Air pollution is associated with various adverse health impacts and is identified as one of the leading risk factors for global disease burden. Further, air pollution is one of the pathways through which climate change could negatively impact health. Field studies have shown that air pollution has high spatiotemporal variability and pollutant concentrations vary substantially within neighborhoods. Characterizing air pollution at a fine-grained level is essential for accurately estimating human exposure, assessing its impact to human health, and further aiding localized air pollution policy. Air quality models are developed to estimate air pollution at locations and time periods without monitors, and these estimates are commonly used for exposure and health effects studies. Traditional land use regression [LUR] models are one of the cost-effective empirical air quality models. LUR typically relies on fixed-site measurements, GIS-derived variables with limited spatial resolution, and captures linear relationships. In recent years, innovative open-source imagery datasets and their associated features (e.g., street view imagery, remote sensing imagery) have emerged and show potential to augment or replace traditional LUR predictors. Such imagery data sources embody abundant information of natural and built environment features. Advanced computer vision techniques enable feature extraction and quantification through these extensive imagery datasets. The overarching objective of this dissertation is to investigate the feasibility of leveraging open-source imagery datasets (i.e., Google Street View [GSV] imagery, Landsat imagery, etc.) and advanced machine learning algorithms to develop image-based empirical air quality models at both local and national scale. The first study of this work established a pipeline of feature extraction through street view imagery sematic segmentation. The resulting street view features were used to predict street-level particulate air pollution for a single city. The results showed that solely using GSV-derived features can achieve comparable model fits as using traditional GIS-derived variables. Feature engineering improved model stability and interpretability through reducing spurious variables from potential misclassifications from computer vision algorithms. The second study further developed GSV-based models at national scale across multiple years. Random forest models were developed to capture the nonlinear relationship between air pollution and its impacting factors. The results showed that with sufficient street view images, GSV imagery alone may explain the variation of long-term national NO2 concentrations. Adding satellite-derived aerosol estimates (i.e., OMI column density) can significantly boost model performance when GSV images are insufficient, but the addition narrows when more GSV images are available. Our systematic assessment of the impact of image availability on model performance suggested that a parsimonious image sampling strategy (i.e., one GSV image per 100m grid) may be sufficient and most cost-effective for model development and application. Our third study explored the feasibility of combining street view and remote sensing derived features for national NO2 and PM2.5 modeling and projection at high spatial resolution. We found that GSV-based models captured both the highest and lowest pollutant concentrations while remote sensing features tended to smooth the air pollution variations. The results suggested that GSV features may have the capability to better capture fine-scale air pollution variability. The resulting air pollution prediction product may serve a variety of applications, including providing new insights into environmental justice and epidemiological studies due to its high spatial resolution (i.e., street level). Collectively, the result of this dissertation suggests that GSV imagery, processed with computer vision techniques, is a promising data source to develop empirical air quality models with high spatial resolution and consistent predictor variables processing protocol. Image-based features assisted with advanced ML approaches have the potential to greatly improve air quality modeling estimates, and successfully show comparable and even superior model performance than other modeling studies. Moreover, the ever-growing public imagery data sources are particularly promising for remote or less developed areas where traditional curated geodatabases are sparse or nonexistent. / Doctor of Philosophy / Air pollution is detrimental to human health and well-being. Further, air pollutants concentrations can change rapidly within a short distance and temporal frame. Monitoring air pollution with high spatial-temporal resolution is important. Traditional air quality monitoring networks are expensive and sparsely distributed, leading to gaps in capturing the air pollution at small spatial scales. Air quality models are developed to estimate air pollution at locations and time periods without monitors. Empirical air quality models often use air measurements from stationary sites and GIS-derived features (e.g., traffic, population density, land use types, etc.) to develop regression models and use the regression formula to estimate air pollutant concentrations in unmonitored areas. However, GIS-derived features are often collected from curated GIS databases, which often have coarse resolution when available across large geography. Street view imagery and remote sensing imagery contains rich information of natural and built environments. Computer vision techniques can be applied to extract such information to replace or augment traditional GIS-derived features. Combined with advanced machine learning algorithms, features derived from open-access images are promising to develop air quality models with a consistent image collection and processing protocol. This dissertation examines the feasibility of using street view imagery (i.e., Google Street View [GSV] Imagery) and remote sensing imagery to develop air quality models at both local and national scales. Our results found that solely using GSV features to build local and national models can achieve good model performance, which is consistent or even better than other models using traditional GIS-derived variables. For areas without sufficient GSV images, adding satellite observations for air pollution can significantly enhance model performance. Remote sensing features tend to smooth air pollution variation while GSV features tend to better capture fine-scale intra-urban air pollution variation. In conclusion, leveraging open-source imagery datasets with advanced machine learning methods are promising for estimating air pollution at high spatial resolution with good model fits.