Mumbai Hourly Multi-Source Geospatial Air Quality Dataset (2019–2023) Ground-Meteorological-Satellite and Coastal Features for PM2.5 Prediction.csv

This dataset provides hourly multi-source air quality observations for Mumbai, India, covering the period 2019–2023. It integrates ground-based monitoring data, ERA5 meteorological variables, satellite-derived atmospheric products, geospatial station information, coastal meteorological indicators (including sea- and land-breeze features), and engineered predictor variables developed for machine learning-based PM2.5 forecasting. The dataset was created to support research in air quality prediction, geospatial analytics, environmental informatics, explainable artificial intelligence (XAI), and urban climate studies. It enables the development, benchmarking, and validation of machine learning and deep learning models for fine particulate matter (PM2.5) prediction in coastal urban environments. The data are provided in a processed and analysis-ready format to facilitate reproducible research while acknowledging the original data providers for the underlying observations.This dataset has been developed as part of ongoing doctoral research on AI-based PM2.5 prediction in Mumbai using multi-source geospatial and meteorological data.