V6.NA.01
This version is recommended for users with a North American-only focus and includes monthly and annual total and compositional PM₂.₅ at around 1km spatial resolution, as well as the uncertainty estimation for 2000-2023. This version uses deep learning based structures.
We estimate annual and monthly ground-level fine particulate matter (PM₂.₅) total and compositional mass concentrations over North America for 1998-2023 by combining Aerosol Optical Depth (AOD) retrievals (Dark Target, Deep Blue, MAIAC, and SNPP VIIRS) that make use of observations from numerous satellite-based NASA instruments (MODIS/Terra, MODIS/Aqua, MISR/Terra, SeaWiFS/SeaStar, VIIRS/SNPP, and VIIRS/NOAA20) with the GEOS-Chem chemical transport model, and subsequently calibrating ground-based observations using a residual Convolutional Neural Network (CNN), as detailed in the below reference for V6.NA.01.
Reference:
Siyuan Shen, Aaron van Donkelaar, Nathan Jacobs, Chi Li, and Randall V. Martin, Enhancing Estimation of Fine Particulate Matter Chemical Composition across North America by Including Geophysical A Priori Information in Deep Learning with Uncertainty Quantification, ACS ES&T Air Article ASAP, DOI: 10.1021/acsestair.5c00251
Scientific Datasets:
Annual and monthly datasets are provided in NetCDF [.nc] format. Gridded files use the WGS84 projection. Latitude centers on the 0.01°×0.01° grid range from 10.005 °N to 69.995 °N and longitude centers range from 169.995 °W to 40.005 °W. Please contact our Support Team (support@satpm.org) for further information.
Note that these estimates are primarily intended to aid in large-scale studies. Annual and coarse-resolution averages correspond to a simple mean of within-grid values. Gridded datasets are provided to allow users to agglomerate data as best meets their particular needs. High-resolution (0.01° × 0.01°) datasets are gridded at the finest resolution of the information sources that were incorporated, but are unlikely to fully resolve PM₂.₅ gradients at the gridded resolution due to the influence of information sources at coarser resolution.
Note that a VPN may be necessary to access the Box data repositories, depending on local web traffic restrictions.
Annual and monthly mean PM₂.₅ total and compositional mass concentrations [µg/m3] at 0.01° × 0.01°:
[https://wustl.box.com/v/ACAG-V6NA01-CNNPM25]
Annual and monthly mean PM₂.₅ total and compositional mass Uncertainty [µg/m3] at 0.1° × 0.1°:
[https://wustl.box.com/v/ACAG-V6NA01-CNNPM25-Uncertainty]