Analysis of Synergistic Changes in PM2.5 and O3 Concentrations Based on Structural Equation Model Study DOI Creative Commons
Zhangwen Su, Liming Yang, Yimin Chen

et al.

Atmosphere, Journal Year: 2024, Volume and Issue: 15(11), P. 1374 - 1374

Published: Nov. 14, 2024

Given the increasing importance of effectively identifying synergistic changes between PM2.5 and O3 comprehensively analyzing their impact on air quality management in China, we employ Sen+Mann–Kendall (Sen+M-K) trend test this study to examine temporal spatial variation trends Yangtze River Delta (YRD), from 2003 2020. We identified regions where these pollutants exhibited established pathways potential drivers, using geographically weighted random forest algorithms structural equation modeling. The results revealed as follows: (1) Overall, concentrations show a decreasing trend, while exhibit an YRD. Analysis combined indicates that approximately 95% area displays opposing for O3, with only about 4% southern region showing both pollutants. (2) Drought average temperature are main drivers areas experiencing changes. Their effects alleviate aggregation reduce formation VOCs, indirectly reducing generation negative effect concentration may indicate existence nonlinear complex interaction drivers. NOx VOCs play important dual roles conversion pollutants, although overall is smaller than meteorological factors. They produce significant indirect through other human factors, further affecting O3. In without coordinated changes, factors remains unchanged, relationship two anthropogenic emission sources complex, different directions levels involved. This provides detailed insights into YRD offers scientific basis environmental authorities develop more comprehensive targeted strategies balancing control pollution.

Language: Английский

Impacts of meteorological and precursor emission factors on PM2.5 and O3 from 2019 to 2022: Insights from multiple perspectives DOI
Decai Gong,

Ning Du,

Li Wang

et al.

Atmospheric Research, Journal Year: 2025, Volume and Issue: unknown, P. 107933 - 107933

Published: Jan. 1, 2025

Language: Английский

Citations

1
The capacity of human interventions to regulate PM2.5 concentration has substantially improved in China DOI Creative Commons

Jiachen Meng,

Wenchao Han,

Cheng Yuan

et al.

Environment International, Journal Year: 2025, Volume and Issue: 195, P. 109251 - 109251

Published: Jan. 1, 2025

The rapid urbanization in China has brought about serious air pollution problems, which are likely to persist for a considerable period as the process continues. In urban areas, spatial distribution of pollutants represented by PM

Language: Английский

Citations

0
Estimating Regional Forest Carbon Density Using Remote Sensing and Geographically Weighted Random Forest Models: A Case Study of Mid- to High-Latitude Forests in China DOI Open Access
Yuan Zhou,

Geran Wei,

Yang Wang

et al.

Forests, Journal Year: 2025, Volume and Issue: 16(1), P. 96 - 96

Published: Jan. 9, 2025

In the realm of global climate change and environmental protection, precise estimation forest ecosystem carbon density is essential for devising effective management emission reduction strategies. This study employed inventory, soil carbon, remote sensing data combined with three models—Random Forest (RF), Geographically Weighted Regression (GWR), innovative Random (GWRF) model—integrated technology to develop a framework assessing regional spatial distribution vegetation (FVC) (FSC). The findings revealed that GWRF model outperformed other models in estimating both FVC FSC. indicated Heilongjiang Province ranged from 4.91 t/ha 72.39 t/ha, an average 40.88 t/ha. contrast, FSC was 182.29 range 96.01 255.09 Additionally, (FEC) varied 124.36 302.18 averaging 223.17 Spatially, FVC, FSC, FEC exhibited consistent growth trend north south. results this demonstrate machine learning consider relationships can improve predictive accuracy, providing valuable insights future modeling storage.

Language: Английский

Citations

0
Integrated spatial generalized additive modeling for forest fire prediction: a case study in Fujian Province, China DOI
Chunhui Li, Zhangwen Su, Ruijing Ni

et al.

Journal of Forestry Research, Journal Year: 2025, Volume and Issue: 36(1)

Published: Feb. 4, 2025

Language: Английский

Citations

0
Integrating Genetic Algorithm and Geographically Weighted Approaches into Machine Learning Improves Soil pH Prediction in China DOI Creative Commons
Wantao Zhang, Jingyi Ji, Binbin Li

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(6), P. 1086 - 1086

Published: March 20, 2025

Accurate soil pH prediction is critical for management and ecological environmental protection. Machine learning (ML) models have been widely applied in the field of prediction. However, when using these models, spatial heterogeneity relationship between variables often not fully considered, which limits predictive capability especially large-scale regions with complex landscapes. To address challenges, this study collected data from 4335 surface points (0–20 cm) obtained China Soil System Survey, combined a multi-source covariate. This integrates Geographic Weighted Regression (GWR) three ML (Random Forest, Cubist, XGBoost) designs develops geographically weighted machine optimized by Genetic Algorithms to improve values. Compared GWR traditional R2 geographic random forest (GWRF), Cubist (GWCubist), extreme gradient boosting (GWXGBoost) increased 1.98% 14.29%, while RMSE decreased 1.81% 11.98%. Among GWRF model performed best effectively reduced uncertainty mapping. Mean Annual Precipitation Normalized Difference Vegetation Index are two key influencing pH, they significant negative impact on distribution pH. These findings provide scientific basis effective health implementation modeling programs.

Language: Английский

Citations

0
A Novel Methodological Framework for Decoding the Spatial Pattern of Pm2.5 Pollution DOI
Yanyan Wang,

Zhongwei Luo,

Haoqi Wang

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
An interpretable spatially weighted machine learning approach for revealing spatial nonstationarity impacts of the built environment on air pollution DOI

Shumin Wang,

Mingxing Hu, Jianyu Li

et al.

Building and Environment, Journal Year: 2025, Volume and Issue: unknown, P. 113150 - 113150

Published: May 1, 2025

Language: Английский

Citations

0
Correlation or Causation: Unraveling the Relationship between PM2.5 Air Pollution and COVID-19 Spread Across the United States DOI Creative Commons
Mohammad Maniat,

Hosein Habibi,

Elham Manshoorinia

et al.

Journal of Environmental Science and Economics, Journal Year: 2024, Volume and Issue: 3(1), P. 27 - 41

Published: Feb. 17, 2024

Numerous studies have examined the potential connection between air pollution, particularly PM2.5, and incidence of COVID-19 cases during pandemic. While several demonstrated a strong correlation, caution is advised as correlation does not imply causation. To address this concern, our two-year observational study employs comprehensive approach that utilizes large sample size draws on temporal spatial data across United States, surpassing limitations previous restricted to specific locations. Through rigorous regression analyses, we control for confounding factors. Air pollution data, crucial component study, has been sourced from States Environmental Protection Agency (EPA). Additionally, case extracted Center Systems Science Engineering (CSSE) at Johns Hopkins University, providing robust widely recognized dataset analyses. Notably, significant exists population (r=0.98, p-value <0.01), confirmed by multivariate analysis, suggesting influence population. It emphasize automatically direct cause-and-effect relationship. Moreover, minimize impact population, employ rates (COVID-19 cases/population States), demonstrating rate independent PM2.5 infection correlated with density, implying population's more likely due probability rather than being cause. In summary, while many report cases, factors like density necessitates further investigation establish definitive causal conclusion,

Language: Английский

Citations

2
Deriving PM2.5 from satellite observations with spatiotemporally weighted tree-based algorithms: enhancing modeling accuracy and interpretability DOI Creative Commons
Tongwen Li, Yuan Wang, Jingan Wu

et al.

npj Climate and Atmospheric Science, Journal Year: 2024, Volume and Issue: 7(1)

Published: June 18, 2024

Abstract Tree-based machine learning algorithms, such as random forest, have emerged effective tools for estimating fine particulate matter (PM 2.5 ) from satellite observations. However, they typically unchanged model structures and configurations over time space, thus may not fully capture the spatiotemporal variations in relationship between PM predictors, resulting limited accuracy. Here, we propose geographically temporally weighted tree-based models (GTW-Tree) remote sensing of surface . Unlike traditional models, GTW-Tree vary by space to simulate variability estimation, can output variable importance every location deeper understanding determinants. Experiments China demonstrate that significantly outperform conventional with predictive error reduced >21%. The GTW-Tree-derived time-location-specific reveals spatiotemporally varying impacts predictors on Aerosol optical depth (AOD) contributes largely particularly central China. proposed are valuable modeling interpretation other various fields environmental sensing.

Language: Английский

Citations

2
Exploring the spatiotemporal patterns of county-scale PM2.5 drivers in Shandong Province from 2000 to 2020 DOI Creative Commons
Dongchao Wang, Xichun Li,

Xinrong Duan

et al.

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(10), P. e0310190 - e0310190

Published: Oct. 3, 2024

In the rapid development of air pollution over past two decades in Shandong Province, it has played a detrimental role, causing severe damage to regional ecological security and public health. There been little research at county scale explore spatiotemporal causes heterogeneity PM2.5 pollution. This study utilizes Geographically Temporally Weighted Regression Model (GTWR) environmentally model meteorological elements socioeconomic conditions Province from 2000 2020, aiming identify key driving factors concentration changes across 136 counties. The results show that peaked 2013, followed by decline levels. Geographically, counties western plains generally exhibit higher levels, while most central hills Jiaodong Peninsula are low areas. Strong winds positively influence quality southeast Shandong; high temperatures can ameliorate areas outside southeast, whereas pressure exhibits opposite effect. Precipitation shows significant negative correlation Laizhou Bay regions, relative humidity primarily exerts effect coastal impact fractional vegetation cover is relatively mild, with positive effects observed southern other regions. Population density Shandong. Economic predominantly relationships, particularly northwest Peninsula. Electricity consumption correlates positively, industrial province-wide. demonstrates heterogeneity, aligning governmental expectations for effectiveness control measures. conclusions this be utilized assess efficiency abatement level provide quantitative data support revision emission reduction policies.

Language: Английский

Citations

2