Application of machine learning in atmospheric pollution research: A state-of-art review

The Science of The Total Environment, Год журнала: 2023, Номер 910, С. 168588 - 168588

Опубликована: Ноя. 18, 2023

Язык: Английский

---

Estimation of Near-Surface High Spatiotemporal Resolution Ozone Concentration in China Using Himawari-8 AOD

Remote Sensing, Год журнала: 2025, Номер 17(3), С. 528 - 528

Опубликована: Фев. 4, 2025

Near-surface ozone is a secondary pollutant, and its high concentrations pose significant risks to human plant health. Based on an Extra Tree (ET) model, this study estimated near-surface with the spatiotemporal resolution based Himawari-8 aerosol optical depth (AOD) data meteorological variables from 1 January 2016 31 December 2020. The SHapley Additive exPlanation (SHAP) method was employed evaluate contribution of AOD factors concentration. results indicate that (1) ET model achieves sample-based cross-validation R2 0.75–0.87 RMSE (μg/m3) 17.96–20.30. coefficient determination (R2) values in spring, summer, autumn, winter are 0.81, 0.80, 0.87, 0.75, respectively. (2) Higher temperature boundary layer heights were found positively contribute concentration, whereas higher relative humidity exerted negative influence. (3) From 11:00 15:00 (Beijing time, UTC+08:00), concentration increases gradually, highest occurring followed by spring. This has obtained spatial temporal data, offering valuable insights for development fine-scale pollution prevention control strategies.

Язык: Английский

---

Additive-feature-attribution methods: A review on explainable artificial intelligence for fluid dynamics and heat transfer

International Journal of Heat and Fluid Flow, Год журнала: 2024, Номер 112, С. 109662 - 109662

Опубликована: Дек. 9, 2024

Язык: Английский

---

Combined PMF modelling and machine learning to identify sources and meteorological influencers of volatile organic compound pollution in an industrial city in eastern China

Atmospheric Environment, Год журнала: 2024, Номер 334, С. 120714 - 120714

Опубликована: Июль 23, 2024

Язык: Английский

---

Estimating ground-level high-resolution ozone concentration across China using a stacked machine-learning method

Atmospheric Pollution Research, Год журнала: 2024, Номер 15(6), С. 102114 - 102114

Опубликована: Март 13, 2024

Язык: Английский

---

A spatiotemporal deep learning ensemble for multi-step PM2.5 prediction: A case study of Bangkok metropolitan region in Thailand

Atmospheric Pollution Research, Год журнала: 2025, Номер unknown, С. 102406 - 102406

Опубликована: Янв. 1, 2025

Язык: Английский

---

Spatiotemporal correlations of PM2.5 and O3 variations: A street-scale perspective on synergistic regulation

The Science of The Total Environment, Год журнала: 2025, Номер 965, С. 178578 - 178578

Опубликована: Янв. 31, 2025

Язык: Английский

---

Comprehensive 24-Hour Ground-Level Ozone Monitoring: Leveraging Machine Learning for Full-Coverage Estimation in East Asia

Journal of Hazardous Materials, Год журнала: 2025, Номер 488, С. 137369 - 137369

Опубликована: Фев. 1, 2025

Язык: Английский

---

Spatiotemporal changes of desertification areas in the Alxa Desert obtained from satellite imagery

Earth Surface Processes and Landforms, Год журнала: 2025, Номер 50(2)

Опубликована: Фев. 1, 2025

Abstract Desertification is defined as land degradation in arid, semi‐arid and dry sub‐humid areas resulting from various factors. High‐spatial‐resolution desertification monitoring with long time series accurate area quantification the Alxa Desert has yet to be fully elucidated. Here, we exploited Landsat satellite images develop a method for of high‐resolution, large‐scale dynamics using Difference Index (DDI) model based on albedo Topsoil Grain Size (TGSI). On this basis, examined spatial–temporal changes extent desertified ascertained impact factors (temperature, precipitation, total livestock) process. We made detailed classification (five types) found that non‐desertification accounted smallest proportion entire study region (annual mean 2.00 × 10 4 km 2 , 7.8%), while severe contributed largest 7.88 30.9%). Over past 20 years, there been substantial reduction extremely (−251 /yr) moderate (−230 areas, demonstrating effectiveness desert management. Regionally, considerable attention should paid eastern Tengger terms control; temporally, special summer. High temperatures can exacerbate severe, desertification, contrary effect increasing precipitation. Dynamic will become more complex under predicted climate change patterns, indicating prevention prioritized over control.

Язык: Английский

---

Spatiotemporal Changes of Pollutant Concentrations in South India during COVID-19 Lockdown Using Ground and Satellite-based data: a Comparative Analysis from the Machine Learning Model

Water Air & Soil Pollution, Год журнала: 2025, Номер 236(3)

Опубликована: Фев. 28, 2025

Язык: Английский

---