Mobile and ubiquitous sensing of urban air quality has received increased attention as an economically and operationally viable means to survey atmospheric environment with high spatial-temporal resolution. This paper proposes a machine learning based mobile air pollution sensing framework, coined Deep-MAPS, and demonstrates its scientific and financial values in the following aspects. (1) Based on a combination of fixed and mobile air quality sensors, we perform spatial inference of PM2.5 concentrations in Beijing (3,025 km, 19 Jun -16 Jul 2018) for a spatial-temporal resolution of 1 km ×1 km and 1 hour, with under 15% SMAPE. (2) We leverage urban big data to generate insights regarding the potential cause of pollution, which facilitates evidence-based sustainable urban management. (3) To achieve such spatial-temporal coverage and accuracy, Deep-MAPS can save up to 90% hardware investment, compared with ubiquitous sensing that relies primarily on fixed sensors.