Application of Prisma Hyperspectral Data for PM2.5 Estimation: A Case Study on New Delhi, India

City based pollution monitoring is essential for overall health and sustainability of the concerned city. PM 2.5 is one of the most hazardous pollutants whose excessive presence in the urban air makes it unfit to breathe. A study is conducted to estimate PM 2.5 (particulate matter with diameter ≤ $2.5\ \mu\mathrm{m}$ ) using PRISMA (hyperspectral imagery based satellite) hyperspectral bands for the Delhi region in India. By using ground station measurements and simulated PM 2.5 concentrations (using Sequential Gaussian Simulation) as a reference, estimates of PM 2.5 are created from the PRISMA imagery. Various regression models are developed for PM 2.5 estimation from hyperspectral data and deployed for spatial estimation. This study provides a comparative demonstration of ground level PM 2.5 prediction for urban areas using various machine learning models from hyperspectral imagery and indicates the importance of it.