skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Graph convolutional network as a fast statistical emulator for numerical ice sheet modeling
Abstract 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.  more » « less
Award ID(s):
2308649
PAR ID:
10566776
Author(s) / Creator(s):
;
Publisher / Repository:
Cambridge University Press
Date Published:
Journal Name:
Journal of Glaciology
Volume:
71
ISSN:
0022-1430
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, AGU23 Online Program)
    Tedesco, Marco; Lai, Ching_Yao; Brinkerhoff, Douglas; Stearns, Leigh (Ed.)
    Emulators of ice flow models have shown promise for speeding up simulations of glaciers and ice sheets. Existing ice flow emulators have relied primarily on convolutional neural networks (CNN’s), which assume that model inputs and outputs are discretized on a uniform computational grid. However, many existing finite element-based ice sheet models such as the Ice-Sheet and Sea-level System model (ISSM) benefit from their ability to use unstructured computational meshes. Unstructured meshes allow for greater flexibility and computational efficiency in many modeling scenarios. In this work, we present an emulator of a higher order, finite element ice flow model based on a graph neural network (GNN) architecture. In this architecture, an unstructured finite element mesh is represented as a graph, with inputs and outputs of the ice flow model represented as variables on graph nodes and edges. An advantage of this approach is that the ice flow emulator can interface directly with a standard finite element –based ice sheet model by mapping between the finite element mesh and a graph suitable for the GNN emulator. We test the ability of the GNN to predict velocity fields on complex mountain glacier geometries and show how the emulated velocity can be used to solve for mass continuity using a standard finite element approach. 
    more » « less
  2. ; ; (, IEEE)
    Graph Convolutional Networks (GCNs) have successfully incorporated deep learning to graph structures for social network analysis, bio-informatics, etc. The execution pattern of GCNs is a hybrid of graph processing and neural networks which poses unique and significant challenges for hardware implementation. Graph processing involves a large amount of irregular memory access with little computation whereas processing of neural networks involves a large number of operations with regular memory access. Existing graph processing and neural network accelerators are therefore inefficient for computing GCNs. This paper presents Parag, processing in memory (PIM) architecture for GCN computation. It consists of customized logic with minuscule computing units called Neural Processing Elements (NPEs) interfaced to each bank of the DRAM to support parallel graph processing and neural network computation. It utilizes the massive internal parallelism of DRAM to accelerate the GCN execution with high energy efficiency. Simulation results for inference of GCN over standard datasets show a latency and energy reduction by three orders of magnitude over a CPU implementation. When compared to a state-of-the-art PIM architecture, PARAG achieves on an average 4x reduction in latency and 4.23x reduction in the energy-delay-product (EDP). 
    more » « less
  3. ; ; ; ; ; ; ; ; (, The cryosphere)
    Abstract. The Greenland Ice Sheet's negative mass balance is driven by a sensitivity to both a warming atmosphere and ocean. The fidelity of ice-sheet models in accounting for ice-ocean interaction is inherently uncertain and often constrained against recent fluctuations in the ice-sheet margin from the previous decades. The geological record can be utilised to contextualise ice-sheet mass loss and understand the drivers of changes at the marine margin across climatic shifts and previous extended warm periods, aiding our understanding of future ice-sheet behaviour. Here, we use the Ice-sheet and Sea-level System Model (ISSM) to explore the Holocene evolution of Ryder Glacier draining into Sherard Osborn Fjord, Northern Greenland. Our modelling results are constrained with terrestrial reconstructions of the paleo-ice sheet margin and an extensive marine sediment record from Sherard Osborn Fjord that details ice dynamics over the past 12.5 ka years. By employing a consistent mesh resolution of <1 km at the ice-ocean boundary, we assess the importance of atmospheric and oceanic changes to Ryder Glacier's Holocene behaviour. Our simulations show that the initial retreat of the ice margin after the Younger Dryas cold period was driven by a warming climate and the resulting fluctuations in Surface Mass Balance. Changing atmospheric conditions remain the first order control in the timing of ice retreat during the Holocene. We find ice-ocean interactions become increasingly fundamental to Ryder's retreat in the mid-Holocene; with higher than contemporary melt rates required to force grounding line retreat and capture the collapse of the ice tongue during the Holocene Thermal Maximum. Regrowth of the tongue during the neo-glacial cooling of the late Holocene is necessary to advance both the terrestrial and marine margins of the glacier. Our results stress the importance of accurately resolving the ice-ocean interface in modelling efforts over centennial and millennial time scales, in particular the role of floating ice tongues and submarine melt, and provide vital analogous for the future evolution of Ryder in a warming climate. 
    more » « less
  4. ; (, Machine Learning: Science and Technology)
    Abstract We define a novel type of ensemble graph convolutional network (GCN) model. Using optimized linear projection operators to map between spatial scales of graph, this ensemble model learns to aggregate information from each scale for its final prediction. We calculate these linear projection operators as the infima of an objective function relating the structure matrices used for each GCN. Equipped with these projections, our model (a Graph Prolongation-Convolutional Network) outperforms other GCN ensemble models at predicting the potential energy of monomer subunits in a coarse-grained mechanochemical simulation of microtubule bending. We demonstrate these performance gains by measuring an estimate of the Floating Point OPerations spent to train each model, as well as wall-clock time. Because our model learns at multiple scales, it is possible to train at each scale according to a predetermined schedule of coarse vs. fine training. We examine several such schedules adapted from the algebraic multigrid literature, and quantify the computational benefit of each. We also compare this model to another model which features an optimized coarsening of the input graph. Finally, we derive backpropagation rules for the input of our network model with respect to its output, and discuss how our method may be extended to very large graphs. 
    more » « less
  5. ; ; (, Journal of Manufacturing Science and Engineering)
    Abstract Milling is a critical manufacturing process to produce high-value components in aerospace, tooling, and automotive industries. However, milling is prone to chatter, a severe vibration that damages surface quality, cutting tools, and machines. Traditional experimental and mechanistic methods of chatter prediction have significant limitations. This study presents a data-driven machine learning (ML) model to predict and quantify milling chatter directly based on time-series vibration data. Three ML models, including hybrid long short-term memory (LSTM)—fully convolutional network (FCN) model, gated recurrent unit (GRU)—FCN model, and temporal convolutional network (TCN) models, have been developed and verified by incorporating milling parameters to enhance prediction accuracy and stability. Among the proposed models, the best-performing ML model (GRU-FCN) demonstrates strong performance in chatter prediction and severity quantification, providing actionable insights with improved computational efficiency. The integration of milling parameters into the ML model notably enhances the prediction accuracy and stability, proving particularly effective in real-time monitoring scenarios. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email