Discovering Spatial Correlations of Earth Observations for weather forecasting by using Graph Structure Learning

• URL: http://arxiv.org/abs/2508.07659v2
• Date: Mon, 10 Nov 2025 02:06:30 GMT
• Title: Discovering Spatial Correlations of Earth Observations for weather forecasting by using Graph Structure Learning
• Authors: Hyeon-Ju Jeon, Jeon-Ho Kang, In-Hyuk Kwon, O-Joun Lee,
• Abstract summary: This study aims to improve the accuracy of weather predictions by discovering spatial correlations between Earth observations and atmospheric states.<n>We employ atemporal graph neural networks (STGNNs) with structure learning to solve this problem.<n>We validated the effectiveness of the proposed method using real-world atmospheric state and observation data from East Asia.
• Score: 4.794822439017277
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This study aims to improve the accuracy of weather predictions by discovering spatial correlations between Earth observations and atmospheric states. Existing numerical weather prediction (NWP) systems predict future atmospheric states at fixed locations, which are called NWP grid points, by analyzing previous atmospheric states and newly acquired Earth observations. However, the shifting locations of observations and the surrounding meteorological context induce complex, dynamic spatial correlations that are difficult for traditional NWP systems to capture, since they rely on strict statistical and physical formulations. To handle complicated spatial correlations, which change dynamically, we employ a spatiotemporal graph neural networks (STGNNs) with structure learning. However, structure learning has an inherent limitation that this can cause structural information loss and over-smoothing problem by generating excessive edges. To solve this problem, we regulate edge sampling by adaptively determining node degrees and considering the spatial distances between NWP grid points and observations. We validated the effectiveness of the proposed method (CloudNine-v2) using real-world atmospheric state and observation data from East Asia, achieving up to 15\% reductions in RMSE over existing STGNN models. Even in areas with high atmospheric variability, CloudNine-v2 consistently outperformed baselines with and without structure learning.

Related papers

• From Observations to States: Latent Time Series Forecasting [65.98504021691666]
  We propose Latent Time Series Forecasting (LatentTSF), a novel paradigm that shifts TSF from observation regression to latent state prediction.<n>Specifically, LatentTSF employs an AutoEncoder to project observations at each time step into a higher-dimensional latent state space.<n>Our proposed latent objectives implicitly maximize mutual information between predicted latent states and ground-truth states and observations.
  arXiv  Detail & Related papers  (2026-01-30T20:39:44Z)
• S$^2$Transformer: Scalable Structured Transformers for Global Station Weather Forecasting [67.93713728260646]
  Existing time series forecasting methods often ignore or unidirectionally model spatial correlation when conducting large-scale global station forecasting.<n>This contradicts the nature underlying observations of the global weather system limiting forecast performance.<n>We propose a novel Structured Spatial Attention in this paper.<n>It partitions the spatial graph into a set of subgraphs and instantiates Intra-subgraph Attention to learn local spatial correlation within each subgraph.<n>It aggregates nodes into subgraph representations for message passing among the subgraphs via Inter-subgraph Attention -- considering both spatial proximity and global correlation.
  arXiv  Detail & Related papers  (2025-09-10T05:33:28Z)
• Satellite Observations Guided Diffusion Model for Accurate Meteorological States at Arbitrary Resolution [48.34051432429767]
  We propose a conditional diffusion model pre-trained on ERA5 reanalysis data with satellite observations (GridSat) as conditions.<n>During the training process, we propose to fuse the information from GridSat satellite observations into ERA5 maps via the attention mechanism.<n>In the sampling, we employed optimizable convolutional kernels to simulate the upscale process.
  arXiv  Detail & Related papers  (2025-02-09T02:05:33Z)
• Kolmogorov Arnold Neural Interpolator for Downscaling and Correcting Meteorological Fields from In-Situ Observations [32.5581352874406]
  We propose the Kolmogorov Arnold Neural Interpolator (KANI), a framework that redefines meteorological field representation as continuous neural functions.<n>KANI captures the inherent continuity of atmospheric states and leverages sparse in-situ observations to correct these biases systematically.<n> Experimental results indicate that KANI achieves an accuracy improvement of 40.28% for temperature and 67.41% for wind speed.
  arXiv  Detail & Related papers  (2025-01-24T11:18:19Z)
• MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling [68.69647625472464]
  Downscaling, a crucial task in meteorological forecasting, enables the reconstruction of high-resolution meteorological states for target regions. Previous downscaling methods lacked tailored designs for meteorology and encountered structural limitations. We propose a novel model called MambaDS, which enhances the utilization of multivariable correlations and topography information.
  arXiv  Detail & Related papers  (2024-08-20T13:45:49Z)
• Generating Fine-Grained Causality in Climate Time Series Data for Forecasting and Anomaly Detection [67.40407388422514]
  We design a conceptual fine-grained causal model named TBN Granger Causality. Second, we propose an end-to-end deep generative model called TacSas, which discovers TBN Granger Causality in a generative manner. We test TacSas on climate benchmark ERA5 for climate forecasting and the extreme weather benchmark of NOAA for extreme weather alerts.
  arXiv  Detail & Related papers  (2024-08-08T06:47:21Z)
• Explainable Graph Neural Networks for Observation Impact Analysis in Atmospheric State Estimation [1.7410069559220338]
  We integrate observation and Numerical Weather Prediction points into a meteorological graph, extracting $k$-hop subgraphs centered on NWP points. Self-supervised GNNs are employed to estimate the atmospheric state by aggregating data within these $k$-hop radii. The study applies gradient-based explainability methods to quantify the significance of different observations in the estimation process.
  arXiv  Detail & Related papers  (2024-03-26T05:10:47Z)
• CloudNine: Analyzing Meteorological Observation Impact on Weather Prediction Using Explainable Graph Neural Networks [1.9019250262578853]
  CloudNine'' allows analysis of individual observations' impacts on specific predictions based on explainable graph neural networks (XGNNs) We provide a web application to search for observations in the 3D space of the Earth system and to visualize the impact of individual observations on predictions in specific spatial regions and time periods.
  arXiv  Detail & Related papers  (2024-02-21T01:29:17Z)
• VN-Net: Vision-Numerical Fusion Graph Convolutional Network for Sparse Spatio-Temporal Meteorological Forecasting [12.737085738169164]
  VN-Net is the first attempt to introduce GCN method to utilize multi-modal data for better handling sparse-temporal meteorological forecasting. VN-Net outperforms state-of-the-art by a significant margin on mean absolute error (MAE) and root mean square error (RMSE) for temperature, relative humidity, and forecasting.
  arXiv  Detail & Related papers  (2024-01-26T12:41:57Z)
• Observation-Guided Meteorological Field Downscaling at Station Scale: A Benchmark and a New Method [66.80344502790231]
  We extend meteorological downscaling to arbitrary scattered station scales and establish a new benchmark and dataset. Inspired by data assimilation techniques, we integrate observational data into the downscaling process, providing multi-scale observational priors. Our proposed method outperforms other specially designed baseline models on multiple surface variables.
  arXiv  Detail & Related papers  (2024-01-22T14:02:56Z)
• WeatherGNN: Exploiting Meteo- and Spatial-Dependencies for Local Numerical Weather Prediction Bias-Correction [11.10401300641113]
  We propose WeatherGNN, a local NWP bias-correction method that exploits meteorological dependencies and spatial dependencies under the guidance of domain knowledge. Our experimental results on two real-world datasets demonstrate that WeatherGNN achieves the state-of-the-art performance, outperforming the best baseline with an average of 4.75 % on RMSE.
  arXiv  Detail & Related papers  (2023-10-09T08:33:19Z)
• Convolutional GRU Network for Seasonal Prediction of the El Ni\~no-Southern Oscillation [24.35408676030181]
  We present a modified Convolutional Gated Recurrent Unit (ConvGRU) network for the El Nino-Southern Oscillation (ENSO) region-temporal sequence prediction problem. The proposed ConvGRU network, with an encoder-decoder sequence-to-sequence structure, takes historical SST maps of the Pacific region as input and generates future SST maps for subsequent months within the ENSO region. The results demonstrate that the ConvGRU network significantly improves the predictability of the Nino 3.4 index compared to LIM, AF, and RNN.
  arXiv  Detail & Related papers  (2023-06-18T00:15:45Z)
• Federated Prompt Learning for Weather Foundation Models on Devices [37.88417074427373]
  On-device intelligence for weather forecasting uses local deep learning models to analyze weather patterns without centralized cloud computing. This paper propose Federated Prompt Learning for Weather Foundation Models on Devices (FedPoD) FedPoD enables devices to obtain highly customized models while maintaining communication efficiency.
  arXiv  Detail & Related papers  (2023-05-23T16:59:20Z)
• Forecasting large-scale circulation regimes using deformable convolutional neural networks and global spatiotemporal climate data [86.1450118623908]
  We investigate a supervised machine learning approach based on deformable convolutional neural networks (deCNNs) We forecast the North Atlantic-European weather regimes during extended boreal winter for 1 to 15 days into the future. Due to its wider field of view, we also observe deCNN achieving considerably better performance than regular convolutional neural networks at lead times beyond 5-6 days.
  arXiv  Detail & Related papers  (2022-02-10T11:37:00Z)
• HiSTGNN: Hierarchical Spatio-temporal Graph Neural Networks for Weather Forecasting [13.317147032467306]
  We propose a novel Graph Hierarchical Spatio-Temporal Neural Network (HiSTGNN) to model cross-regional-temporal correlations among meteorological variables in multiple stations. Experimental results on three real-world meteorological datasets demonstrate the superior performance of HiSTGNN beyond 7 baselines. It reduces the errors by 4.2% to 11.6% especially compared to state-of-the-art weather forecasting method.
  arXiv  Detail & Related papers  (2022-01-22T17:30:46Z)
• Deep Learning Based Cloud Cover Parameterization for ICON [55.49957005291674]
  We train NN based cloud cover parameterizations with coarse-grained data based on realistic regional and global ICON simulations. Globally trained NNs can reproduce sub-grid scale cloud cover of the regional simulation. We identify an overemphasis on specific humidity and cloud ice as the reason why our column-based NN cannot perfectly generalize from the global to the regional coarse-grained data.
  arXiv  Detail & Related papers  (2021-12-21T16:10:45Z)

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.