This study introduces a machine learning approach called S-MESH (Satellite and ML-based Estimation of Surface air quality at High resolution) to estimate daily surface NO₂ concentrations over Europe at 1 km spatial resolution using the eXtreme gradient boost (XGBoost) model. The model utilizes a variety of datasets, including TROPOMI NO₂ tropospheric vertical column density, night light radiance from VIIRS, NDVI from MODIS, air quality station observations, and meteorological parameters. The overall model evaluation shows a mean absolute error of 7.77 μg/m³, a median bias of 0.6 μg/m³, and a Spearman rank correlation of 0.66. The model's performance is influenced by NO₂ concentration levels, with the most reliable predictions at concentrations of 10–40 μg/m³. Spatial and temporal error analyses indicate the model's robustness across the study area, with better prediction accuracy during winter months. The SHAP value analysis highlights TROPOMI NO₂ tropospheric column density as the main source of information for deriving surface NO₂ concentrations, emphasizing its significant potential in such studies. The study also demonstrates the importance of anthropogenic emission proxy inputs like VIIRS night lights in complementing TROPOMI NO₂ values for higher-resolution and detailed spatial patterns of NO₂ variations.This study introduces a machine learning approach called S-MESH (Satellite and ML-based Estimation of Surface air quality at High resolution) to estimate daily surface NO₂ concentrations over Europe at 1 km spatial resolution using the eXtreme gradient boost (XGBoost) model. The model utilizes a variety of datasets, including TROPOMI NO₂ tropospheric vertical column density, night light radiance from VIIRS, NDVI from MODIS, air quality station observations, and meteorological parameters. The overall model evaluation shows a mean absolute error of 7.77 μg/m³, a median bias of 0.6 μg/m³, and a Spearman rank correlation of 0.66. The model's performance is influenced by NO₂ concentration levels, with the most reliable predictions at concentrations of 10–40 μg/m³. Spatial and temporal error analyses indicate the model's robustness across the study area, with better prediction accuracy during winter months. The SHAP value analysis highlights TROPOMI NO₂ tropospheric column density as the main source of information for deriving surface NO₂ concentrations, emphasizing its significant potential in such studies. The study also demonstrates the importance of anthropogenic emission proxy inputs like VIIRS night lights in complementing TROPOMI NO₂ values for higher-resolution and detailed spatial patterns of NO₂ variations.