{"id":891531,"date":"2022-10-24T09:48:22","date_gmt":"2022-10-24T16:48:22","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/"},"modified":"2024-01-22T12:09:35","modified_gmt":"2024-01-22T20:09:35","slug":"intraurban-no2-hotspot-detection-via-clustering-of-in-situ-remote-and-modeled-air-quality-data-products","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/intraurban-no2-hotspot-detection-via-clustering-of-in-situ-remote-and-modeled-air-quality-data-products\/","title":{"rendered":"Intraurban NO2 hotspot detection via clustering of in-situ, remote, and modeled air quality data products"},"content":{"rendered":"
Novel\u00a0<\/span>air quality\u00a0<\/span>data sources promise unprecedented insights on intra-urban variations in\u00a0<\/span>air pollution<\/span>\u00a0<\/span>by enabling\u00a0<\/span>stakeholders\u00a0<\/span>to\u00a0<\/span>identify<\/span>\u00a0and mitigate hotspots<\/span>.<\/span>\u00a0However, s<\/span>parse regulatory networks limit validation<\/span>\u00a0of novel datasets<\/span>,<\/span>\u00a0resulting in\u00a0<\/span>pollutant exposure<\/span>\u00a0estimates\u00a0<\/span>that are<\/span>\u00a0likely to be noisy\u00a0<\/span>and difficult to cross-analyze<\/span>\u00a0across platforms<\/span>.<\/span>\u00a0<\/span>In this study,\u00a0<\/span>we\u00a0<\/span>identify<\/span>\u00a0and evaluate\u00a0<\/span>clusters<\/span>\u00a0of\u00a0<\/span>NO<\/span><\/span>2<\/span><\/span><\/sub>\u00a0<\/span>using the\u00a0<\/span>Getis<\/span>-Ord G* statistic\u00a0<\/span>across Chicago, IL using three\u00a0<\/span>novel<\/span>\u00a0<\/span>air quality datasets<\/span>:<\/span>\u00a0(1) a two-way\u00a0<\/span>coupled\u00a0<\/span>WRF-CMAQ simulation<\/span>\u00a0performed at\u00a0<\/span>1.3 km\u00a0<\/span>resolution<\/span>; (2) the\u00a0<\/span>TropOMI<\/span>\u00a0satellite instrument; and (3) a<\/span>\u00a0high-density<\/span>\u00a0network of<\/span>\u00a0l<\/span>ow-cost\u00a0<\/span>air quality\u00a0<\/span>sensors deployed through the Microsoft Eclipse project. We\u00a0<\/span>identify<\/span>\u00a0a large, statistically significant cluster of heightened exposures that is\u00a0<\/span>observed<\/span>\u00a0across all three data sources, enabling us to report with high confidence the presence of a \u201ctrue\u201d hotspot<\/span>,<\/span>\u00a0despite a dearth of regulatory data in the affected area. Moreover, using the temporally fine-grained data sets (WRF-CMAQ and Eclipse), we\u00a0<\/span>observe<\/span>\u00a0that the hotspot is consistent across dominant wind directions. By analyzing the disagreement across\u00a0<\/span>clusters,<\/span>\u00a0we may systematically analyze the reasons for divergence.<\/span>\u00a0For example,<\/span>\u00a0a hotspot that\u00a0<\/span>emerges<\/span>\u00a0in the<\/span>\u00a0observational datasets<\/span>\u00a0but\u00a0<\/span>not<\/span>\u00a0modeled dataset\u00a0<\/span>enables us to interrogate model biases with respect to\u00a0<\/span>underlying\u00a0<\/span>emissions\u00a0<\/span>and meteorological performance<\/span>.\u00a0<\/span>To contrast,\u00a0<\/span>hotspot<\/span>s<\/span>\u00a0<\/span>simulated<\/span>\u00a0<\/span>by WRF-CMAQ\u00a0<\/span>but not\u00a0<\/span>observed<\/span>\u00a0by sensors<\/span>\u00a0<\/span>enable<\/span>\u00a0us to prioritize new locations for sensor deployment. This work offers an example of how researchers can\u00a0<\/span>utilize<\/span>\u00a0and build confidence in<\/span>\u00a0multiple sources of novel air quality data<\/span>. As such, these\u00a0<\/span>complementary<\/span>\u00a0tools\u00a0<\/span>can be used<\/span>\u00a0to<\/span>\u00a0both<\/span>\u00a0evaluate confidence in policy-relevant insights and<\/span>\u00a0to<\/span>\u00a0interrogate and improve\u00a0<\/span>discrepancies across datasets<\/span>.<\/span><\/span><\/p>\n","protected":false},"excerpt":{"rendered":" Novel\u00a0air quality\u00a0data sources promise unprecedented insights on intra-urban variations in\u00a0air pollution\u00a0by enabling\u00a0stakeholders\u00a0to\u00a0identify\u00a0and mitigate hotspots.\u00a0However, sparse regulatory networks limit validation\u00a0of novel datasets,\u00a0resulting in\u00a0pollutant exposure\u00a0estimates\u00a0that are\u00a0likely to be noisy\u00a0and difficult to cross-analyze\u00a0across platforms.\u00a0In this study,\u00a0we\u00a0identify\u00a0and evaluate\u00a0clusters\u00a0of\u00a0NO2\u00a0using the\u00a0Getis-Ord G* statistic\u00a0across Chicago, IL using three\u00a0novel\u00a0air quality datasets:\u00a0(1) a two-way\u00a0coupled\u00a0WRF-CMAQ simulation\u00a0performed at\u00a01.3 km\u00a0resolution; (2) the\u00a0TropOMI\u00a0satellite instrument; and (3) a\u00a0high-density\u00a0network of\u00a0low-cost\u00a0air […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,198583],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[246685,246850],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-891531","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-ecology-environment","msr-locale-en_us","msr-field-of-study-machine-learning","msr-field-of-study-sustainability"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2022-12-15","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/agu.confex.com\/agu\/fm22\/meetingapp.cgi\/Paper\/1172485","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Anastasia Montgomery","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Madeleine Daepp","user_id":39856,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Madeleine Daepp"},{"type":"user_nicename","value":"Marah Abdin","user_id":39657,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Marah Abdin"},{"type":"text","value":"Pallavi Choudry","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Sara Malvar","user_id":40753,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Sara Malvar"},{"type":"user_nicename","value":"Scott Counts","user_id":31471,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Scott Counts"},{"type":"text","value":"Daniel E Horton","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[992148],"msr_event":[],"msr_group":[144894,714067],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/891531"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/891531\/revisions"}],"predecessor-version":[{"id":1001139,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/891531\/revisions\/1001139"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=891531"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=891531"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=891531"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=891531"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=891531"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=891531"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=891531"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=891531"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=891531"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=891531"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=891531"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=891531"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=891531"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=891531"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=891531"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=891531"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}