Synergistic Fusion of Aerosol Optical Depth over India from multi-sensor satellite retrievals with ground-based measurements

This research focuses on the synergistic fusion of aerosol parameters derived from multi-sensor measurements to create consistent representations of aerosol distribution, which is vital for accurate climate impact assessment. The study integrates satellite observations from the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Multi-angle Imaging SpectroRadiometer (MISR) with ground-based measurements obtained from the ARFINET and AERONET networks. The primary objective is to develop a robust fusion framework for Aerosol Optical Depth (AOD) over India. Two distinct approaches are evaluated and compared: Universal Kriging (UK) and a novel hybrid Residual Kriging – Machine Learning (RK-ML) method. Both methodologies share a common geostatistical foundation, utilizing variogram-based spatial modeling, but diverge in their

estimation of the AOD mean structure. Universal Kriging employs satellite-retrieved AOD as a deterministic trend for spatial prediction, proving effective when ground-based observations are densely distributed. Conversely, the RK-ML approach leverages Machine Learning (specifically Support Vector Regression) to predict AOD as a prior, subsequently applying Ordinary Kriging to interpolate residuals from real-time ground observations. This strategy ensures a near-zero residual mean away from observation points, thereby mitigating distortion under conditions of sparse and uneven data availability. The study's findings elucidate the seasonal fused AOD characteristics and the comparative performance of these fusion techniques.

Message: Hi FE, I need help with “Synergistic Fusion of Aerosol Optical Depth over India from multi-sensor satellite retrievals with ground-based measurements” in “Environmental Engineering”