Hybrid graph convolutional LSTM model for spatio-temporal air quality transfer learning

IF 2.9 4区 环境科学与生态学 Q3 ENVIRONMENTAL SCIENCES
Sooraj Raj, Jim Smith, Enda Hayes
{"title":"Hybrid graph convolutional LSTM model for spatio-temporal air quality transfer learning","authors":"Sooraj Raj,&nbsp;Jim Smith,&nbsp;Enda Hayes","doi":"10.1007/s11869-025-01713-8","DOIUrl":null,"url":null,"abstract":"<div><p>The short-term air quality forecasting models serve as an early warning system for local agencies, aiding in preparing mitigation strategies against severe pollution episodes. This paper explores the application of Transfer Learning to enhance short-term air quality forecasting model accuracy when labelled data is limited or missing, as often occurs with newly installed monitoring stations or due to sensor malfunctions. These monitoring stations are typically installed in areas of high exposure, like roads or urban/industrial areas, due to recurrent peak episodes or to monitor background pollutant levels generally. Forecasts with greater reliability, even when there is limited historical data available due to the recent installation of the monitoring station for example, are expected to enable the swift implementation of proactive measures to prevent significant pollution episodes from happening. The proposed method leverages knowledge from spatially neighbouring air quality monitoring stations to achieve the multi-modal spatial-temporal transfer learning to the target station, exploring multivariate time series data available from neighbouring monitoring stations. This study employed historical air quality data from spatially adjacent monitoring stations identified in South Wales, UK. The study evaluates the predictive capabilities of four base models and their corresponding transfer learning variants for estimating NO<sub>2</sub> and PM<sub>10</sub> pollutant levels, which are the most difficult pollutants to meet objectives and limit values in the UK’s air quality strategy. The paper highlights the importance of capturing spatial patterns from different monitoring stations along with temporal trends when it comes to air quality prediction. Our experiments demonstrate that transfer learning models outperform models trained from scratch on air quality multivariate time series prediction problems in a low data environment. The proposed hybrid Graph Convolutional-LSTM model, making use of a novel Granger causality-based adjacency matrix for the new site, has significantly outperformed other baseline models in predicting pollutants, achieving notable improvements in prediction accuracy of approximately 8% for PM<sub>10</sub> and 7% for NO<sub>2</sub> values, as reflected in the RMSE values. It has also demonstrated the potential for data-efficient approaches in spatial transfer learning by reducing the need for large datasets by incorporating prior causal information.</p></div>","PeriodicalId":49109,"journal":{"name":"Air Quality Atmosphere and Health","volume":"18 5","pages":"1425 - 1445"},"PeriodicalIF":2.9000,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s11869-025-01713-8.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Air Quality Atmosphere and Health","FirstCategoryId":"93","ListUrlMain":"https://link.springer.com/article/10.1007/s11869-025-01713-8","RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

The short-term air quality forecasting models serve as an early warning system for local agencies, aiding in preparing mitigation strategies against severe pollution episodes. This paper explores the application of Transfer Learning to enhance short-term air quality forecasting model accuracy when labelled data is limited or missing, as often occurs with newly installed monitoring stations or due to sensor malfunctions. These monitoring stations are typically installed in areas of high exposure, like roads or urban/industrial areas, due to recurrent peak episodes or to monitor background pollutant levels generally. Forecasts with greater reliability, even when there is limited historical data available due to the recent installation of the monitoring station for example, are expected to enable the swift implementation of proactive measures to prevent significant pollution episodes from happening. The proposed method leverages knowledge from spatially neighbouring air quality monitoring stations to achieve the multi-modal spatial-temporal transfer learning to the target station, exploring multivariate time series data available from neighbouring monitoring stations. This study employed historical air quality data from spatially adjacent monitoring stations identified in South Wales, UK. The study evaluates the predictive capabilities of four base models and their corresponding transfer learning variants for estimating NO2 and PM10 pollutant levels, which are the most difficult pollutants to meet objectives and limit values in the UK’s air quality strategy. The paper highlights the importance of capturing spatial patterns from different monitoring stations along with temporal trends when it comes to air quality prediction. Our experiments demonstrate that transfer learning models outperform models trained from scratch on air quality multivariate time series prediction problems in a low data environment. The proposed hybrid Graph Convolutional-LSTM model, making use of a novel Granger causality-based adjacency matrix for the new site, has significantly outperformed other baseline models in predicting pollutants, achieving notable improvements in prediction accuracy of approximately 8% for PM10 and 7% for NO2 values, as reflected in the RMSE values. It has also demonstrated the potential for data-efficient approaches in spatial transfer learning by reducing the need for large datasets by incorporating prior causal information.

空气质量时空迁移学习的混合图卷积LSTM模型
短期空气质量预报模型是地方机构的早期预警系统,有助于制定针对严重污染事件的缓解战略。本文探讨了迁移学习在标记数据有限或缺失时的应用,以提高短期空气质量预测模型的准确性,这通常发生在新安装的监测站或由于传感器故障。这些监测站通常安装在高暴露地区,如道路或城市/工业区,因为经常出现峰值,或一般监测背景污染物水平。例如,即使由于最近安装了监测站,可用的历史数据有限,预报的可靠性也有望提高,从而能够迅速实施主动措施,防止重大污染事件的发生。该方法利用空间相邻的空气质量监测站的知识,实现向目标站的多模态时空迁移学习,探索相邻监测站的多变量时间序列数据。本研究采用了英国南威尔士空间相邻监测站的历史空气质量数据。该研究评估了四种基本模型及其相应的迁移学习变量的预测能力,以估计NO2和PM10污染物水平,这是最难达到英国空气质量战略目标和限值的污染物。本文强调了在空气质量预测中,从不同监测站获取空间格局和时间趋势的重要性。我们的实验表明,在低数据环境下,迁移学习模型在空气质量多变量时间序列预测问题上优于从零开始训练的模型。所提出的混合图卷积- lstm模型,利用新的基于格兰杰因果关系的邻接矩阵,在预测污染物方面明显优于其他基线模型,PM10和NO2的预测精度分别显著提高了8%和7%,如RMSE值所示。它还展示了空间迁移学习中数据高效方法的潜力,通过整合先验因果信息来减少对大型数据集的需求。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Air Quality Atmosphere and Health
Air Quality Atmosphere and Health ENVIRONMENTAL SCIENCES-
CiteScore
8.80
自引率
2.00%
发文量
146
审稿时长
>12 weeks
期刊介绍: Air Quality, Atmosphere, and Health is a multidisciplinary journal which, by its very name, illustrates the broad range of work it publishes and which focuses on atmospheric consequences of human activities and their implications for human and ecological health. It offers research papers, critical literature reviews and commentaries, as well as special issues devoted to topical subjects or themes. International in scope, the journal presents papers that inform and stimulate a global readership, as the topic addressed are global in their import. Consequently, we do not encourage submission of papers involving local data that relate to local problems. Unless they demonstrate wide applicability, these are better submitted to national or regional journals. Air Quality, Atmosphere & Health addresses such topics as acid precipitation; airborne particulate matter; air quality monitoring and management; exposure assessment; risk assessment; indoor air quality; atmospheric chemistry; atmospheric modeling and prediction; air pollution climatology; climate change and air quality; air pollution measurement; atmospheric impact assessment; forest-fire emissions; atmospheric science; greenhouse gases; health and ecological effects; clean air technology; regional and global change and satellite measurements. This journal benefits a diverse audience of researchers, public health officials and policy makers addressing problems that call for solutions based in evidence from atmospheric and exposure assessment scientists, epidemiologists, and risk assessors. Publication in the journal affords the opportunity to reach beyond defined disciplinary niches to this broader readership.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信