{"id":168410,"date":"2015-08-01T00:00:00","date_gmt":"2015-08-01T00:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/forecasting-fine-grained-air-quality-based-on-big-data\/"},"modified":"2018-10-16T20:18:40","modified_gmt":"2018-10-17T03:18:40","slug":"forecasting-fine-grained-air-quality-based-on-big-data","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/forecasting-fine-grained-air-quality-based-on-big-data\/","title":{"rendered":"Forecasting Fine-Grained Air Quality Based on Big Data"},"content":{"rendered":"<div class=\"asset-content\">\n<p>In this paper, we forecast the reading of an air quality monitoring station in the next 48 hours, using a data-driven method that considers the current meteorological data, weather forecasts, and the air quality data of the station and that of other stations within a few hundred kilometers to the station. Our predictive model is comprised of four major components: 1) a linear regression-based temporal predictor to model the local factor of air quality, 2) a neural network-based spatial predictor modeling the global factors, 3) a dynamic aggregator combining the predictions of the spatial and temporal predictors according to the meteorological data, and 4) an inflection predictor to capture the sudden changes of air quality. We evaluate our model with the data of 43 cities in China, surpassing the results of multiple baseline methods. We have deployed a system in Chinese Ministry of Environmental Protection, providing 48-hour fine-grained air quality forecasts for four major Chinese cities every hour. The forecast function is also enabled on Microsoft Bing Map and MS cloud platform Azure. Our technology is general and can be applied globally for other cities.<\/p>\n<p>(<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/02\/Data-1.zip\">Data<\/a>)(<a href=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/02\/forecasting20air20quality-kdd2015-presentation-yuzheng.pptx\">PPT<\/a>)<\/p>\n<div style=\"width: 1920px;\" class=\"wp-video\"><!--[if lt IE 9]><script>document.createElement('video');<\/script><![endif]-->\n<video class=\"wp-video-shortcode\" id=\"video-168410-1\" width=\"1920\" height=\"1080\" preload=\"metadata\" controls=\"controls\"><source type=\"video\/mp4\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/06\/Air-quality-forecast.mp4?_=1\" \/><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/06\/Air-quality-forecast.mp4\">https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2016\/06\/Air-quality-forecast.mp4<\/a><\/video><\/div>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>In this paper, we forecast the reading of an air quality monitoring station in the next 48 hours, using a data-driven method that considers the current meteorological data, weather forecasts, and the air quality data of the station and that of other stations within a few hundred kilometers to the station. Our predictive model is [&hellip;]<\/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":[13556,13563],"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":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-168410","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-data-platform-analytics","msr-locale-en_us"],"msr_publishername":"KDD 2015","msr_edition":"Proceedings of the 21th SIGKDD conference on Knowledge Discovery and Data Mining","msr_affiliation":"","msr_published_date":"2015-08-01","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":"204224","msr_publicationurl":"http:\/\/urbanair.msra.cn\/","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"Forecasting%20air%20qualtiy-kdd2015-camera-ready.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/Forecasting20air20qualtiy-kdd2015-camera-ready.pdf","id":204224,"label_id":0},{"type":"file","title":"Data.zip","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/Data-1.zip","id":204225,"label_id":0},{"type":"file","title":"forecasting%20air%20quality-kdd2015-presentation-yuzheng.pptx","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/forecasting20air20quality-kdd2015-presentation-yuzheng.pptx","id":204223,"label_id":0},{"type":"url","title":"http:\/\/urbanair.msra.cn\/","viewUrl":false,"id":false,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":0,"url":"http:\/\/urbanair.msra.cn\/"},{"id":204225,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/Data-1.zip"},{"id":204224,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/Forecasting20air20qualtiy-kdd2015-camera-ready.pdf"},{"id":204223,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/02\/forecasting20air20quality-kdd2015-presentation-yuzheng.pptx"}],"msr-author-ordering":[{"type":"user_nicename","value":"yuzheng","user_id":35088,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=yuzheng"},{"type":"text","value":"Xiuwen Yi","user_id":0,"rest_url":false},{"type":"user_nicename","value":"mili","user_id":32926,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=mili"},{"type":"text","value":"Ruiyuan Li","user_id":0,"rest_url":false},{"type":"text","value":"Zhangqing Shan","user_id":0,"rest_url":false},{"type":"user_nicename","value":"echang","user_id":31709,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=echang"},{"type":"text","value":"Tianrui Li","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[199560],"msr_event":[],"msr_group":[],"msr_project":[171316,170824],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":171316,"post_title":"Urban Air","post_name":"urban-air","post_type":"msr-project","post_date":"2014-03-24 02:17:14","post_modified":"2018-04-02 19:26:10","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/urban-air\/","post_excerpt":"Using a diversity of big data to infer and predict fine-grained air quality throughout a city, and finally tackle air pollutions. \u00a0 http:\/\/urbanair.msra.cn\/\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0Install Mobile Apps Many countries are suffering from air pollutions. Many cities have built a few\u00a0air quality monitoring stations to inform people urban air quality every hour. Influenced by multiple complex factors, however,\u00a0urban air quality is\u00a0highly skewed in a city, varying by locations significantly and changing over time differently in different places.&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/171316"}]}},{"ID":170824,"post_title":"Urban Computing","post_name":"urban-computing","post_type":"msr-project","post_date":"2016-07-03 10:26:01","post_modified":"2018-04-07 17:32:40","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/urban-computing\/","post_excerpt":"Concept\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 (\u4e2d\u6587\u4e3b\u9875) Urban computing is a process of acquisition, integration, and analysis of big and heterogeneous data generated by a diversity of sources in urban spaces, such as sensors, devices, vehicles, buildings, and human, to tackle the major issues that cities face, e.g. air pollution, increased energy consumption and traffic congestion. Urban computing connects unobtrusive and ubiquitous sensing technologies, advanced data management and analytics models, and novel visualization methods, to create win-win-win solutions that improve&hellip;","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/170824"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/168410"}],"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":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/168410\/revisions"}],"predecessor-version":[{"id":525870,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/168410\/revisions\/525870"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=168410"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=168410"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=168410"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=168410"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=168410"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=168410"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=168410"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=168410"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=168410"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=168410"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=168410"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=168410"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=168410"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=168410"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=168410"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=168410"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}