LLMAir: Adaptive Reprogramming Large Language Model for Air Quality Prediction

Accurate and timely air quality prediction is crucial for cities and individuals to effectively take necessary precautions against potential air pollution. Existing studies typically rely on building prediction models based on large-scale monitoring data, often designed for specific tasks. Recently,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings - International Conference on Parallel and Distributed Systems S. 423 - 430
Hauptverfasser: Fan, Jinxiao, Chu, Haolin, Liu, Liang, Ma, Huadong
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 10.10.2024
Schlagworte:
ISSN:2690-5965
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Accurate and timely air quality prediction is crucial for cities and individuals to effectively take necessary precautions against potential air pollution. Existing studies typically rely on building prediction models based on large-scale monitoring data, often designed for specific tasks. Recently, pre-trained large language models (LLMs) have achieved significant progress in various time series analysis tasks due to their powerful representation and inference capabilities. However, their application to air quality data with spatio-temporal features remains largely unexplored. In this work, we propose LLMAir, an adaptive reprogramming approach that adapts pre-trained LLMs for air quality prediction. We first construct spatiotemporal tokens based on monitoring stations by integrating value, node, and time embeddings. Next, we design an adaptive semantic-enhanced reprogramming module to compute similarity matching scores between our spatiotemporal tokens and pre-trained word embeddings for alignment. We employ a semantic regulator to generate the optimal length of word prototypes, which serve as prompt prefixes for adaptive reprogramming and guiding the spatiotemporal token embeddings into the frozen LLM. Additionally, we jointly optimize predictive error and alignment loss to train our model. Experimental results demonstrate that LLMAir achieves state-of-the-art performance in air quality prediction and few-shot forecasting across two real-world datasets.
AbstractList Accurate and timely air quality prediction is crucial for cities and individuals to effectively take necessary precautions against potential air pollution. Existing studies typically rely on building prediction models based on large-scale monitoring data, often designed for specific tasks. Recently, pre-trained large language models (LLMs) have achieved significant progress in various time series analysis tasks due to their powerful representation and inference capabilities. However, their application to air quality data with spatio-temporal features remains largely unexplored. In this work, we propose LLMAir, an adaptive reprogramming approach that adapts pre-trained LLMs for air quality prediction. We first construct spatiotemporal tokens based on monitoring stations by integrating value, node, and time embeddings. Next, we design an adaptive semantic-enhanced reprogramming module to compute similarity matching scores between our spatiotemporal tokens and pre-trained word embeddings for alignment. We employ a semantic regulator to generate the optimal length of word prototypes, which serve as prompt prefixes for adaptive reprogramming and guiding the spatiotemporal token embeddings into the frozen LLM. Additionally, we jointly optimize predictive error and alignment loss to train our model. Experimental results demonstrate that LLMAir achieves state-of-the-art performance in air quality prediction and few-shot forecasting across two real-world datasets.
Author Ma, Huadong
Fan, Jinxiao
Chu, Haolin
Liu, Liang
Author_xml – sequence: 1
  givenname: Jinxiao
  surname: Fan
  fullname: Fan, Jinxiao
  email: jinxiaofan@bupt.edu.cn
  organization: Beijing University of Posts and Telecommunications,Beijing,China,100876
– sequence: 2
  givenname: Haolin
  surname: Chu
  fullname: Chu, Haolin
  email: haolinchu@bupt.edu.cn
  organization: Beijing University of Posts and Telecommunications,Beijing,China,100876
– sequence: 3
  givenname: Liang
  surname: Liu
  fullname: Liu, Liang
  email: liangliu@bupt.edu.cn
  organization: Beijing University of Posts and Telecommunications,Beijing,China,100876
– sequence: 4
  givenname: Huadong
  surname: Ma
  fullname: Ma, Huadong
  email: mhd@bupt.edu.cn
  organization: Beijing University of Posts and Telecommunications,Beijing,China,100876
BookMark eNotj8tOwzAURA0Cibb0DxDyD6Rcx7Eds4tKgUoplNe6uk5uIqM8KjdF6t8TCTYzZ3NGmim76PqOGLsVsBAC7N16uc0ePrSUChYxxMkCAHR8xubW2FRKoYSyWp-zSawtRCOrKzY9HL4BYhidCXvJ803mwz3PStwP_of4O-1DXwdsW9_VPMdQ05hdfcQRNn1JDa_6wEeJvx2x8cOJbwOVvhh8312zywqbA83_e8a-Hlefy-cof31aL7M88sLoIYqxFK4i0BJROpsYoW0qHCGlRQWlcsIkgkRSKKfGC65Ak2pMlZNUpVg6OWM3f7ueiHb74FsMp50Ao6VJQP4C1hdRsA
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICPADS63350.2024.00062
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9798331515966
EISSN 2690-5965
EndPage 430
ExternalDocumentID 10763740
Genre orig-research
GroupedDBID 29O
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i176t-2ad1bfe063aa3b94716981beae8cf0d5b1741e14c5b5515bca786a85b3ef8adb3
IEDL.DBID RIE
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001481011800052&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 01:59:32 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i176t-2ad1bfe063aa3b94716981beae8cf0d5b1741e14c5b5515bca786a85b3ef8adb3
PageCount 8
ParticipantIDs ieee_primary_10763740
PublicationCentury 2000
PublicationDate 2024-Oct.-10
PublicationDateYYYYMMDD 2024-10-10
PublicationDate_xml – month: 10
  year: 2024
  text: 2024-Oct.-10
  day: 10
PublicationDecade 2020
PublicationTitle Proceedings - International Conference on Parallel and Distributed Systems
PublicationTitleAbbrev ICPADS
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0020350
Score 2.2782125
Snippet Accurate and timely air quality prediction is crucial for cities and individuals to effectively take necessary precautions against potential air pollution....
SourceID ieee
SourceType Publisher
StartPage 423
SubjectTerms Air quality
Air quality prediction
Analytical models
Atmospheric modeling
Data models
Large language models
Monitoring
Predictive models
Regulators
Semantics
Spatiotemporal phenomena
Urban data analysis
Title LLMAir: Adaptive Reprogramming Large Language Model for Air Quality Prediction
URI https://ieeexplore.ieee.org/document/10763740
WOSCitedRecordID wos001481011800052&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aPHiqj4pvcvC6utt9JPFWqkVhXRZ80FvJYxYK2pY-BP-9M9lt9eLBy7IEQiDDzHyTeXyMXaFPVRrtXAAWxUDjTwIDAgJJg0achkx5HrK3XBSFHA5V2TSr-14YAPDFZ3BNvz6X76Z2RU9lqOGoDSLBCH1bCFE3a22iK0qRNS3AUahuHvtl7-45i3EVo8AuzcgOiRLnF4eKdyGD9j8P32Odn2Y8Xm7czD7bgskBa6_ZGHijnIesyPOn3nh-y3tOz8iIcQTXdfXVB27kOdV847d-n-REgvbOEbJy3MTrURpfeBAlbkhYHfY6uH_pPwQNW0IwjkS2DLraRaYChBxax0YlNAYHMSlokLYKXWow9oggSmxqECWlxmohMy1TE0MltTPxEWtNphM4ZtwqIyhllkhlErR_Wrm4gswnDRGSqBPWofsZzeqBGKP11Zz-sX7GdkkEZPKj8Jy1lvMVXLAd-7kcL-aXXozfXAud2A
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB6kCnqqj4pv9-A1mjSvXW-lWlpMQ8EqvZXd7AQK2pbaCv57Z5K0evHgJYSFZWGHmflm5_EB3JBPVZrsnIMZiYHHnzgGY3QkDxqxGiNV8JC9JnGaytFIDapm9aIXBhGL4jO85d8il29n2YqfykjDSRvigCL07TAIml7ZrrWJrzhJVjUBe66667UHrYfnyKdVigObPCXbZVKcXywqhRPp1P95_D40ftrxxGDjaA5gC6eHUF_zMYhKPY8gTZJ-a7K4Fy2r52zGBMHrsv7qnTaKhKu-6Vu-UAqmQXsTBFoFbRLlMI0vOohTNyyuBrx0HoftrlPxJTgTL46WTlNbz-RIoENr36iAB-EQKkWNMstdGxqKPjz0giw0hJNCk-lYRlqGxsdcamv8Y6hNZ1M8AZEpE3PSLJDKBGQBtbJ-jlGRNiRQok6hwfcznpcjMcbrqzn7Y_0adrvDfjJOeunTOeyxONgBeO4F1JaLFV7CTva5nHwsrgqRfgPB6qEf
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+-+International+Conference+on+Parallel+and+Distributed+Systems&rft.atitle=LLMAir%3A+Adaptive+Reprogramming+Large+Language+Model+for+Air+Quality+Prediction&rft.au=Fan%2C+Jinxiao&rft.au=Chu%2C+Haolin&rft.au=Liu%2C+Liang&rft.au=Ma%2C+Huadong&rft.date=2024-10-10&rft.pub=IEEE&rft.eissn=2690-5965&rft.spage=423&rft.epage=430&rft_id=info:doi/10.1109%2FICPADS63350.2024.00062&rft.externalDocID=10763740