Spatial Support Matters: Geometry-Aware Graph Fusion for Rainfall Field Reconstruction
Quick Answer
The proposed geometry-aware multi-support heterogeneous graph neural network significantly improves fine-scale rainfall reconstruction, achieving a 23.2% RMSE reduction over classical methods.
Quick Take
This model effectively integrates diverse spatial supports, outperforming convolutional fusion and support-agnostic baselines, particularly in under-sampled areas.
Key Points
- Introduces a geometry-aware multi-support graph neural network for rainfall reconstruction.
- Achieves 23.2% RMSE reduction compared to classical interpolation methods.
- Outperforms convolutional fusion and support-agnostic models on Singapore data.
- Generalization study shows effectiveness depends on gauge spacing relative to correlation length.
- Code and models will be open-sourced upon paper acceptance.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Fine-scale rainfall reconstruction is critical for urban flood modeling, but real rainfall sensing systems observe the field through incompatible spatial supports: gauges measure points, microwave links measure paths, and radar/satellite products measure gridded areas. These differences in measurement support impose geometrically distinct constraints on the rainfall field, yet existing heterogeneous graph approaches reconcile such sources in feature space, giving each its own embedding while discarding the geometry of its support. We propose a geometry-aware multi-support heterogeneous graph neural network that represents each observation according to its support type (0D point, 1D line, or 2D grid) as a distinct node layer, and fuses them through cross-support message passing into a point-support prediction layer from which the field is reconstructed. An inductive masked-node formulation decouples prediction resolution from sensing resolution, allowing the same trained model to reconstruct the field at user-defined target locations or display grids. On Singapore data, the proposed method reduces RMSE by 23.2\% over the classical interpolation baseline, inverse-distance weighting, and consistently outperforms other neural architectures such as convolutional fusion and support-agnostic heterogeneous graph baselines. A generalization study using data from Sydney, Australia lets us characterize when multi-support fusion helps: the available skill appears to depend on gauge spacing relative to the spatial correlation length of the field, so fusion delivers the largest gains where the field is under-sampled relative to its correlation length and little when it is already resolved. Code and models will be open-sourced upon paper acceptance.
| Comments: | Submitted to WACV 2027, applications track |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.01621 [cs.AI] |
| (or arXiv:2607.01621v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.01621 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sanka Rasnayaka [view email]
[v1]
Thu, 2 Jul 2026 02:38:59 UTC (3,619 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.