LGHAP v2: Global Daily 1-km Aerosol and PM2.5 Data (2000-2021)

22-year-long gap-free daily aerosol optical depth and PM2.5 concentration grids at 1-km resolution cover the global land area from 2000 to 2021. Kaixu Bai from East China Normal University produced this dataset by integrating multimodal AODs and air quality measurements from satellites, ground monitors, and numerical models. An ensemble learning graph attention network was developed to predict PM2.5 concentrations, especially for regions with limited ground measurements.

Use Cases

• Modeling long-term global air pollution trends based on the 22-year daily time series.
• Analyzing spatial patterns of aerosol optical depth at 1-km resolution for environmental management.
• Estimating near-surface PM2.5 concentrations in data-sparse regions using the described scene-aware ensemble learning method.
• Conducting earth system science analysis with gap-free, high-resolution pollutant grids.

Strengths

• 22-year temporal coverage from 2000 to 2021 provides a long-term record.
• Daily data at 1-km spatial resolution offers high granularity for global land analysis.
• Dataset integrates measurements from diverse sources including satellites, ground monitors, and numerical models.
• Gap-free grids are produced using an attention-reinforced tensor construction framework.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.
• Data may reflect geographic bias inherent to the integration of source measurements with varying coverage.

Provenance

Source

East China Normal University

Collection Method

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

Time Range

2000 to 2021

Geography

Global land area