AEROPMAP

AEROPMAP provides global daily 1 km Aerosol Optical Depth and PM2.5 maps by fusing satellite and ground data with deep learning. This comprehensive dataset provides unprecedented spatial coverage and accuracy, significantly improving real-time air quality monitoring and informing public health decisions and climate research.

[fr]

Overview of the global 1km gap-free aerosol optical depth maps. © East China Normal University

AEROsol and Particulate Matter MAPping

Overview

AEROPMAP is a global mapping project of aerosol optical depth (AOD) and fine particulate matter (PM2.5). It integrates satellite observations and ground monitoring data into a consistent, high-resolution (1 km) dataset.

The project delivers daily global coverage, filling gaps in existing remote sensing data and addressing spatial limitations of ground networks. By applying deep learning methods tailored to the spatial and temporal patterns of aerosols, the project generates robust estimates even in regions with poor monitoring infrastructure. Its innovative fusion framework improves completeness and accuracy, supporting reliable environmental assessments at local and global scales.

The resulting dataset supports applications in air quality management, public health analysis, and climate research. Users can track pollutant exposure, study trends, and assess risks with greater confidence. This work helps bridge critical data gaps, offering decision-makers and researchers a new tool to address environmental and societal challenges linked to air pollution.

Test area

China

Data

Satellite

EXERCICE 3 MERSI AOD
Terra/Aqua MODIS AOD
MODIS NDVI & Land Cover

Other

Ground-Based Observations
Numerical Model Data

Results - Final product(s)

The project delivers a global dataset of daily 1 km resolution Aerosol Optical Depth (AOD) and surface PM2.5 concentrations.

The final products include gap-filled AOD maps derived from satellite retrievals and globally inferred PM2.5 estimates. These datasets offer broad spatial coverage, high temporal consistency, and enhanced accuracy.

Accessible via an open data platform, the products support diverse applications, including air quality monitoring, health risk analysis, and climate modeling. The outputs are updated in near-real time and designed for ease of use by researchers, policymakers, and the public, significantly advancing global environmental data availability and utility.

References

Bai, K., Li, K., Qiu, S., Zheng, Z., Jiao, P., Sun, Y., Shao, L., Liu, C., Li, X., Li, Z., Guo, J., Chang, N., 2025. SCAGAT: A scene-aware ensemble graph attention network for global PM2.5 pollution mapping via land–atmosphere interactions. ISPRS J. Photogramm. Remote Sens. 225, 19–35. https://doi.org/10.1016/j.isprsjprs.2025.04.019
Bai, K., Li, K., Shao, L., Li, X., Liu, C., Li, Z., Ma, M., Han, D., Sun, Y., Zheng, Z., Li, R., Chang, N.-B., Guo, J., 2024. LGHAP v2: a global gap-free aerosol optical depth and PM2.5 concentration dataset since 2000 derived via big Earth data analytics. Earth Syst. Sci. Data 16, 2425–2448. https://doi.org/10.5194/essd-16-2425-2024
Bai, K., Li, Ke, Ma, M., Li, Kaitao, Li, Z., Guo, J., Chang, N., Tan, Z., Han, D., 2022. LGHAP: the Long-term Gap-free High-resolution Air Pollutant concentration dataset, derived via tensor-flow-based multimodal data fusion. Earth Syst. Sci. Data 14, 907–927. https://doi.org/10.5194/essd-14-907-2022