Learning Spatio-Temporal Patterns of Polar Ice Layers With Physics-Informed Graph Neural Network

• URL: http://arxiv.org/abs/2406.15299v1
• Date: Fri, 21 Jun 2024 16:41:02 GMT
• Title: Learning Spatio-Temporal Patterns of Polar Ice Layers With Physics-Informed Graph Neural Network
• Authors: Zesheng Liu, Maryam Rahnemoonfar,
• Abstract summary: We propose a physics-informed hybrid graph neural network that combines the GraphSAGE framework for graph feature learning with the long short-term memory (LSTM) structure for learning temporal changes. We found that our network can consistently outperform the current non-inductive or non-physical model in predicting deep ice layer thickness.
• Score: 0.7673339435080445
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning spatio-temporal patterns of polar ice layers is crucial for monitoring the change in ice sheet balance and evaluating ice dynamic processes. While a few researchers focus on learning ice layer patterns from echogram images captured by airborne snow radar sensors via different convolutional neural networks, the noise in the echogram images proves to be a major obstacle. Instead, we focus on geometric deep learning based on graph neural networks to learn the spatio-temporal patterns from thickness information of shallow ice layers and make predictions for deep layers. In this paper, we propose a physics-informed hybrid graph neural network that combines the GraphSAGE framework for graph feature learning with the long short-term memory (LSTM) structure for learning temporal changes, and introduce measurements of physical ice properties from Model Atmospheric Regional (MAR) weather model as physical node features. We found that our proposed network can consistently outperform the current non-inductive or non-physical model in predicting deep ice layer thickness.

Related papers

• Multi-branch Spatio-Temporal Graph Neural Network For Efficient Ice Layer Thickness Prediction [0.7673339435080445]
  We developed a multi-branch-temporal graph neural network that used the GraphSS framework for learning and a temporal convolution operation to capture temporal changes. We found that our proposed multi-branch network can consistently outperform the current fused-temporal graph neural network in both accuracy and efficiency.
  arXiv  Detail & Related papers  (2024-11-06T16:59:51Z)
• Exploring Geometric Deep Learning For Precipitation Nowcasting [28.44612565923532]
  We propose a geometric deep learning-based temporal Graph Convolutional Network (GCN) for precipitation nowcasting. The adjacency matrix that simulates the interactions among grid cells is learned automatically by minimizing the L1 loss between prediction and ground truth pixel value. We test the model on sequences of radar reflectivity maps over the Trento/Italy area.
  arXiv  Detail & Related papers  (2023-09-11T21:14:55Z)
• Prediction of Deep Ice Layer Thickness Using Adaptive Recurrent Graph Neural Networks [0.38073142980732994]
  We propose a machine learning model that uses adaptive, recurrent graph convolutional networks to predict snow accumulation. We found that our model performs better and with greater consistency than our previous model as well as equivalent non-temporal, non-geometric, and non-adaptive models.
  arXiv  Detail & Related papers  (2023-06-22T19:59:54Z)
• Dynamic Causal Explanation Based Diffusion-Variational Graph Neural Network for Spatio-temporal Forecasting [60.03169701753824]
  We propose a novel Dynamic Diffusion-al Graph Neural Network (DVGNN) fortemporal forecasting. The proposed DVGNN model outperforms state-of-the-art approaches and achieves outstanding Root Mean Squared Error result.
  arXiv  Detail & Related papers  (2023-05-16T11:38:19Z)
• Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks [80.8446673089281]
  We study a new paradigm of knowledge transfer that aims at encoding graph topological information into graph neural networks (GNNs) We propose Neural Heat Kernel (NHK) to encapsulate the geometric property of the underlying manifold concerning the architecture of GNNs. A fundamental and principled solution is derived by aligning NHKs on teacher and student models, dubbed as Geometric Knowledge Distillation.
  arXiv  Detail & Related papers  (2022-10-24T08:01:58Z)
• Dynamic Analysis of Nonlinear Civil Engineering Structures using Artificial Neural Network with Adaptive Training [2.1202971527014287]
  In this study, artificial neural networks are developed with adaptive training algorithms. The networks can successfully predict the time-history response of the shear frame and the rock structure to real ground motion records.
  arXiv  Detail & Related papers  (2021-11-21T21:14:48Z)
• Probabilistic modeling of lake surface water temperature using a Bayesian spatio-temporal graph convolutional neural network [55.41644538483948]
  We propose to aggregate simulations of lake temperature at a certain depth together with a range of meteorological features. This work demonstrates that the proposed model can deliver homogeneously good performance covering the whole lake surface. Results are compared with a state-of-the-art Bayesian deep learning method.
  arXiv  Detail & Related papers  (2021-09-27T09:19:53Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• Learning Contact Dynamics using Physically Structured Neural Networks [81.73947303886753]
  We use connections between deep neural networks and differential equations to design a family of deep network architectures for representing contact dynamics between objects. We show that these networks can learn discontinuous contact events in a data-efficient manner from noisy observations. Our results indicate that an idealised form of touch feedback is a key component of making this learning problem tractable.
  arXiv  Detail & Related papers  (2021-02-22T17:33:51Z)
• Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition [126.51241919472356]
  We design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition. Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
  arXiv  Detail & Related papers  (2020-11-26T14:43:04Z)

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.