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

<p><i>This dataset contains many files</i>; use the Tree view below or <a href=https://dataverse.harvard.edu/api/datasets/:persistentId/dirindex?persistentId=doi:10.7910/DVN/58C6HG>Dataverse API directory index</a> to get a condensed overview of what is available. See the <code>README-PM25.pdf</code> file for more information.</p>

<h3>Overview</h3>

<p>This dataset includes daily predictions of ambient PM<sub>2.5</sub> 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 R<sup>2</sup> values were 0.86 for daily predictions and 0.89 for annual predictions.</p>

<p>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.</p>

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

<p>This is a reupload and slight format change of data that was <a href=https://web.archive.org/web/20241005025401/https://sedac.ciesin.columbia.edu/data/set/aqdh-pm2-5-concentrations-contiguous-us-1-km-2000-2016>previously available on SEDAC / EarthData</a> under the name "Daily and Annual PM2.5 Concentrations for the Contiguous United States, 1-km Grids, v1 (2000 – 2016)".</p>

<h3>Bulk downloads</h3>

<p><code>wget</code> and other download programs can be used to bulk download files using the Dataverse API directory index:</p>

<p><code>wget --recursive --execute robots=off --no-host-directories --span-hosts --content-disposition 'https://dataverse.harvard.edu/api/datasets/:persistentId/dirindex?persistentId=doi:10.7910/DVN/58C6HG'</code></p>