Atmospheric Pollution Research最新文献

{"title":"Machine learning analysis of drivers of differences in PAH content between PM1 and PM10 in Zagreb, Croatia","authors":"Nikolina Račić ,&nbsp;Gordana Pehnec ,&nbsp;Ivana Jakovljević ,&nbsp;Zdravka Sever Štrukil ,&nbsp;Francesco Mureddu ,&nbsp;Michael Forsmann ,&nbsp;Mario Lovrić","doi":"10.1016/j.apr.2025.102541","DOIUrl":"10.1016/j.apr.2025.102541","url":null,"abstract":"<div><div>Particulate matter (PM) is a critical component of air pollution, with its size fractions, PM₁ and PM₁₀, posing varying risks to human health. Among its constituents, polycyclic aromatic hydrocarbons (PAHs) are of particular concern due to their toxicity and ability to affect respiratory health. PM₁ particles, being smaller, can penetrate deeper into the respiratory system, making the distribution of PAHs across PM₁ and PM₁₀ especially relevant. This study examines the seasonal patterns and factors influencing PAH concentrations in PM₁ and PM₁₀ collected in Zagreb, Croatia. A combination of machine learning (ML) techniques, including Random Forest (RF) regression and Principal Component Analysis (PCA), and statistical approaches like t-tests and Cohen's d, were applied to explore these relationships. Post-hoc interpretation using SHapley Additive exPlanations (SHAP) clarified the contribution of various predictors in the models. Results indicated that PAH concentrations contributions were higher in PM₁ than PM₁₀, posing greater health risks associated with finer particles. Seasonal trends showed increased PAH levels during winter and spring, primarily driven by heating activities and temperature inversions. The study also highlighted the \"J_Curve_Day\" variable as the most critical predictor in RF regression models, capturing the influence of seasonal changes on PAH levels through its representation of meteorological conditions and atmospheric processes. These insights shows the importance of understanding seasonal variability in PAH distributions within PM to inform air quality management and public health strategies.</div></div>","PeriodicalId":8604,"journal":{"name":"Atmospheric Pollution Research","volume":"16 7","pages":"Article 102541"},"PeriodicalIF":3.9,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantitative source apportionment of surface ozone in Liaoning Province, China, under the Asian summer monsoon background","authors":"Ningwei Liu ,&nbsp;Simeng Ma ,&nbsp;Kun Wang ,&nbsp;Sen Yang ,&nbsp;Zhigang Zhang","doi":"10.1016/j.apr.2025.102540","DOIUrl":"10.1016/j.apr.2025.102540","url":null,"abstract":"<div><div>At present, few quantitative study has been carried out on the proportion of local generation and long range transport of ozone in Liaoning, which is the key to reveal regional ozone pollution. Using the Ozone Source Apportionment Technology in the CAMx model, surface ozone concentrations in Liaoning Province, China, were simulated during the warm season of 2023. The contributions of 23 source regions, five industrial sectors, and two chemical precursors to ozone concentrations in 14 cities in Liaoning were determined under the Asian summer monsoon (ASM) background. The major components were lowest in May and increased from June to August, reflecting a significant increase in the northward transport of ozone and its precursors from upstream regions (north and east China) with the onset of the ASM. The contribution of surrounding provinces to Liaoning's ozone embodied the principle of \"proximity and directness\" - the more direct the transport direction of the ASM and the closer the source province to the receptor city, the greater the contribution from source to receptor. Under the ASM background, most ozone was transported from upwind to downwind cities within Liaoning (e.g., Dalian contributed 1.44 % to Anshan, Dandong contributed 1.76 % to Benxi), indicating that the prevailing southwest wind transported ozone and its precursors from upstream cities, contributing to the ozone concentrations in downstream cities. The results may provide reference for regional ozone pollution control.</div></div>","PeriodicalId":8604,"journal":{"name":"Atmospheric Pollution Research","volume":"16 7","pages":"Article 102540"},"PeriodicalIF":3.9,"publicationDate":"2025-04-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143828968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Atmospheric microplastic deposition in Guilin karst wetlands: Sources and agricultural impact","authors":"Lishan Zhang,&nbsp;Bihong Xu,&nbsp;Zengxian Wei,&nbsp;Xiaolu Liang,&nbsp;Yan Chen,&nbsp;Xuan Ru,&nbsp;Qian Zhang,&nbsp;Shan Zhong","doi":"10.1016/j.apr.2025.102537","DOIUrl":"10.1016/j.apr.2025.102537","url":null,"abstract":"<div><div>Atmospheric deposition of microplastics (MPs) poses a significant threat to natural wetlands. This study investigates the characteristics, distribution, and sources of atmospheric MPs in the Huixian Wetland, focusing on the influence of land use and human activities. The results show an average MP deposition rate of 98.85 ± 43.50 items·m⁻²·d⁻¹, with wet deposition at 110.93 ± 42.67 items·m⁻²·d⁻¹ and dry deposition at 86.17 ± 41.67 items·m⁻²·d⁻¹. Deposition rates were found to be significantly higher in non-wetland park areas compared to wetland parks. MPs smaller than 500 μm comprised 60 % of the total, predominantly fibrous (93 %) and colorless or transparent (83 %). The dominant polymers were PE (31 %) and PP (23 %). The primary source of atmospheric MPs in the Huixian Wetland is local agricultural activity. Cluster analysis indicates that atmospheric MPs serve as a major source of microplastics in other environmental media within the wetland. The geological characteristics of the wetland, coupled with agricultural practices, exacerbate microplastic pollution. Additionally, human activities such as tourism and transportation contribute to the influx of MPs into the wetland. This study provides essential insights for the management and reduction of MP pollution in karst wetlands and protected areas.</div></div>","PeriodicalId":8604,"journal":{"name":"Atmospheric Pollution Research","volume":"16 8","pages":"Article 102537"},"PeriodicalIF":3.9,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143874140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimation and impact factor analysis of 24-h near-surface ozone concentration in China using FY-4A/B collaboration and machine learning","authors":"Yixuan Wang ,&nbsp;Bin Chen ,&nbsp;Qia Ye ,&nbsp;Lin Zhao ,&nbsp;Zhihao Song","doi":"10.1016/j.apr.2025.102538","DOIUrl":"10.1016/j.apr.2025.102538","url":null,"abstract":"<div><div>Ozone pollution in China's urban agglomerations poses a significant environmental challenge. Nine machine learning models were constructed based on the Extra Tree (ET) algorithm, utilizing top-of-atmosphere radiation (TOAR) data from Fengyun (FY)-4A and FY-4B Advanced Geosynchronous Radiation Imager (AGRI), to estimate 24-h near-surface ozone concentrations across China from June 2022 to May 2023. Analysis identified five TOAR channels strongly correlated with ozone concentrations: channels 7, 8, and 11–13 for FY-4A, and channels 7, 8, and 12–14 for FY-4B. The all-sky data model demonstrated superior performance in ozone estimation, achieving an R² of 0.91, outperforming models using only cloudy or clear-sky data. Through partial dependency plots and feature importance assessments, key meteorological drivers were identified: relative humidity below 60 % and temperatures between 20 and 35 °C. These findings provide valuable insights for ozone forecasting and pollution control strategies.</div></div>","PeriodicalId":8604,"journal":{"name":"Atmospheric Pollution Research","volume":"16 7","pages":"Article 102538"},"PeriodicalIF":3.9,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143828967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The heat-pollution paradox: understanding the relationship between land surface temperature and air pollution in a heavily polluted megacity","authors":"Manob Das ,&nbsp;Arijit Das ,&nbsp;Suman Singha","doi":"10.1016/j.apr.2025.102531","DOIUrl":"10.1016/j.apr.2025.102531","url":null,"abstract":"<div><div>In rapidly urbanizing megacities, increasing land surface temperature (LST) and acute air pollution present considerable environmental and public health issues. Urban sprawl, industrial discharges, and automotive emissions degrade air quality, while heat-absorbing surfaces exacerbate urban heat island (UHI) phenomena. Comprehending the correlation between LST and air pollution is essential, as elevated temperatures can exacerbate pollutant concentrations via photochemical reactions and meteorological alterations. This study aims to assess the relationship between LST and air pollution during winter and summer in Delhi (India) using Remote Sensing and National Air Quality Monitoring Program (NAMP). The findings showed that the LST in Delhi exhibited seasonal variation, with summer LST reaching a maximum of 31.08 °C (mean: 28.99 °C) and winter LST declining to 16.30 °C (mean: 18.29 °C). Elevated LST were recorded in the northern, eastern, and western regions during the summer season. Air pollution exacerbated in winter, with particulate matter i.e. PM_2.5 and PM₁₀ concentrations attaining 277.13 μg/m³ and 228.33 μg/m³, respectively, whilst O₃ concentrations peak in summer at 41.08 μg/m³. The core areas maintained higher LST than the transitional zones. PM₁₀ exhibited a strong correlation with LST (winter: 0.611, summer: 0.222), affecting heat retention, but CO and O₃ demonstrated weak correlations relationships. Increased winter PM₁₀ levels (0.767) correlated with heightened summer surface UHI (SUHI), underscoring the significance of PM in warming. The study emphasized the necessity of targeted mitigation strategies, such as the expansion of urban natural infrastructure, to mitigate LST and air pollution. Policies should prioritize the integration of heat mitigation measures into city planning, the enhancement of air quality monitoring, and the regulation of winter PM levels.</div></div>","PeriodicalId":8604,"journal":{"name":"Atmospheric Pollution Research","volume":"16 8","pages":"Article 102531"},"PeriodicalIF":3.9,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143855410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Physico-chemical characterization of atmospheric particles during two intense dust storms in the vicinity of Thar Desert","authors":"Mamta Devi ,&nbsp;Sumit Kumar Mishra ,&nbsp;Aravindakshan Jayakumar ,&nbsp;Supreet Kaur ,&nbsp;Vikas Goel ,&nbsp;Vijayan Narayanasamy ,&nbsp;Gounda Abdul Basheed ,&nbsp;Kartika Pandey","doi":"10.1016/j.apr.2025.102532","DOIUrl":"10.1016/j.apr.2025.102532","url":null,"abstract":"<div><div>Particulate Matter (PM₅; aerodynamic diameter ≤5 μm) was collected over the Jhunjhunu region (28°80′N, 75°24′E) in the neighborhood of the Thar Desert, Rajasthan, India. Sample collection was done during two intense Dust Storm (DS) conditions i.e., DS-1 on May 4, 2022 and DS-2 on May 6, 2022. The physico-chemical properties of dust particles collected pre-, during, and post-DS events were studied using X-ray diffraction (XRD), X-ray Fluorescence Spectroscopy (XRF), and Scanning Electron Microscope coupled with Energy Dispersive X-ray Spectroscopy (SEM-EDS). The frequency distribution of AR (Aspect Ratio) of particles shows bimodal peaks in the bin range &gt;1.6–1.8 and &gt; 2.00–2.20 during DS-1 and monomodal peak at &gt;1.6–1.8 during DS-2, indicating most of the particles are highly non-spherical. Based on bulk compositional analysis of dust particles obtained using XRF, oxides of different elements were observed in the order of SiO₂&gt; Al₂O₃&gt; CaCO₃&gt;MgO &gt; Fe₂O₃&gt; Cr₂O₃ during both storms. Hematite (Fe₂O₃) which has high absorption potential in visible and near UV Wavelength is found to increase from 1.47 % (pre-DS) to 6.14 % (DS-1) and 5.43 % (DS-2), respectively. For the visible range spectrum (0.38–0.68 μm), it is discovered that the imaginary part of the refractive index (k) value rises from 0.004 to 0.048 during DS-1 and from 0.003 to 0.045 during DS-2. The present work could reduce the uncertainty in the radiation budget estimations of mineral dust over the Thar Desert region.</div></div>","PeriodicalId":8604,"journal":{"name":"Atmospheric Pollution Research","volume":"16 8","pages":"Article 102532"},"PeriodicalIF":3.9,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Seasonal variations and risk assessment of PAHs in Xiamen: Insights into the impacts of local and long-range transport sources","authors":"Zheng Zhang ,&nbsp;Haolong Zhang ,&nbsp;Cheng Luo ,&nbsp;Minggang Cai ,&nbsp;Lei Wang ,&nbsp;Bin Yan ,&nbsp;Yan Lin","doi":"10.1016/j.apr.2025.102536","DOIUrl":"10.1016/j.apr.2025.102536","url":null,"abstract":"<div><div>Polycyclic aromatic hydrocarbons (PAHs) are among the most toxic pollutants in air pollution with severe health implications, yet their seasonal characteristics and health risk based on specific sources from local and long-range transport in coastal cities are insufficiently studied. This research presents a detailed seasonal analysis of 29 PAHs in atmospheric particulate matter across five districts of Xiamen, China. The study found clear seasonal variations due to monsoon climate, with the highest PAH concentrations observed in winter (mean 69.70 ng/m³), 2.9 times higher than in summer (mean 23.88 ng/m³). The higher winter concentrations are mainly attributed to the influx of pollution-laden air masses from northern China. In contrast, the reduced levels in summer might be due to frequent rainfall, stronger photochemical degradation and the dilution effect of clean air masses from the ocean. The main sources were transportation emission (32.1 %), petrogenic source (30.5 %), biomass combustion (28.5 %), and coal combustion (8.9 %). Health risk assessments indicated that winter posed the greatest health risks, with carcinogenic and mutagenic risks up to 5.35 times higher than in summer, particularly in districts like Jimei, where traffic-related PAHs contributed to 43.3 % of the total risk, while Oil spill-related emissions in Haicang were responsible for 50 % of the carcinogenic toxicity in that district. Women face higher health risks than men, with greater risks near transportation hubs and industrial areas. These findings underscore the impact of external pollution on Xiamen's atmospheric PAHs, emphasizing the need for targeted winter pollution control.</div></div>","PeriodicalId":8604,"journal":{"name":"Atmospheric Pollution Research","volume":"16 7","pages":"Article 102536"},"PeriodicalIF":3.9,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143828969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Long term (2011–2023) analysis of traffic and biomass burning contributions to black carbon in the third largest metropolitan area of Spain","authors":"Violeta Matos ,&nbsp;Mar Sorribas ,&nbsp;Sara Segura ,&nbsp;María Pilar Utrillas ,&nbsp;Víctor Estellés","doi":"10.1016/j.apr.2025.102527","DOIUrl":"10.1016/j.apr.2025.102527","url":null,"abstract":"<div><div>This work is focused on the temporal characterization of equivalent Black Carbon (eBC) mass concentrations and their sources in a suburban station notably impacted by traffic, located in the metropolitan area of Valencia, Spain (western Mediterranean Sea). The average (<span><math><mo>±</mo></math></span> standard deviation) concentrations of fossil fuel (eBC_ff) and biomass burning (eBC_bb) contributions were 0.9 <span><math><mo>±</mo></math></span> <span><math><mrow><mn>0</mn><mo>.</mo><mn>5</mn></mrow></math></span> <span><math><mrow><mi>μ</mi><msup><mrow><mi>gm</mi></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span> and 0.06 <span><math><mo>±</mo></math></span> <span><math><mrow><mn>0</mn><mo>.</mo><mn>05</mn></mrow></math></span> <span><math><mrow><mi>μ</mi><msup><mrow><mi>gm</mi></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span>, respectively. These values represent the anthropogenic character of local aerosols. Both contributions also show a very marked seasonality: higher values in winter and lower in summer, corresponding to the strong dependence of the atmospheric conditions. The eBC_ff concentrations exhibit a daily pattern consistent with the evolution of traffic: a morning peak (around 8 LT) and other in the evening (around 19 LT). The seasonal Mann–Kendall test was applied to identify long-term trends and the Sen slope estimation to quantify the annual variation. Decreasing trends were found for eBC_ff concentrations (<span><math><mrow><mo>−</mo><mn>0</mn><mo>.</mo><mn>023</mn></mrow></math></span> <span><math><mrow><mi>μ</mi><msup><mrow><mi>gm</mi></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></math></span>/yr), showing the effectiveness of air quality regulations. Less noticeable trends were found for eBC_bb concentrations. This fact evidences the contribution of biomass burning is not only related to changes in anthropogenic emissions, but also to natural phenomena, making it more difficult to interpret long-term trends.</div></div>","PeriodicalId":8604,"journal":{"name":"Atmospheric Pollution Research","volume":"16 7","pages":"Article 102527"},"PeriodicalIF":3.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143823695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing atmospheric particulate matters and their removal potential through roadside trees in Chattogram city, Bangladesh","authors":"Nayeem Uddin Emon ,&nbsp;Chinmoy Sarkar Anik ,&nbsp;Forkan Ahamed Rubel ,&nbsp;Sahadeb Chandra Majumder ,&nbsp;Tapan Kumar Nath ,&nbsp;Shyamal Karmakar ,&nbsp;Tarit Kumar Baul","doi":"10.1016/j.apr.2025.102535","DOIUrl":"10.1016/j.apr.2025.102535","url":null,"abstract":"<div><div>Atmospheric particulate matter (PM) affects urban air quality and poses significant health risks. In this study, we measured ambient PM levels and heavy metal concentrations at six vegetated and one non-vegetated (control) roadside locations in Chattogram City, Bangladesh. Using a portable air quality sensor, we assessed ambient PM_0.5 and PM_2.5 concentrations every 15 days over the course of one year and found that the mean concentrations of PM₀.₅ and PM₂.₅ in the control site were significantly higher (<em>p</em> ≤ 0.05) than those at the vegetated roadsides. We also investigated whether roadside trees can effectively remove PM and collected 84 leaf samples from seven tree species each month to quantify PM deposition on the leaves. PM concentrations in the air and on the leaves were higher during the dry season compared to the rainy season. Further analysis of meteorological factors revealed that PM accumulation on the leaves decreased with high temperature, wind speed, and precipitation. These findings suggest that meteorological conditions play a crucial role in PM dynamics, influencing both airborne concentration and accumulation on leaves. Besides, tree species and leaf characteristics play a substantial role in PM accumulation on the leaves. Copper and zinc were in the accumulated PM along all roadsides, indicating the possibility of heavy metal contamination. We propose planting roadside trees with rhomboid, elliptical, rough, and simple leaves to enhance the removal of PM and other contaminants through deposition.</div></div>","PeriodicalId":8604,"journal":{"name":"Atmospheric Pollution Research","volume":"16 7","pages":"Article 102535"},"PeriodicalIF":3.9,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143816432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sulfur dioxide concentrations forecasting using a deep learning model in Quintero, Chile","authors":"Patricio Perez ,&nbsp;Francisco Gomez ,&nbsp;Camilo Menares ,&nbsp;Zoë L. Fleming","doi":"10.1016/j.apr.2025.102534","DOIUrl":"10.1016/j.apr.2025.102534","url":null,"abstract":"<div><div>Close to Quintero, a Chilean coastal city, located 160 km northwest of Santiago, a highly concentrated accumulation of industries generate high levels of atmospheric pollution which significantly affects the quality of life of its rural and urban population. The industrial complex, alongside other smaller industries, is home to an oil refinery, a copper foundry and 3 coal power plants. Sulfur dioxide (SO₂) frequently exceeds international and national standards in the area. Episodes of fainting and poisoning associated to high levels of SO₂ have been reported in Quintero. Due to this situation, it is highly relevant to develop a sulfur dioxide forecasting model which may be used as a tool to warn authorities and the local population about unfavorable air quality conditions. Three SO₂ forecasting models for the city of Quintero based on Machine Learning Techniques have been implemented: a Random Forest model, a Deep Learning Feed Forward model (DFFNN) and a Convolutional Long Short Term Memory (LSTM) Deep Learning model. The goal was to forecast the maximum of the hourly average value of SO₂ for the first 12 h of the following day based on information available during the present day. The LSTM model gives the best results with a 78 % accuracy.</div></div>","PeriodicalId":8604,"journal":{"name":"Atmospheric Pollution Research","volume":"16 8","pages":"Article 102534"},"PeriodicalIF":3.9,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143855409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}