Scholarlink

<p>High-resolution population data are essential for spatial analysis in Geographic Information Systems. However, census data are typically available only at coarse administrative scales. This paper presents popVAT, a geospatial representation-learning framework for fine-grained population mapping that integrates heterogeneous geospatial data using gridded population products as supervisory reference layers. The architecture combines a Variational Autoencoder for probabilistic spatial representation with pixel-level and atrous-convolution branches capturing local and large-scale spatial context. To address limitations of static multi-scale fusion, the model introduces adaptive gating mechanisms that dynamically regulate interactions between latent representations and contextual features. Using multi-source geospatial covariates, the framework generates 100 m resolution population estimates for Tunisia. Experimental results show strong predictive performance (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(R^{2}= 0.9714; RMSE = 43,488\)</EquationSource> </InlineEquation>), demonstrating stronger agreement with the supervisory reference surface while maintaining higher consistency with independent census aggregates than the evaluated baselines. The results highlight the potential of adaptive spatial representation learning for GIS-based population modeling. Our code and training dataset are available<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(^{3}\)</EquationSource> </InlineEquation></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adaptive spatial feature fusion for fine-grained population estimation from multi-source geospatial data

  • 期刊论文

  • 发表日期：

    2026年6月26日

查看全文
  • Issa Nasralli,
  • Imen Masmoudi,
  • Hassen Drira,
  • Mohamed Ali Hadj Taieb

摘要

High-resolution population data are essential for spatial analysis in Geographic Information Systems. However, census data are typically available only at coarse administrative scales. This paper presents popVAT, a geospatial representation-learning framework for fine-grained population mapping that integrates heterogeneous geospatial data using gridded population products as supervisory reference layers. The architecture combines a Variational Autoencoder for probabilistic spatial representation with pixel-level and atrous-convolution branches capturing local and large-scale spatial context. To address limitations of static multi-scale fusion, the model introduces adaptive gating mechanisms that dynamically regulate interactions between latent representations and contextual features. Using multi-source geospatial covariates, the framework generates 100 m resolution population estimates for Tunisia. Experimental results show strong predictive performance ( \(R^{2}= 0.9714; RMSE = 43,488\) ), demonstrating stronger agreement with the supervisory reference surface while maintaining higher consistency with independent census aggregates than the evaluated baselines. The results highlight the potential of adaptive spatial representation learning for GIS-based population modeling. Our code and training dataset are available \(^{3}\)