813215872]
We develop a hybrid (graph) neural network that combines a traditional graph convolutional network with an embedded differentiable fluid dynamics simulator inside the network itself.
We show that we can both generalize well to new situations and benefit from the substantial speedup of neural network CFD predictions.
arXiv Detail & Related papers (2020-07-08T21:23:19Z) - Toward fast and accurate human pose estimation via soft-gated skip
connections [97.06882200076096]
This paper is on highly accurate and highly efficient human pose estimation.
We re-analyze this design choice in the context of improving both the accuracy and the efficiency over the state-of-the-art.
Our model achieves state-of-the-art results on the MPII and LSP datasets.
arXiv Detail & Related papers (2020-02-25T18:51:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.