This dataset is the surface NO₂ sub-dataset (ChinaHighNO₂) of the China High-Resolution and High-Quality Near-Surface Air Pollutant Dataset (CHAP), covering the entire territory of China from 2013 to 2020. It adopts artificial intelligence technology, integrates multi-source big data such as ground-based observations, satellite remote sensing products, atmospheric reanalysis and model simulation data, and considers the spatiotemporal heterogeneity of air pollution to generate seamless surface NO₂ data. The spatial resolution is 10km from 2013 to 2018 and improved to 1km after 2019, with temporal resolutions including daily, monthly and annual scales, and the unit is µg/m³. The 10-fold cross-validation results show R²=0.84 and RMSE=7.99µg/m³ for 2013-2018, and R²=0.93 and RMSE=4.89µg/m³ for 2019-2020. The data files include four programming language codes for converting NC to GeoTiff.