A spatiotemporal ensemble model to predict gross beta particulate radioactivity across the contiguous United States
Particulate radioactivity, a characteristic of particulate matter, is primarily determined by the abundance of radionuclides that are bound to airborne particulates. Exposure to high levels of particulate radioactivity has been associated with negative health outcomes. However, there are currently n...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-11-01
|
| Series: | Environment International |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0160412021002683 |
| _version_ | 1831652391782449152 |
|---|---|
| author | Longxiang Li Annelise J. Blomberg Joy Lawrence Weeberb J. Réquia Yaguang Wei Man Liu Adjani A. Peralta Petros Koutrakis |
| author_facet | Longxiang Li Annelise J. Blomberg Joy Lawrence Weeberb J. Réquia Yaguang Wei Man Liu Adjani A. Peralta Petros Koutrakis |
| author_sort | Longxiang Li |
| collection | DOAJ |
| description | Particulate radioactivity, a characteristic of particulate matter, is primarily determined by the abundance of radionuclides that are bound to airborne particulates. Exposure to high levels of particulate radioactivity has been associated with negative health outcomes. However, there are currently no spatially and temporally resolved particulate radioactivity data for exposure assessment purposes. We estimated the monthly distributions of gross beta particulate radioactivity across the contiguous United States from 2001 to 2017 with a spatial resolution of 32 km, via a multi-stage ensemble-based model. Particulate radioactivity was measured at 129 RadNet monitors across the contiguous U.S. In stage one, we built 264 base learning models using six methods, then selected nine base models that provide different predictions. In stage two, we used a non-negative geographically and temporally weighted regression method to aggregate the selected base learner predictions based on their local performance. The results of block cross-validation analysis suggested that the non-negative geographically and temporally weighted regression ensemble learning model outperformed all base learning model with the smallest rooted mean square error (0.094 mBq/m3). Our model provided an accurate estimation of particulate radioactivity, thus can be used in future health studies. |
| first_indexed | 2024-12-19T15:45:37Z |
| format | Article |
| id | doaj.art-96a37d78a41446f49c913c593675c251 |
| institution | Directory Open Access Journal |
| issn | 0160-4120 |
| language | English |
| last_indexed | 2024-12-19T15:45:37Z |
| publishDate | 2021-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Environment International |
| spelling | doaj.art-96a37d78a41446f49c913c593675c2512022-12-21T20:15:21ZengElsevierEnvironment International0160-41202021-11-01156106643A spatiotemporal ensemble model to predict gross beta particulate radioactivity across the contiguous United StatesLongxiang Li0Annelise J. Blomberg1Joy Lawrence2Weeberb J. Réquia3Yaguang Wei4Man Liu5Adjani A. Peralta6Petros Koutrakis7Department of Environmental Health, Harvard T. H. Chan School of Public Health, Boston, MA 02114, USA; Corresponding author at: Department of Environmental Health, Harvard T.H. Chan School of Public Health, Landmark Center 4th West, 401 Park Drive, Boston, MA 02215, USA.Department of Environmental Health, Harvard T. H. Chan School of Public Health, Boston, MA 02114, USA; Division of Occupational and Environmental Medicine, Lund University, Lund, SwedenDepartment of Environmental Health, Harvard T. H. Chan School of Public Health, Boston, MA 02114, USASchool of Public Policy and Government, Fundação Getúlio Vargas Brasília, Distrito Federal, BrazilDepartment of Environmental Health, Harvard T. H. Chan School of Public Health, Boston, MA 02114, USADepartment of Environmental Health, Harvard T. H. Chan School of Public Health, Boston, MA 02114, USADepartment of Environmental Health, Harvard T. H. Chan School of Public Health, Boston, MA 02114, USADepartment of Environmental Health, Harvard T. H. Chan School of Public Health, Boston, MA 02114, USAParticulate radioactivity, a characteristic of particulate matter, is primarily determined by the abundance of radionuclides that are bound to airborne particulates. Exposure to high levels of particulate radioactivity has been associated with negative health outcomes. However, there are currently no spatially and temporally resolved particulate radioactivity data for exposure assessment purposes. We estimated the monthly distributions of gross beta particulate radioactivity across the contiguous United States from 2001 to 2017 with a spatial resolution of 32 km, via a multi-stage ensemble-based model. Particulate radioactivity was measured at 129 RadNet monitors across the contiguous U.S. In stage one, we built 264 base learning models using six methods, then selected nine base models that provide different predictions. In stage two, we used a non-negative geographically and temporally weighted regression method to aggregate the selected base learner predictions based on their local performance. The results of block cross-validation analysis suggested that the non-negative geographically and temporally weighted regression ensemble learning model outperformed all base learning model with the smallest rooted mean square error (0.094 mBq/m3). Our model provided an accurate estimation of particulate radioactivity, thus can be used in future health studies.http://www.sciencedirect.com/science/article/pii/S0160412021002683Particulate radioactivitySpatiotemporal ensemble learningStatistical learningGeographically and temporally weighted regression |
| spellingShingle | Longxiang Li Annelise J. Blomberg Joy Lawrence Weeberb J. Réquia Yaguang Wei Man Liu Adjani A. Peralta Petros Koutrakis A spatiotemporal ensemble model to predict gross beta particulate radioactivity across the contiguous United States Environment International Particulate radioactivity Spatiotemporal ensemble learning Statistical learning Geographically and temporally weighted regression |
| title | A spatiotemporal ensemble model to predict gross beta particulate radioactivity across the contiguous United States |
| title_full | A spatiotemporal ensemble model to predict gross beta particulate radioactivity across the contiguous United States |
| title_fullStr | A spatiotemporal ensemble model to predict gross beta particulate radioactivity across the contiguous United States |
| title_full_unstemmed | A spatiotemporal ensemble model to predict gross beta particulate radioactivity across the contiguous United States |
| title_short | A spatiotemporal ensemble model to predict gross beta particulate radioactivity across the contiguous United States |
| title_sort | spatiotemporal ensemble model to predict gross beta particulate radioactivity across the contiguous united states |
| topic | Particulate radioactivity Spatiotemporal ensemble learning Statistical learning Geographically and temporally weighted regression |
| url | http://www.sciencedirect.com/science/article/pii/S0160412021002683 |
| work_keys_str_mv | AT longxiangli aspatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT annelisejblomberg aspatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT joylawrence aspatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT weeberbjrequia aspatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT yaguangwei aspatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT manliu aspatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT adjaniaperalta aspatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT petroskoutrakis aspatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT longxiangli spatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT annelisejblomberg spatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT joylawrence spatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT weeberbjrequia spatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT yaguangwei spatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT manliu spatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT adjaniaperalta spatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates AT petroskoutrakis spatiotemporalensemblemodeltopredictgrossbetaparticulateradioactivityacrossthecontiguousunitedstates |