Air pollution is one of the leading global health risk factors. Ambient air pollution has been traditionally monitored at regulatory stations at high instrumentation and maintenance costs. Sparse and uneven regulatory monitoring has a limited ability to reÔ¨Çect pollution details, especially in remote communities. This paradigm is shifting with increasingly available satellite remote sensing instruments to monitor air quality at a global scale and low-cost air sensors that enable community-level air quality monitoring. In this talk, I will present my past and ongoing research in developing statistical methods to overcome the current challenges of utilizing novel satellite and low-cost sensor data in large-scale, high-resolution ambient air pollution prediction, such as satellite data missingness and inaccuracy in low-cost sensor data. These methods particularly hold promise to advance air pollution exposure assessment that has been poorly characterized with regulatory monitoring, such as wildfire smoke estimation.