NO2, PM25, and O3 daily 1km x 1km grid predictions for the U.S.

 

Daily, Monthly, and Annual PM2.5 Concentrations for the Contiguous United States, 1-km Grid (2000 – 2016)

This dataset includes daily predictions of ambient PM_2.5 across the contiguous U.S. from 2000 to 2016. These predictions were produced by a geographically-weighted ensemble model that combined predictions from fitted neural network, random forest, and gradient boosting machine learners. The overall 10-fold cross-validated R² values were 0.86 for daily predictions and 0.89 for annual predictions.

Daily predictions and monthly and yearly aggregates are available in RDS and plaintext formats, and the prediction grid is available as CSV and GeoPackage files. Example R code is provided to facilitate reading and common merge operations.

When using this dataset, please also cite the Related Publication below, which further details the data sources and processes used to produce these predictions.

This is a reupload and slight format change of data that was previously available on SEDAC / EarthData under the name "Daily and Annual PM2.5 Concentrations for the Contiguous United States, 1-km Grids, v1 (2000 – 2016)".

Link to Dataset: dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/58C6HG

 

Daily, Monthly, and Annual NO2 Concentrations for the Contiguous United States, 1-km Grid (2000 – 2016)

This dataset includes daily predictions of ambient NO₂ across the contiguous U.S. from 2000 to 2016. These predictions were produced by a geographically-weighted ensemble model that combined predictions from fitted neural network, random forest, and gradient boosting machine learners. The overall 10-fold cross-validated R² values were 0.79 for daily predictions and 0.84 for annual predictions.

Daily predictions and monthly and yearly aggregates are available in RDS and plaintext formats, and the prediction grid is available as CSV and GeoPackage files. Example R code is provided to facilitate reading and common merge operations.

When using this dataset, please also cite the Related Publication below, which further details the data sources and processes used to produce these predictions.

This is a reupload and slight format change of data that was previously available on SEDAC / EarthData under the name "Daily and Annual NO2 Concentrations for the Contiguous United States, 1-km Grids, v1.10 (2000 – 2016)".

Link to Dataset: dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/LUFKYG

 

Daily, Monthly, and Annual 8-Hour Maximum O3 Concentrations for the Contiguous United States, 1-km Grid (2000 – 2016)

This dataset includes daily predictions of 8-hour maximum ambient O₃ across the contiguous U.S. from 2000 to 2016. These predictions were produced by a geographically-weighted ensemble model that combined predictions from fitted neural network, random forest, and gradient boosting machine learners. The overall 10-fold cross-validated R² values were 0.90 for daily predictions and 0.86 for annual predictions.

Daily predictions and monthly and yearly aggregates are available in RDS and plaintext formats, and the prediction grid is available as CSV and GeoPackage files. Example R code is provided to facilitate reading and common merge operations.

When using this dataset, please also cite the Related Publication below, which further details the data sources and processes used to produce these predictions.

This is a reupload and slight format change of data that was previously available on SEDAC / EarthData under the name "Daily and Annual 8-Hour Maximum O3 Concentrations for the Contiguous United States, 1-km Grids, v1.10 (2000 – 2016)".

Link to Dataset: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/DGXCTH