The abstract is read at the publisher; the summary is JClub's.
XGBoost most competitively estimated marine PM 2.5 over the eastern China seas from 2019–2024, enabling mapping of spatial gradients and seasonal patterns.
- Why it matters: Sparse marine monitoring and complex meteorology–chemistry–transport interactions limit accurate PM 2.5 assessment, motivating a multi-source, data-driven estimation framework.
- What they did: The study fused AOD, meteorological variables, and chemical parameters (NO 2 , CO, O 3 , SO 2 ) and compared BPNN, RF, and XGBoost using sample-, spatial-, and temporal-based validations.
- The result: Estimated PM 2.5 decreased west-to-east and north-to-south, peaked in winter and dipped in summer, fell markedly in 2020, and SHAP linked AOD to spring–autumn while winter accumulation reflected boundary layer reduction, northwesterly transport, and higher NO 2 and CO.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.