Scholarlink

This paper presents a novel spatial downscaling methodology for PM10 data, offering valuable insights for air quality assessment and public health protection. The proposed framework integrates spectral methods with artificial intelligence techniques to construct both linear and nonlinear spatial regression models. By harmonizing coarse-resolution PM10 data obtained from large-scale sources, such as the Copernicus Atmosphere Monitoring Service (CAMS), with point-level measurements from monitoring stations, the methodology enhances spatial resolution and improves the accuracy of population exposure estimates at the municipality level. These fine-scale exposure assessments provide public health authorities with essential tools to identify high-risk areas, design targeted intervention strategies, and evaluate the effectiveness of air quality regulations.

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

Linear and Nonlinear Regression Models for Spatial Downscaling of Particulate Matter

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Luigi Ippoliti,
  • Tonio Di Battista,
  • Luigi Di Carlo,
  • Stefania Fensore,
  • Eugenia Nissi,
  • Pasquale Valentini,
  • Carlo Zaccardi

摘要

This paper presents a novel spatial downscaling methodology for PM10 data, offering valuable insights for air quality assessment and public health protection. The proposed framework integrates spectral methods with artificial intelligence techniques to construct both linear and nonlinear spatial regression models. By harmonizing coarse-resolution PM10 data obtained from large-scale sources, such as the Copernicus Atmosphere Monitoring Service (CAMS), with point-level measurements from monitoring stations, the methodology enhances spatial resolution and improves the accuracy of population exposure estimates at the municipality level. These fine-scale exposure assessments provide public health authorities with essential tools to identify high-risk areas, design targeted intervention strategies, and evaluate the effectiveness of air quality regulations.