Overview: This dataset accompanies the recent publication "Local exposure misclassification in national models: relationships with urban infrastructure and demographics" (DOI: 10.1038/s41370-023-00624-z). It provides essential data for replicating and extending the analysis conducted in the study. The script for the analysis is available at https://github.com/SEChambliss-AQ/LD-analysis. The dataset consists of four key files. Files Included: Gridded OSM and GSV Data (gridded_OSM_GSV.RDS): This R object offers a 100mx100m grid covering select neighborhoods in the San Francisco Bay Area. Each grid cell includes average air pollution levels (Ultrafine Particle Count in thousand count per cubic meter; Nitrogen Dioxide in ppb) from mobile monitoring. The file also provides normalized z-scores of local density of urban infrastructure related to air pollutants based on OpenStreetMap (OSM) data. Further details can be found in the associated publication. BartMachine Outputs (bartMachine R objects.zip): A collection of R object outputs from the bartMachine package, an R-Java Bayesian Additive Regression Trees implementation. These objects, which can be regenerated using the provided script, are included to reduce computational requirements for future analyses. The script for generating these outputs is available at the above GitHub Repository. NO2 Predictions (CACES_criteria.csv): Land Use Regression (LUR) data for Nitrogen Dioxide, provided by the Center for Air, Climate, and Energy Solutions. Methodologies for integrating these data with the gridded dataset are described in the publication and script. UFP Predictions (CACES_UFP.csv): Similar to the NO2 dataset, this file contains LUR data for Ultrafine Particle predictions. Methods for data integration are detailed in the publication and available script. Usage: These files are intended for researchers and analysts aiming to replicate or build upon the study's findings. They provide a source of data for exploring the complex interplay between air pollution, urban infrastructure, and demographic factors in urban environments. For detailed methodology and analysis, refer to the original publication and the accompanying GitHub repository.