Environmental Pollution, Год журнала: 2025, Номер 381, С. 126621 - 126621
Опубликована: Июнь 4, 2025
Язык: Английский
Environmental Pollution, Год журнала: 2025, Номер 381, С. 126621 - 126621
Опубликована: Июнь 4, 2025
Язык: Английский
Environmental Research, Год журнала: 2025, Номер unknown, С. 121434 - 121434
Опубликована: Март 1, 2025
Язык: Английский
Процитировано
0Journal of Environmental Management, Год журнала: 2025, Номер 381, С. 125265 - 125265
Опубликована: Апрель 9, 2025
Язык: Английский
Процитировано
0Remote Sensing, Год журнала: 2025, Номер 17(9), С. 1632 - 1632
Опубликована: Май 4, 2025
Fine particulate matter (PM2.5) has garnered significant scientific and public health concern owing to its capacity for deep penetration into the human respiratory system, presenting risks. Despite implementation of strict environmental policies in China over past decade reduce PM2.5 levels, long-term concerns remain a serious issue. Our study aims provide high-quality, seamless daily dataset covering years 2015 2024. A two-step estimation model is established based on machine learning algorithm spatio-temporal decomposition method. First, we utilize XGBoost (EXtreme Gradient Boosting) address gaps MAIAC (Multi-Angle Implementation Atmospheric Correction) AOD (Aerosol Optical Depth), with R2/RMSE (coefficient determination/Root Mean Square Error) 0.67/0.2678 compared AERONET Robotic Network) AOD. Then, novel approach by integrating EOF (Empirical Orthogonal Function) introduced estimation. The integration allows incorporation entire meteorological field information model, significantly enhancing accuracy: spatial CV (cross-validation)-R2 improved from 0.8340 0.8935, CV-RMSE reduced 13.8177 11.0668. Leveraging newly produced dataset, analyze variations across decomposition, particularly noting that levels eastern anthropogenic intensive regions continuously declined 2020, fluctuated steadily during 2020–2024. This research underscores critical need sustained effective air quality management strategies China.
Язык: Английский
Процитировано
0Atmosphere, Год журнала: 2025, Номер 16(6), С. 655 - 655
Опубликована: Май 28, 2025
The satellite remote sensing of Aerosol Optical Depth (AOD) products is crucial in environmental monitoring and atmospheric pollution research. However, data gaps AOD from satellites like Fengyun significantly hinder continuous, seamless capabilities, posing challenges for the long-term analysis trends, responses to sudden ecological events, disaster management. This study aims develop a high-precision method fill spatial missing values generate daily full-coverage Beijing–Tianjin–Hebei region 2021 by integrating multi-dimensional data, including meteorological models, multi-source sensing, surface conditions, nighttime light parameters, applying machine learning methods. A comparison five models showed that random forest model performed optimally inversion, achieving root mean square error (RMSE) 0.11 coefficient determination (R2) 0.93. Seasonal evaluation further indicated model’s simulation was best winter. Variable importance identified relative humidity (RH) as most critical factor influencing results. reconstructed product exhibited distribution trend higher southern plain areas compared mountainous regions, consistent with actual aerosol patterns area. Moreover, demonstrated overall smoothness high accuracy. research lays foundation establishing long-term, 1 km resolution, spatially continuous beyond, providing more robust support addressing regional larger-scale challenges.
Язык: Английский
Процитировано
0Environmental Pollution, Год журнала: 2025, Номер 381, С. 126621 - 126621
Опубликована: Июнь 4, 2025
Язык: Английский
Процитировано
0