FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3120307210> ?p ?o ?g. }

• W3120307210 endingPage "118209" @default.
• W3120307210 startingPage "118209" @default.
• W3120307210 abstract "PM 2.5 is an important atmospheric constituent associated to human health. Therefore, the capability of estimating PM 2.5 concentrations at high spatiotemporal resolutions, particularly in places with no ground stations, would be invaluable. Although several studies have involved the estimation of PM 2.5 , few have estimated PM 2.5 concentrations at high spatial resolutions. In this study, we leverage the aerosol optical depth (AOD) and random forest (RF) algorithm to estimate daily 1-km PM 2.5 concentrations over Texas from 2014 to 2018. For this purpose, we use collection 6 Multi-Angle Implementation of Atmospheric Correction (MAIAC) AOD products from the Moderate Resolution Imaging Spectroradiometer (MODIS). To address the different sources and speciation of PM 2.5 over Texas, we use several important control parameters. As a result, the accuracy of RF remains consistent throughout the study area. After estimating ground-level PM 2.5 levels, we apply a ten-fold cross-validation approach to obtain a correlation coefficient ( R ) of 0.83–0.90 and a mean absolute bias (MAB) of 1.47–1.77 μg/m 3 . Our results show that RF is highly capable of estimating ground-level PM 2.5 concentrations. In addition to the RF model, we also compare the capability of commonly used models, including multiple linear regression (MLR) and mixed effects model (MEM), for estimating the PM 2.5 concentrations of global regions. Results indicate that RF, compared to the other models, has the highest accuracy, MEM the second-highest, and MLR the third. We also leverage the USEPA Environmental Benefits Mapping and Analysis Program Community Edition (BenMAP-CE) to estimate the impact of changes in PM 2.5 levels on the number of respiratory-related premature mortalities in Texas in 2014–2018. Considering 2014 as the baseline year, the BenMAP analyses reveal that PM 2.5 reductions could have prevented a large number of premature mortalities, particularly among adults aged 25–99, from 2014 to 2018 in Texas. • We used MAIAC AOD and random forest model to estimate daily PM 2.5 levels in Texas. • Random forest showed a strong capability for PM 2.5 estimation (CV R: 0.83–0.90). • The accuracy of the random forest model was consistent throughout the study area. • The capability of different models for PM 2.5 estimation was tested in this study. • BenMAP showed that PM 2.5 reductions could have prevented many premature deaths." @default.
• W3120307210 created "2021-01-18" @default.
• W3120307210 creator A5011146766 @default.
• W3120307210 creator A5012790271 @default.
• W3120307210 creator A5026764121 @default.
• W3120307210 creator A5035870471 @default.
• W3120307210 creator A5037692383 @default.
• W3120307210 creator A5068158544 @default.
• W3120307210 date "2021-02-01" @default.
• W3120307210 modified "2023-10-16" @default.
• W3120307210 title "Estimating daily high-resolution PM2.5 concentrations over Texas: Machine Learning approach" @default.
• W3120307210 cites W1173523477 @default.
• W3120307210 cites W1819362720 @default.
• W3120307210 cites W1974759371 @default.
• W3120307210 cites W1984153926 @default.
• W3120307210 cites W1987098847 @default.
• W3120307210 cites W1990858038 @default.
• W3120307210 cites W2005259442 @default.
• W3120307210 cites W2008919671 @default.
• W3120307210 cites W2011740524 @default.
• W3120307210 cites W2016199013 @default.
• W3120307210 cites W2025772648 @default.
• W3120307210 cites W2029401079 @default.
• W3120307210 cites W2037329711 @default.
• W3120307210 cites W2038343834 @default.
• W3120307210 cites W2039240409 @default.
• W3120307210 cites W2066387723 @default.
• W3120307210 cites W2069977802 @default.
• W3120307210 cites W2077288509 @default.
• W3120307210 cites W2080649592 @default.
• W3120307210 cites W2081990052 @default.
• W3120307210 cites W2085260550 @default.
• W3120307210 cites W2086810878 @default.
• W3120307210 cites W2088115529 @default.
• W3120307210 cites W2092953734 @default.
• W3120307210 cites W2094440342 @default.
• W3120307210 cites W2095478908 @default.
• W3120307210 cites W2103893521 @default.
• W3120307210 cites W2108162680 @default.
• W3120307210 cites W2110673467 @default.
• W3120307210 cites W2112869689 @default.
• W3120307210 cites W2119582180 @default.
• W3120307210 cites W2142749598 @default.
• W3120307210 cites W2145265567 @default.
• W3120307210 cites W2152657820 @default.
• W3120307210 cites W2161669929 @default.
• W3120307210 cites W2168593932 @default.
• W3120307210 cites W2169262944 @default.
• W3120307210 cites W2252305884 @default.
• W3120307210 cites W2275537745 @default.
• W3120307210 cites W2294879709 @default.
• W3120307210 cites W2323483937 @default.
• W3120307210 cites W2404713802 @default.
• W3120307210 cites W2469366019 @default.
• W3120307210 cites W2516758599 @default.
• W3120307210 cites W2520198120 @default.
• W3120307210 cites W2553429315 @default.
• W3120307210 cites W2611772571 @default.
• W3120307210 cites W2617655798 @default.
• W3120307210 cites W2620300958 @default.
• W3120307210 cites W2745393078 @default.
• W3120307210 cites W2766668310 @default.
• W3120307210 cites W2792885425 @default.
• W3120307210 cites W2793935423 @default.
• W3120307210 cites W2794260655 @default.
• W3120307210 cites W2794664463 @default.
• W3120307210 cites W2883213919 @default.
• W3120307210 cites W2887101236 @default.
• W3120307210 cites W2891119716 @default.
• W3120307210 cites W2908201380 @default.
• W3120307210 cites W2940897106 @default.
• W3120307210 cites W2952215413 @default.
• W3120307210 cites W2953978338 @default.
• W3120307210 cites W2962232058 @default.
• W3120307210 cites W2963325458 @default.
• W3120307210 cites W2966752805 @default.
• W3120307210 cites W2981441128 @default.
• W3120307210 cites W3014859458 @default.
• W3120307210 cites W3024068309 @default.
• W3120307210 cites W3082513963 @default.
• W3120307210 cites W3084362562 @default.
• W3120307210 cites W561421126 @default.
• W3120307210 doi "https://doi.org/10.1016/j.atmosenv.2021.118209" @default.
• W3120307210 hasPublicationYear "2021" @default.
• W3120307210 type Work @default.
• W3120307210 sameAs 3120307210 @default.
• W3120307210 citedByCount "30" @default.
• W3120307210 countsByYear W31203072102021 @default.
• W3120307210 countsByYear W31203072102022 @default.
• W3120307210 countsByYear W31203072102023 @default.
• W3120307210 crossrefType "journal-article" @default.
• W3120307210 hasAuthorship W3120307210A5011146766 @default.
• W3120307210 hasAuthorship W3120307210A5012790271 @default.
• W3120307210 hasAuthorship W3120307210A5026764121 @default.
• W3120307210 hasAuthorship W3120307210A5035870471 @default.
• W3120307210 hasAuthorship W3120307210A5037692383 @default.
• W3120307210 hasAuthorship W3120307210A5068158544 @default.
• W3120307210 hasBestOaLocation W31203072101 @default.

• next