Spatiotemporal MultiWaveNet for Efficiently Generating Environmental Spatiotemporal Series

Real-time and accurate modeling of environmental variables in a specific region is of great significance to human production activities. In the era of intelligence, there is an increasing demand for accuracy and real-time performance of modeling environmental variables. However, due to the lack of a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-17
Hauptverfasser: Gao, Sheng, Meng, Gong, Lin, Lianlei, Zhang, Zongwei, Wang, Junkai, Zhao, Hanqing
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 17
container_issue
container_start_page 1
container_title IEEE transactions on geoscience and remote sensing
container_volume 62
creator Gao, Sheng
Meng, Gong
Lin, Lianlei
Zhang, Zongwei
Wang, Junkai
Zhao, Hanqing
description Real-time and accurate modeling of environmental variables in a specific region is of great significance to human production activities. In the era of intelligence, there is an increasing demand for accuracy and real-time performance of modeling environmental variables. However, due to the lack of a priori knowledge of spatiotemporal features and the high computational complexity, the existing deep learning methods have poor accuracy, and the real-time performance needs to be improved. To solve the above problems, this article proposes a novel SpatioTemporal MultiWaveNet (STMWNet) based on 3-D convolution for end-to-end environmental spatiotemporal variables generation. The Spatiotemporal MultiWave Layer (STMW Layer) is designed based on the principle of wavelet transform to extract multifrequency spatiotemporal features from the series. The multiscale embedding module (MSEM), time infofusion module (TIFM), and embedding integration module (EIM) are proposed to further extract and integrate the spatiotemporal features to improve the accuracy of the model. Considering the short-term and long-term temporal characteristics of spatiotemporal series, the date encoding strategy and the cross-attention head are proposed to integrate relative and absolute date information. The improved loss function is proposed to optimize the model learning. Comparative experiments on three datasets with different physical fields, different spatial scales, and resolutions show that the proposed method can accurately generate the mesoscale environmental spatiotemporal variables in real time for different tasks with the generation error lower than other methods by 1.02%~83.52% on root mean square error (RMSE), and 1.67%~83.68% on mean absolute error (MAE). Further experiments show that the proposed method can maintain its performance in practical applications.
doi_str_mv 10.1109/TGRS.2024.3424241
format Article
fullrecord <record><control><sourceid>crossref_RIE</sourceid><recordid>TN_cdi_ieee_primary_10587193</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10587193</ieee_id><sourcerecordid>10_1109_TGRS_2024_3424241</sourcerecordid><originalsourceid>FETCH-LOGICAL-c148t-5861713ce5c18d598fba9ebdfc8b2ce1ff5a9c795a541b924847b63cb2caccc33</originalsourceid><addsrcrecordid>eNpdkM1Kw0AUhQdRsFYfQHCRF0idOz_JzFJKTIWqYCuCmzCZ3pGRNAkzsdC3N6VdiNzFXZzzncVHyC3QGQDV9-vybTVjlIkZF2w8OCMTkFKlNBPinEwo6CxlSrNLchXjN6UgJOQT8rnqzeC7Abd9F0yTPP80g_8wO3zBIXFdSArnvPXYDs0-KbHFMNbbr6Rodz507XYMRurfyAqDx3hNLpxpIt6c_pS8Pxbr-SJdvpZP84dlakGoIZUqgxy4RWlBbaRWrjYa642zqmYWwTlptM21NFJArZlQIq8zbsfQWGs5nxI47trQxRjQVX3wWxP2FdDqIKc6yKkOcqqTnJG5OzIeEf_0pcpBc_4LlW1j_g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Spatiotemporal MultiWaveNet for Efficiently Generating Environmental Spatiotemporal Series</title><source>IEEE Electronic Library (IEL)</source><creator>Gao, Sheng ; Meng, Gong ; Lin, Lianlei ; Zhang, Zongwei ; Wang, Junkai ; Zhao, Hanqing</creator><creatorcontrib>Gao, Sheng ; Meng, Gong ; Lin, Lianlei ; Zhang, Zongwei ; Wang, Junkai ; Zhao, Hanqing</creatorcontrib><description>Real-time and accurate modeling of environmental variables in a specific region is of great significance to human production activities. In the era of intelligence, there is an increasing demand for accuracy and real-time performance of modeling environmental variables. However, due to the lack of a priori knowledge of spatiotemporal features and the high computational complexity, the existing deep learning methods have poor accuracy, and the real-time performance needs to be improved. To solve the above problems, this article proposes a novel SpatioTemporal MultiWaveNet (STMWNet) based on 3-D convolution for end-to-end environmental spatiotemporal variables generation. The Spatiotemporal MultiWave Layer (STMW Layer) is designed based on the principle of wavelet transform to extract multifrequency spatiotemporal features from the series. The multiscale embedding module (MSEM), time infofusion module (TIFM), and embedding integration module (EIM) are proposed to further extract and integrate the spatiotemporal features to improve the accuracy of the model. Considering the short-term and long-term temporal characteristics of spatiotemporal series, the date encoding strategy and the cross-attention head are proposed to integrate relative and absolute date information. The improved loss function is proposed to optimize the model learning. Comparative experiments on three datasets with different physical fields, different spatial scales, and resolutions show that the proposed method can accurately generate the mesoscale environmental spatiotemporal variables in real time for different tasks with the generation error lower than other methods by 1.02%~83.52% on root mean square error (RMSE), and 1.67%~83.68% on mean absolute error (MAE). Further experiments show that the proposed method can maintain its performance in practical applications.</description><identifier>ISSN: 0196-2892</identifier><identifier>EISSN: 1558-0644</identifier><identifier>DOI: 10.1109/TGRS.2024.3424241</identifier><identifier>CODEN: IGRSD2</identifier><language>eng</language><publisher>IEEE</publisher><subject>3-D convolutional neural network (CNN) ; Data models ; deep learning regression ; environmental variables ; Feature extraction ; Mathematical models ; Predictive models ; Spatiotemporal phenomena ; spatiotemporal series generation ; Task analysis ; wavelet transform ; Wavelet transforms</subject><ispartof>IEEE transactions on geoscience and remote sensing, 2024, Vol.62, p.1-17</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c148t-5861713ce5c18d598fba9ebdfc8b2ce1ff5a9c795a541b924847b63cb2caccc33</cites><orcidid>0009-0006-2921-0097 ; 0000-0002-5827-8692 ; 0000-0002-3726-3416 ; 0000-0001-6916-989X ; 0000-0001-6829-5747</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10587193$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,4024,27923,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10587193$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Gao, Sheng</creatorcontrib><creatorcontrib>Meng, Gong</creatorcontrib><creatorcontrib>Lin, Lianlei</creatorcontrib><creatorcontrib>Zhang, Zongwei</creatorcontrib><creatorcontrib>Wang, Junkai</creatorcontrib><creatorcontrib>Zhao, Hanqing</creatorcontrib><title>Spatiotemporal MultiWaveNet for Efficiently Generating Environmental Spatiotemporal Series</title><title>IEEE transactions on geoscience and remote sensing</title><addtitle>TGRS</addtitle><description>Real-time and accurate modeling of environmental variables in a specific region is of great significance to human production activities. In the era of intelligence, there is an increasing demand for accuracy and real-time performance of modeling environmental variables. However, due to the lack of a priori knowledge of spatiotemporal features and the high computational complexity, the existing deep learning methods have poor accuracy, and the real-time performance needs to be improved. To solve the above problems, this article proposes a novel SpatioTemporal MultiWaveNet (STMWNet) based on 3-D convolution for end-to-end environmental spatiotemporal variables generation. The Spatiotemporal MultiWave Layer (STMW Layer) is designed based on the principle of wavelet transform to extract multifrequency spatiotemporal features from the series. The multiscale embedding module (MSEM), time infofusion module (TIFM), and embedding integration module (EIM) are proposed to further extract and integrate the spatiotemporal features to improve the accuracy of the model. Considering the short-term and long-term temporal characteristics of spatiotemporal series, the date encoding strategy and the cross-attention head are proposed to integrate relative and absolute date information. The improved loss function is proposed to optimize the model learning. Comparative experiments on three datasets with different physical fields, different spatial scales, and resolutions show that the proposed method can accurately generate the mesoscale environmental spatiotemporal variables in real time for different tasks with the generation error lower than other methods by 1.02%~83.52% on root mean square error (RMSE), and 1.67%~83.68% on mean absolute error (MAE). Further experiments show that the proposed method can maintain its performance in practical applications.</description><subject>3-D convolutional neural network (CNN)</subject><subject>Data models</subject><subject>deep learning regression</subject><subject>environmental variables</subject><subject>Feature extraction</subject><subject>Mathematical models</subject><subject>Predictive models</subject><subject>Spatiotemporal phenomena</subject><subject>spatiotemporal series generation</subject><subject>Task analysis</subject><subject>wavelet transform</subject><subject>Wavelet transforms</subject><issn>0196-2892</issn><issn>1558-0644</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkM1Kw0AUhQdRsFYfQHCRF0idOz_JzFJKTIWqYCuCmzCZ3pGRNAkzsdC3N6VdiNzFXZzzncVHyC3QGQDV9-vybTVjlIkZF2w8OCMTkFKlNBPinEwo6CxlSrNLchXjN6UgJOQT8rnqzeC7Abd9F0yTPP80g_8wO3zBIXFdSArnvPXYDs0-KbHFMNbbr6Rodz507XYMRurfyAqDx3hNLpxpIt6c_pS8Pxbr-SJdvpZP84dlakGoIZUqgxy4RWlBbaRWrjYa642zqmYWwTlptM21NFJArZlQIq8zbsfQWGs5nxI47trQxRjQVX3wWxP2FdDqIKc6yKkOcqqTnJG5OzIeEf_0pcpBc_4LlW1j_g</recordid><startdate>2024</startdate><enddate>2024</enddate><creator>Gao, Sheng</creator><creator>Meng, Gong</creator><creator>Lin, Lianlei</creator><creator>Zhang, Zongwei</creator><creator>Wang, Junkai</creator><creator>Zhao, Hanqing</creator><general>IEEE</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0009-0006-2921-0097</orcidid><orcidid>https://orcid.org/0000-0002-5827-8692</orcidid><orcidid>https://orcid.org/0000-0002-3726-3416</orcidid><orcidid>https://orcid.org/0000-0001-6916-989X</orcidid><orcidid>https://orcid.org/0000-0001-6829-5747</orcidid></search><sort><creationdate>2024</creationdate><title>Spatiotemporal MultiWaveNet for Efficiently Generating Environmental Spatiotemporal Series</title><author>Gao, Sheng ; Meng, Gong ; Lin, Lianlei ; Zhang, Zongwei ; Wang, Junkai ; Zhao, Hanqing</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c148t-5861713ce5c18d598fba9ebdfc8b2ce1ff5a9c795a541b924847b63cb2caccc33</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>3-D convolutional neural network (CNN)</topic><topic>Data models</topic><topic>deep learning regression</topic><topic>environmental variables</topic><topic>Feature extraction</topic><topic>Mathematical models</topic><topic>Predictive models</topic><topic>Spatiotemporal phenomena</topic><topic>spatiotemporal series generation</topic><topic>Task analysis</topic><topic>wavelet transform</topic><topic>Wavelet transforms</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Gao, Sheng</creatorcontrib><creatorcontrib>Meng, Gong</creatorcontrib><creatorcontrib>Lin, Lianlei</creatorcontrib><creatorcontrib>Zhang, Zongwei</creatorcontrib><creatorcontrib>Wang, Junkai</creatorcontrib><creatorcontrib>Zhao, Hanqing</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><jtitle>IEEE transactions on geoscience and remote sensing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Gao, Sheng</au><au>Meng, Gong</au><au>Lin, Lianlei</au><au>Zhang, Zongwei</au><au>Wang, Junkai</au><au>Zhao, Hanqing</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Spatiotemporal MultiWaveNet for Efficiently Generating Environmental Spatiotemporal Series</atitle><jtitle>IEEE transactions on geoscience and remote sensing</jtitle><stitle>TGRS</stitle><date>2024</date><risdate>2024</risdate><volume>62</volume><spage>1</spage><epage>17</epage><pages>1-17</pages><issn>0196-2892</issn><eissn>1558-0644</eissn><coden>IGRSD2</coden><abstract>Real-time and accurate modeling of environmental variables in a specific region is of great significance to human production activities. In the era of intelligence, there is an increasing demand for accuracy and real-time performance of modeling environmental variables. However, due to the lack of a priori knowledge of spatiotemporal features and the high computational complexity, the existing deep learning methods have poor accuracy, and the real-time performance needs to be improved. To solve the above problems, this article proposes a novel SpatioTemporal MultiWaveNet (STMWNet) based on 3-D convolution for end-to-end environmental spatiotemporal variables generation. The Spatiotemporal MultiWave Layer (STMW Layer) is designed based on the principle of wavelet transform to extract multifrequency spatiotemporal features from the series. The multiscale embedding module (MSEM), time infofusion module (TIFM), and embedding integration module (EIM) are proposed to further extract and integrate the spatiotemporal features to improve the accuracy of the model. Considering the short-term and long-term temporal characteristics of spatiotemporal series, the date encoding strategy and the cross-attention head are proposed to integrate relative and absolute date information. The improved loss function is proposed to optimize the model learning. Comparative experiments on three datasets with different physical fields, different spatial scales, and resolutions show that the proposed method can accurately generate the mesoscale environmental spatiotemporal variables in real time for different tasks with the generation error lower than other methods by 1.02%~83.52% on root mean square error (RMSE), and 1.67%~83.68% on mean absolute error (MAE). Further experiments show that the proposed method can maintain its performance in practical applications.</abstract><pub>IEEE</pub><doi>10.1109/TGRS.2024.3424241</doi><tpages>17</tpages><orcidid>https://orcid.org/0009-0006-2921-0097</orcidid><orcidid>https://orcid.org/0000-0002-5827-8692</orcidid><orcidid>https://orcid.org/0000-0002-3726-3416</orcidid><orcidid>https://orcid.org/0000-0001-6916-989X</orcidid><orcidid>https://orcid.org/0000-0001-6829-5747</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 0196-2892
ispartof IEEE transactions on geoscience and remote sensing, 2024, Vol.62, p.1-17
issn 0196-2892
1558-0644
language eng
recordid cdi_ieee_primary_10587193
source IEEE Electronic Library (IEL)
subjects 3-D convolutional neural network (CNN)
Data models
deep learning regression
environmental variables
Feature extraction
Mathematical models
Predictive models
Spatiotemporal phenomena
spatiotemporal series generation
Task analysis
wavelet transform
Wavelet transforms
title Spatiotemporal MultiWaveNet for Efficiently Generating Environmental Spatiotemporal Series
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T13%3A20%3A18IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Spatiotemporal%20MultiWaveNet%20for%20Efficiently%20Generating%20Environmental%20Spatiotemporal%20Series&rft.jtitle=IEEE%20transactions%20on%20geoscience%20and%20remote%20sensing&rft.au=Gao,%20Sheng&rft.date=2024&rft.volume=62&rft.spage=1&rft.epage=17&rft.pages=1-17&rft.issn=0196-2892&rft.eissn=1558-0644&rft.coden=IGRSD2&rft_id=info:doi/10.1109/TGRS.2024.3424241&rft_dat=%3Ccrossref_RIE%3E10_1109_TGRS_2024_3424241%3C/crossref_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10587193&rfr_iscdi=true