A hybrid approach for integrating micro-satellite images and sensors network-based ground measurements using deep learning for high-resolution prediction of fine particulate matter (PM2.5) over an indian city, lucknow

The detrimental impacts of fine particulate matter (PM_2.5) on human health, climate, ecosystems, crops, and building materials are well-established. However, there remain unresolved inquiries regarding the precise location of the sources of PM_2.5. This study is the first attempt to use a calibrated sensors-based ambient air quality monitoring network (SAAQM network) and regulatory government monitors to train micro-satellite images for high spatial-resolution air pollution field determination of PM_2.5 in Lucknow, Uttar Pradesh, India. A hybrid approach is developed to integrate three different datasets that include microsatellite images, PM_2.5 ground measurements, and supporting information (meteorological parameters and geographical coordinates), to be fed into a Random Trees-Random Forest- Convolutional Neural Network (RT-RF-CNN) joint model to estimate PM_2.5 concentrations at a sub-km level. The RT-RF-CNN joint model can derive PM_2.5 concentrations at a spatial resolution of 500 m with statistically significant indicators such as spatial r of 0.9, a low root-mean-square error of 26.9 μg/m³ and a mean absolute error of 17.2 μg/m³. Based on our approach, the PM_2.5 prediction maps using micro-satellite images (spatial resolution of 3m/pixel) and RT-RF-CNN joint model were generated for each day throughout the study period (December 2021–December 2022). The inter-grid comparison of these maps revealed the intra-urban local hotspots and coolspots at a fine-granular level seasonally, monthly, and daily. It is observed that the monsoon season has the highest number of coolspots (67%), while winter (0.1%), post-monsoon (0.5%) and summer (11%) have fewer. It is noted that the high temporal-spatial information of PM_2.5 estimates from our integrated approach is not achievable by ground-based measurements and other existing satellite-based estimates alone. The findings of this study have potential applications on a diverse array, encompassing near real-time daily PM_2.5 predicted maps, specific air pollution hotspot identification, PM_2.5 exposure assessment at the neighbourhood level, and integration of remote sensing-based micro-satellite images and ground-based measurements.