A spatial correlation prediction model of urban PM2.5 concentration based on deconvolution and LSTM
Precise prediction of air pollutants can effectively reducre the occurrence of heavy pollution incidents. With the current surge of massive data, deep learning appears to be a promising technique to achieve dynamic prediction of air pollutant concentration from both the spatial and temporal dimensio...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier B.V.
2023
|
Subjects: | |
Online Access: | View Fulltext in Publisher View in Scopus |
LEADER | 02326nam a2200445Ia 4500 | ||
---|---|---|---|
001 | 10.1016-j.neucom.2023.126280 | ||
008 | 230529s2023 CNT 000 0 und d | ||
020 | |a 09252312 (ISSN) | ||
245 | 1 | 0 | |a A spatial correlation prediction model of urban PM2.5 concentration based on deconvolution and LSTM |
260 | 0 | |b Elsevier B.V. |c 2023 | |
856 | |z View Fulltext in Publisher |u https://doi.org/10.1016/j.neucom.2023.126280 | ||
856 | |z View in Scopus |u https://www.scopus.com/inward/record.uri?eid=2-s2.0-85158833814&doi=10.1016%2fj.neucom.2023.126280&partnerID=40&md5=847ddd325a13db3ba0d119478ae734b7 | ||
520 | 3 | |a Precise prediction of air pollutants can effectively reducre the occurrence of heavy pollution incidents. With the current surge of massive data, deep learning appears to be a promising technique to achieve dynamic prediction of air pollutant concentration from both the spatial and temporal dimensions. This paper presents Dev-LSTM, a prediction model building on deconvolution and LSTM. The novelty of Dev-LSTM lies in its capability to fully extract the spatial feature correlation of air pollutant concentration data, preventing the excessive loss of information caused by traditional convolution. At the same time, the feature associations in the time dimension are mined to produce accurate prediction results. Experimental results show that Dev-LSTM outperforms traditional prediction models on a variety of indicators. © 2023 The Authors | |
650 | 0 | 4 | |a air pollutant |
650 | 0 | 4 | |a Air pollutant concentration prediction |
650 | 0 | 4 | |a Air pollutant concentrations |
650 | 0 | 4 | |a Air pollutants |
650 | 0 | 4 | |a Air pollution |
650 | 0 | 4 | |a article |
650 | 0 | 4 | |a Concentration prediction |
650 | 0 | 4 | |a deconvolution |
650 | 0 | 4 | |a Deconvolution |
650 | 0 | 4 | |a Deconvolutions |
650 | 0 | 4 | |a Deep learnin |
650 | 0 | 4 | |a Dev-LSTM |
650 | 0 | 4 | |a Forecasting |
650 | 0 | 4 | |a Long short-term memory |
650 | 0 | 4 | |a particulate matter 2.5 |
650 | 0 | 4 | |a PM 2.5 |
650 | 0 | 4 | |a prediction |
650 | 0 | 4 | |a Prediction modelling |
650 | 0 | 4 | |a Spatial correlations |
700 | 1 | 0 | |a Li, M. |e author |
700 | 1 | 0 | |a Liu, Y. |e author |
700 | 1 | 0 | |a Pan, J. |e author |
700 | 1 | 0 | |a Yang, R. |e author |
700 | 1 | 0 | |a Yong, R. |e author |
700 | 1 | 0 | |a Zhang, B. |e author |
700 | 1 | 0 | |a Zou, G. |e author |
773 | |t Neurocomputing |