[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-327165-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-327165-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","spatial-support-matters-geometry-aware-graph-fusion-for-rainfall-field-reconstruction-inferred","Spatial Support Matters - Geometry-Aware Graph Fusion for Rainfall Field Reconstruction - [Inferred]","","Fine-scale rainfall reconstruction is essential for urban flood modeling, yet sensing systems observe the same field through incompatible spatial supports: point gauges, path-integrated microwave links, and gridded radar/satellite products. These distinct supports impose different geometric constraints, while prior heterogeneous graph methods often ignore support geometry. The proposed geometry-aware multi-support heterogeneous GNN uses support-typed node layers (0D/1D/2D) with cross-support message passing into a point prediction layer. An inductive masked-node formulation enables reconstruction at user-defined locations and grids, reducing RMSE by 23.2% on Singapore data and identifying when multi-support fusion helps via undersampling relative to correlation length.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/spatial-support-matters-geometry-aware-graph-fusion-for-rainfall-field-reconstruction-inferred/327165/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/spatial-support-matters-geometry-aware-graph-fusion-for-rainfall-field-reconstruction-inferred/327165.png","ImageObject",300,407,{"name":42,"@type":43},"Eliana","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-03","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",17,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is rainfall-field reconstruction difficult across real sensing systems?","Question",{"text":63,"@type":64},"Because different instruments measure the same rainfall field using incompatible spatial supports: gauges sample points, microwave links integrate along paths, and radar/satellite products represent areal averages over grids.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What is the core idea of the proposed method?",{"text":68,"@type":64},"It builds a geometry-aware multi-support heterogeneous GNN where each observation type is represented as a distinct support-typed node layer and fused via cross-support message passing into a point-support prediction layer.",{"name":70,"@type":61,"acceptedAnswer":71},"How does the model enable predictions at locations not directly observed?",{"text":72,"@type":64},"It uses an inductive masked-node formulation that decouples prediction resolution from sensing resolution, allowing reconstruction on user-defined target locations or display grids without leaking gauge values.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},327165,1790357577,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":116,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":4},4398048949847,"https://ap-avatar.wpscdn.com/avatar/400002536579ef2da7f?_k=1778318612642679267","Spatial Support Matters: Geometry-Aware Graph Fusion for Rainfall Field  \nReconstruction  \nLow Jun Yu 1 ,∗ Niramay Kachhadiya2 Herath Mudiyanselage Viraj Vidura Herath2 ,+  \nSanka Rasnayaka 1 and Lucy Amanda Marshall2  \n1 School of Computing, National University of Singapore, 2Faculty of Engineering, The University of Sydney  \n∗ [lowjy28@gmail.com](lowjy28@gmail.com) , +[viraj.herath@sydney.edu.au](viraj.herath@sydney.edu.au)  \narXiv :2607 .0 162 1v 1 [ cs .AI] 2 Jul 2026  \nAbstract  \nFine-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 undersampled relative to its correlation length and little when it is already resolved. Code and models are open-sourced at \u003CANONYMIZED> .  \n1. Introduction  \nFine-scale rainfall reconstruction is critical for urban flood modeling, water management, and disaster response, yet  \nrainfall remains one of the hardest geophysical fields to measure [1] . Rainfall is spatially localized, intermittent, and rapidly evolving, with convective storms producing sharp gradients over a few kilometers that no single instrument captures well. Rain gauges sample it accurately but only at isolated points; weather radar and satellites cover wide areas but observe the field indirectly and aloft; commercial microwave links (CMLs) measure it along the paths between telecommunication towers. Each instrument senses the same field through a different spatial geometry, and no single source is sufficient alone.  \nThe difficulty is not only that the sensors are heterogeneous, but that they observe rainfall over different spatial supports: gauges measure point values, microwave links measure path-integrated attenuation, and radar or satellite products estimate areal averages over grid cells. We refer to this geometric measurement region as the spatial support of an observation. These differences in support are not identical: a point measurement, a path integral, and an areal average impose geometrically distinct constraints on the field, and fusing them well requires respecting that geometry.  \nClassical interpolation techniques such as inversedistance weighting (IDW) and kriging [11, 16] rely on assumptions of stationarity and Gaussian spatial statistics, which are often violated by the highly non-linear, localized nature of convective rainfall. More recent learning-based approaches, including convolutional networks [14, 21] and heterogeneous graph neural networks [18, 20], relax these assum","cbCaipPzvsBc9vsP","https://ap.wps.com/l/cbCaipPzvsBc9vsP","pdf",4844238,"English","# Abstract\n# 1. Introduction\n## Multi-source spatial field estimation\n# 2. Related Work","[{\"question\":\"Why is rainfall-field reconstruction difficult across real sensing systems?\",\"answer\":\"Because different instruments measure the same rainfall field using incompatible spatial supports: gauges sample points, microwave links integrate along paths, and radar/satellite products represent areal averages over grids.\"},{\"question\":\"What is the core idea of the proposed method?\",\"answer\":\"It builds a geometry-aware multi-support heterogeneous GNN where each observation type is represented as a distinct support-typed node layer and fused via cross-support message passing into a point-support prediction layer.\"},{\"question\":\"How does the model enable predictions at locations not directly observed?\",\"answer\":\"It uses an inductive masked-node formulation that decouples prediction resolution from sensing resolution, allowing reconstruction on user-defined target locations or display grids without leaking gauge values.\"}]","Spatial Support Matters - Geometry-Aware Graph Fusion for Rainfall Field Reconstruction - [Inferred] | PDF",1789976579,23]