Matches in SemOpenAlex for { <https://semopenalex.org/work/W3151504452> ?p ?o ?g. }
- W3151504452 abstract "Air pollution has long been a serious environmental health challenge, especially in metropolitan cities, where air pollutant concentrations are exacerbated by the street canyon effect and high building density. Whilst accurately monitoring and forecasting air pollution are highly crucial, existing data-driven models fail to fully address the complex interaction between air pollution and urban dynamics. Our Deep-AIR, a novel hybrid deep learning framework that combines a convolutional neural network with a long short-term memory network, aims to address this gap to provide fine-grained city-wide air pollution estimation and station-wide forecast. Our proposed framework creates 1x1 convolution layers to strengthen the learning of cross-feature spatial interaction between air pollution and important urban dynamic features, particularly road density, building density/height, and street canyon effect. Using Hong Kong and Beijing as case studies, Deep-AIR achieves a higher accuracy than our baseline models. Our model attains an accuracy of 67.6%, 77.2%, and 66.1% in fine-grained hourly estimation, 1-hr, and 24-hr air pollution forecast for Hong Kong, and an accuracy of 65.0%, 75.3%, and 63.5% for Beijing. Our saliency analysis has revealed that for Hong Kong, street canyon and road density are the best estimators for NO2, while meteorology is the best estimator for PM2.5." @default.
- W3151504452 created "2021-04-13" @default.
- W3151504452 creator A5026984704 @default.
- W3151504452 creator A5048232137 @default.
- W3151504452 creator A5056877599 @default.
- W3151504452 creator A5082137392 @default.
- W3151504452 date "2021-03-25" @default.
- W3151504452 modified "2023-09-23" @default.
- W3151504452 title "Deep-AIR: A Hybrid CNN-LSTM Framework for Air Quality Modeling in Metropolitan Cities." @default.
- W3151504452 cites W1163725043 @default.
- W3151504452 cites W1799366690 @default.
- W3151504452 cites W1963511811 @default.
- W3151504452 cites W1969526880 @default.
- W3151504452 cites W1969865391 @default.
- W3151504452 cites W1971402834 @default.
- W3151504452 cites W1998504821 @default.
- W3151504452 cites W2044516799 @default.
- W3151504452 cites W2049070055 @default.
- W3151504452 cites W2065947772 @default.
- W3151504452 cites W2075755007 @default.
- W3151504452 cites W2097117768 @default.
- W3151504452 cites W2103206342 @default.
- W3151504452 cites W2157539394 @default.
- W3151504452 cites W2194775991 @default.
- W3151504452 cites W2335211497 @default.
- W3151504452 cites W2471712270 @default.
- W3151504452 cites W2509599246 @default.
- W3151504452 cites W2515846391 @default.
- W3151504452 cites W2522403126 @default.
- W3151504452 cites W2528639018 @default.
- W3151504452 cites W2531409750 @default.
- W3151504452 cites W2531469489 @default.
- W3151504452 cites W2579140012 @default.
- W3151504452 cites W2717838736 @default.
- W3151504452 cites W2760506659 @default.
- W3151504452 cites W2766040222 @default.
- W3151504452 cites W2783778499 @default.
- W3151504452 cites W2788381291 @default.
- W3151504452 cites W2803892188 @default.
- W3151504452 cites W2805541293 @default.
- W3151504452 cites W2809035759 @default.
- W3151504452 cites W2812669263 @default.
- W3151504452 cites W2880156893 @default.
- W3151504452 cites W2898443553 @default.
- W3151504452 cites W2898461917 @default.
- W3151504452 cites W2899742462 @default.
- W3151504452 cites W2900831480 @default.
- W3151504452 cites W2901165057 @default.
- W3151504452 cites W2905241670 @default.
- W3151504452 cites W2912731314 @default.
- W3151504452 cites W2914430336 @default.
- W3151504452 cites W2914487400 @default.
- W3151504452 cites W2931968749 @default.
- W3151504452 cites W2945400882 @default.
- W3151504452 cites W2952135817 @default.
- W3151504452 cites W2962851944 @default.
- W3151504452 cites W2964335392 @default.
- W3151504452 cites W2965521597 @default.
- W3151504452 cites W2965918989 @default.
- W3151504452 cites W2979088718 @default.
- W3151504452 cites W2979262867 @default.
- W3151504452 cites W2990955039 @default.
- W3151504452 cites W3003725186 @default.
- W3151504452 cites W3020673398 @default.
- W3151504452 cites W3033403115 @default.
- W3151504452 cites W3034690373 @default.
- W3151504452 cites W3038462551 @default.
- W3151504452 cites W3080219577 @default.
- W3151504452 cites W3088611441 @default.
- W3151504452 cites W3096800248 @default.
- W3151504452 cites W3098448153 @default.
- W3151504452 cites W3103794298 @default.
- W3151504452 cites W3108376771 @default.
- W3151504452 cites W3112958374 @default.
- W3151504452 cites W3113701344 @default.
- W3151504452 cites W3115103108 @default.
- W3151504452 cites W956374238 @default.
- W3151504452 hasPublicationYear "2021" @default.
- W3151504452 type Work @default.
- W3151504452 sameAs 3151504452 @default.
- W3151504452 citedByCount "0" @default.
- W3151504452 crossrefType "posted-content" @default.
- W3151504452 hasAuthorship W3151504452A5026984704 @default.
- W3151504452 hasAuthorship W3151504452A5048232137 @default.
- W3151504452 hasAuthorship W3151504452A5056877599 @default.
- W3151504452 hasAuthorship W3151504452A5082137392 @default.
- W3151504452 hasConcept C105795698 @default.
- W3151504452 hasConcept C108583219 @default.
- W3151504452 hasConcept C126314574 @default.
- W3151504452 hasConcept C138885662 @default.
- W3151504452 hasConcept C153294291 @default.
- W3151504452 hasConcept C154945302 @default.
- W3151504452 hasConcept C158739034 @default.
- W3151504452 hasConcept C166957645 @default.
- W3151504452 hasConcept C178790620 @default.
- W3151504452 hasConcept C185429906 @default.
- W3151504452 hasConcept C185592680 @default.
- W3151504452 hasConcept C18903297 @default.
- W3151504452 hasConcept C191935318 @default.
- W3151504452 hasConcept C205649164 @default.