S5P2PM

Data associated with the article: PM2.5 Retrieval with Sentinel-5P Data over Europe Exploiting Deep LearningThis dataset provides pre-processed Sentinel-5P imagery reprojected onto the CAMS grid for PM2.5 estimation. Each sample contains the first 60 principal components extracted from the Sentinel-5P spectral bands, excluding the UV range, after applying Principal Component Analysis (PCA). The final band in each sample represents the PM2.5 concentration values obtained from the CAMS dataset. The dataset is divided into four subsets: training, validation, testing, and generalization, enabling the evaluation of deep learning models under different conditions. Training and validation data are provided in 32×32 pixel patches. This dataset supports research in air quality monitoring and deep learning-based PM2.5 retrieval from satellite observations.