Graph convolutional network as a fast statistical emulator for numerical ice sheet modeling

Αποθηκεύτηκε σε:
Λεπτομέρειες βιβλιογραφικής εγγραφής
Εκδόθηκε σε:Journal of Glaciology vol. 71 (2025)
Κύριος συγγραφέας: Koo, Younghyun
Άλλοι συγγραφείς: Rahnemoonfar, Maryam
Έκδοση:
Cambridge University Press
Θέματα:
Διαθέσιμο Online:Citation/Abstract
Full Text
Full Text - PDF
Ετικέτες: Προσθήκη ετικέτας
Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!

MARC

LEADER 00000nab a2200000uu 4500
001 3154589723
003 UK-CbPIL
022 |a 0022-1430 
022 |a 1727-5652 
024 7 |a 10.1017/jog.2024.93  |2 doi 
035 |a 3154589723 
045 2 |b d20250101  |b d20251231 
100 1 |a Koo, Younghyun  |u Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA, USA; Department of Civil and Environmental Engineering, Lehigh University, Bethlehem, PA, USA 
245 1 |a Graph convolutional network as a fast statistical emulator for numerical ice sheet modeling 
260 |b Cambridge University Press  |c 2025 
513 |a Journal Article 
520 3 |a The Ice-sheet and Sea-level System Model (ISSM) provides numerical solutions for ice sheet dynamics using finite element and fine mesh adaption. However, considering ISSM is compatible only with central processing units (CPUs), it has limitations in economizing computational time to explore the linkage between climate forcings and ice dynamics. Although several deep learning emulators using graphic processing units (GPUs) have been proposed to accelerate ice sheet modeling, most of them rely on convolutional neural networks (CNNs) designed for regular grids. Since they are not appropriate for the irregular meshes of ISSM, we use a graph convolutional network (GCN) to replicate the adapted mesh structures of the ISSM. When applied to transient simulations of the Pine Island Glacier (PIG), Antarctica, the GCN successfully reproduces ice thickness and velocity with a correlation coefficient of approximately 0.997, outperforming non-graph models, including fully convolutional network (FCN) and multi-layer perceptron (MLP). Compared to the fixed-resolution approach of the FCN, the flexible-resolution structure of the GCN accurately captures detailed ice dynamics in fast-ice regions. By leveraging 60–100 times faster computational time of the GPU-based GCN emulator, we efficiently examine the impacts of basal melting rates on the ice sheet dynamics in the PIG. 
651 4 |a Pine Island Glacier 
651 4 |a Greenland 
651 4 |a Antarctica 
653 |a Glaciers 
653 |a Ice thickness 
653 |a Central processing units--CPUs 
653 |a Deep learning 
653 |a Mathematical analysis 
653 |a Ice cover 
653 |a Multilayers 
653 |a Sea level 
653 |a Artificial neural networks 
653 |a Multilayer perceptrons 
653 |a Ice sheet dynamics 
653 |a Neural networks 
653 |a Approximation 
653 |a Computer applications 
653 |a Machine learning 
653 |a Correlation coefficient 
653 |a Sheet modelling 
653 |a Correlation coefficients 
653 |a Statistical models 
653 |a Glaciation 
653 |a Velocity 
653 |a Modelling 
653 |a Partial differential equations 
653 |a Ice 
653 |a Emulators 
653 |a Graphs 
653 |a Graphics processing units 
653 |a Ice sheets 
653 |a Dynamics 
653 |a Information processing 
653 |a Ice environments 
653 |a Computing time 
653 |a Shear stress 
653 |a Environmental 
700 1 |a Rahnemoonfar, Maryam  |u Department of Computer Science and Engineering, Lehigh University, Bethlehem, PA, USA; Department of Civil and Environmental Engineering, Lehigh University, Bethlehem, PA, USA 
773 0 |t Journal of Glaciology  |g vol. 71 (2025) 
786 0 |d ProQuest  |t Research Library 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3154589723/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/3154589723/fulltext/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3154589723/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch