.png){kind=icon}
.png){kind=icon}
Return
Toward Nonuniformly Distributed Weather Forecasting: Adaptive Filtered Hypergraph Convolution Network
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2025.3640219.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Weather forecasting, compared to other multivariate time-series prediction tasks, exhibits notably nonuniform distribution of observation sites. The prevailing approaches primarily leverage graph convolutional neural networks (GCNs) to extract spatial features. However, some studies suggest that the poor performance on uneven graphs is primarily due to the fact that traditional graph neural networks (GNNs) are essentially low-pass filters, discarding information beyond low-frequency information on the graph. From another perspective, since the essence of graph convolution is the smoothing of node features, for uneven graphs, there are noticeable differences in the smoothing rates of node features, leading to the coexistence of overfitting and underfitting phenomena. This issue is further exacerbated in higher order graph structures, such as hypergraphs, due to the irregular and complex nature of hyperedges. To address this issue, we propose a filtered hypergraph neural network. Building on the calculation of hypergraph node smoothing rates, we balance the low-pass and high-pass filter convolutions’ feature extraction through a dual-stream architecture. On uneven graphs, it can be observed that neglecting high-frequency information and concentrating solely on low-frequency information impede the learning of node representations, thereby significantly affecting the performance of downstream prediction tasks. We conducted multidimensional time-series prediction experiments using meteorological data, and the results demonstrate that our model performs with high accuracy in node regression tasks across multiple channels.
Keywords:
Graph neural network (GNN)
hypergraph
weather forecasting
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W