Summary Previous assessments on optimizing urban heat mitigation strategies, critical for urban planning and public health, have generally focused on a handful of cities, rarely considered logistical constraints for implementing common strategies, or used methods that poorly resolve urban-scale processes. Here, we fuse several satellite-derived estimates of heat and physical features with a non-parametric machine learning approach to capture non-linearities in estimating thermal anomalies across 493 U.S. cities, enabling us to perform large-scale, computationally-efficient, data-driven simulations of afforestation and albedo management strategies for urban heat mitigation, including strategies targeting lower income neighborhoods. Key features The data represents almost all cities in the U.S. (493 out of 497) at the census tract level (2010 version). Data quality assurance resulted in the removal of 4 cities with excessive amounts of missing data. The physical covariates are medium-to-high resolution, which is appropriate for capturing intra-urban heterogeneity. We provide variables related to both air and surface temperature for day and nighttime. However, note that air temperature is a more human-relevant thermal metric than surface temperature. We provide facet-level features which parse vegetation and its subtypes (i.e., tree vs. grass), as well as built-up surfaces. These facet-level features enable the consideration of logistical constraints and realistic heat mitigation strategies. We provide simulation outputs for 128 counterfactual heat mitigation strategies. Files data.csv contains the covariates for data exploration and modeling. simulations.csv contains the output for all simulations for the study. Census_UHI_US_Urbanized_climzone_metadata.csv contains urban-level climate zone and coastal indicator Centroid_USUHI.csv contains the centroids for each city Metadata data.csv AT: Air Temperature (in degrees Celsius) LST: Land Surface Temperature (in degrees Celsius) Built, Grass, and Tree Fraction: Fraction of an area covered by built-up extent, grass, or trees Albedo: Overall surface albedo; _Built, _Grass, and _Tree are built, grass, and tree albedo specifically. DEM: Digital Elevation Model (in meters) Climate Zone: Köppen-Geiger climate zone (arid, snow, temperate, or tropical) Coastal?: Whether a tract or urban area is coastal or inland Area (in square meters). We use the following naming conventions: _rur: Rural reference (Spatial mean of the non-urban, non-water pixels within the region of interest) _CT_act: Spatial mean of all non-water pixels intersecting the Census Tract (one value per census tract) For the anomalies: Take the difference between the urban tract value and rural reference value. See the GitHub link (particularly 0-DataProcessing.ipynb) for a complete breakdown. simulations.csv The following describe the naming convention for the simulations. Baseline: The predicted baseline temperature anomaly. The observed baseline is in data.csv. Targeted: The strategy is only applied to those at or below the 25th percentile of median income for a city. Albedo Management: Application of 0.8 built albedo to tracts. X% Afforestation: The afforestation of a tract's grass area increases tree fraction by X%. Methodology and Data Sources For further details on methodology and data source, please consult the publication.