• Urban wetlands act as both sinks and secondary sources of airborne microplastics. • FTIR detected PE, PP, PET, PS, and PVC across air, water, soil, and plant samples. • GIS and HYSPLIT showed MPs can disperse 350 km and rise up to 1500 m altitude. • PET dominated (55%), with strong seasonal links to asthma, COPD, and bronchitis. • Positive correlation (r = 0.68, p < 0.05) between MPs and respiratory illness cases. • Findings stress urgent need for wetland restoration and integrated pollution control. This study investigated the role of Ukkadam Lake, an urban wetland in Coimbatore, India, as both a sink and secondary source of airborne microplastics, and explored their implications for respiratory health. The selection of this urban wetland was motivated by its ecological significance and increasing vulnerability to anthropogenic pollution, particularly from urban runoff. The deterioration of the site has been progressive in recent years, owing to the discharge of untreated effluents and sewage, as well as the invasive proliferation of water hyacinth. This study investigates the role of urban wetlands as both sinks and potential secondary sources of microplastics during the period 2020−2024. Special emphasis was placed on the combined impacts of microplastic pollution and fine particulate matter on respiratory health issues. The FTIR analysis detected five main types of polymers in the samples: polyethylene (38.5%), polypropylene (27.3%), PET (19.6%), polystyrene (9.4%), and PVC (5.2%). Among these, PET was the most common in aquatic plants, revealing the bioaccumulation of microplastics in the vegetation. GIS mapping showed that pollution hotspots were mainly found near urban–wetland boundaries. Dispersion modeling (HYSPLIT) indicated that airborne microplastics can rise up to 1500 m and travel more than 350 km. Seasonal weather patterns and prevailing winds strongly influence their movement. In summary, the results revealed a significant association between airborne microplastic exposure and respiratory health risks in the local population. These suggested the urgent need for targeted mitigation strategies, including the restoration and active management of urban wetlands, enhanced regulation of point and non-point pollution sources, and the development of integrated monitoring frameworks to support sustainable urban ecological management and public health protection.

Abstract Artificial intelligence (AI) models were developed to determine the center of tropical cyclones (TCs) in the western North Pacific. These models integrated information from six channels of geostationary satellite imagery: the brightness temperature of four infrared (IR) and one shortwave IR channels, as well as the reflectivity of one visible channel. The first model is a convolutional neural network designed for spatial data processing, and the second is a convolutional long short-term memory model that effectively captures spatiotemporal information. For training, verification, and testing purposes, spatial images from six channels were obtained from the Japanese Himawari-8 satellite from 2016 to 2021. The position of the European Centre for Medium-Range Weather Forecasts 6- or 12-h prediction was assigned as an initial value to the AI models. Errors in the initial value were 20–50 km compared to the Joint Typhoon Warning Center best track, depending on TC intensity. Weak (strong) TCs exhibited large (small) errors. This error dependency was found in Automated Rotational Center Hurricane Eye Retrieval (ARCHER) product, which is currently used by several operational organizations. ARCHER errors were typically small when observations from both geostationary and polar-orbiting satellites were included. Significant errors remained in the absence of microwave channel information from polar-orbiting satellites. This study successfully developed two AI models that consistently determined the location of the TC center using only six-channel images from geostationary satellites. These models exhibited comparable or better performance than the ARCHER products. The newly developed AI models can potentially be implemented for operational use. Signicance Statement This study has developed AI models that can determine the center of TCs in the western North Pacific, which can be applied to meteorological organizations that have limited access to real-time polar-orbiting satellite data. The newly developed AI models derived positions comparable to or better than ARCHER, which is currently one of the most precise systems for determining the position of the TC center. The successful development of these AI models is very opportune as it was only possible thanks to the recent availability of high-frequency data observed from geostationary satellite, coupled with the rapid technological advances in AI algorithms.