LGHAP v2: Global Daily 1-km Gap-free PM2.5 Grids (2000-2021)

22-year-long gap-free aerosol optical depth (AOD) and near-surface PM2.5 concentration grids with daily 1-km resolution covering global land area from 2000 to 2021. The dataset was produced by Kaixu Bai at East China Normal University using an improved big earth data analytic framework integrating multimodal AODs and air quality measurements from satellites, ground monitors, and models. Data is archived in NetCDF format with Python, MATLAB, R, and IDL codes provided for reading and visualization.

Use Cases

• Modeling long-term PM2.5 exposure for health impact studies based on the 22-year daily time series.
• Analyzing spatial patterns of air pollution at a 1-km resolution for environmental management.
• Training machine learning models for gap-filling and prediction of PM2.5 in data-sparse regions based on the described scene-aware ensemble learning graph attention network (SCAGAT).
• Studying the relationship between aerosol optical depth (AOD) and ground-level PM2.5 concentrations using the integrated multimodal data.

Strengths

• 22-year temporal coverage from 2000 to 2021 provides a long-term baseline for trend analysis.
• Daily 1-km resolution global land coverage offers high spatial and temporal granularity.
• Data integrates measurements from diverse sources including satellites, ground monitors, and numerical models.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for specific ML tasks.

Provenance

Source

East China Normal University

Collection Method

Derived via an integration of multimodal AODs and air quality measurements from satellites, ground monitors, and numerical models using an improved big earth data analytic framework.

Time Range

2000 to 2021

Geography

Global land area