(1) Background: Although numerous artificial intelligence (AI)-based air pollution prediction models have been proposed, research that links key pollution drivers, such as regional industrial facilities, to actionable policy recommendations is required. (2) Methods: This study employs the radial basis function (RBF) and spatial lag features to capture spatial interactions among regions, utilizing a transformer model for analysis. The model was trained on air quality and industrial data from South Korea (2010–2022) and Japan (2017–2020). (3) Results: The transformer model achieved a mean squared error of 0.045 for the Korean dataset and 0.166 for the Japanese dataset, outperforming benchmark models, including Support Vector Regression, neural networks, and the AutoRegressive Integrated Moving Average model. (4) Conclusions: By capturing complex spatial dynamics, the proposed model provides valuable insights that can assist policymakers in developing effective, data-driven strategies for air pollution reduction at the national and regional levels, thereby supporting the broader goals of sustainability through informed, equitable environmental interventions.