{"title":"Modeling PM2.5 urbane pollution using hybrid models incorporating decomposition and multiple factors","authors":"Somayeh Mirzaei , Ting Lun Liao , Chin-Yu Hsu","doi":"10.1016/j.uclim.2025.102338","DOIUrl":null,"url":null,"abstract":"<div><div>PM<sub>2.5</sub> negatively impacts air quality, human health, and the environment. Modeling PM<sub>2.5</sub> concentrations is helpful for understanding pollution dynamics and supporting government emergency responses and preventive measures. This study introduces a novel method to develop hybrid models that enhance PM<sub>2.5</sub> concentration modeling and evaluate source contributions. We applied empirical mode decomposition (EMD)-based models—EMD-LSTM, EMD-Bi-LSTM, EMD-GRU, EMD-CNN, and EMD-CNN-LSTM— to model hourly PM<sub>2.5</sub> concentrations using a 4-year dataset. PM<sub>2.5</sub> concentration data from the target and nine neighboring stations, combined with EMD and time lag functions, as well as other air pollutants and meteorological inputs, were used to develop models. We adopted a Shapley additive explanations analyzer-based LSTM model to identify pivotal features. Among all models, EMD-Bi-LSTM emerged as the top performer, achieving up to 89.5 % model accuracy (<em>R</em><sup>2</sup>). PM<sub>2.5</sub> concentration at the target station from the previous 1 h was identified as a key contributor in the model. Other influencing factors included PM<sub>2.5</sub> concentrations at neighboring stations, PM<sub>10</sub>, CO, O<sub>3</sub>, total hydrocarbon compounds, and wind direction.</div></div>","PeriodicalId":48626,"journal":{"name":"Urban Climate","volume":"60 ","pages":"Article 102338"},"PeriodicalIF":6.0000,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Urban Climate","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2212095525000549","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
PM2.5 negatively impacts air quality, human health, and the environment. Modeling PM2.5 concentrations is helpful for understanding pollution dynamics and supporting government emergency responses and preventive measures. This study introduces a novel method to develop hybrid models that enhance PM2.5 concentration modeling and evaluate source contributions. We applied empirical mode decomposition (EMD)-based models—EMD-LSTM, EMD-Bi-LSTM, EMD-GRU, EMD-CNN, and EMD-CNN-LSTM— to model hourly PM2.5 concentrations using a 4-year dataset. PM2.5 concentration data from the target and nine neighboring stations, combined with EMD and time lag functions, as well as other air pollutants and meteorological inputs, were used to develop models. We adopted a Shapley additive explanations analyzer-based LSTM model to identify pivotal features. Among all models, EMD-Bi-LSTM emerged as the top performer, achieving up to 89.5 % model accuracy (R2). PM2.5 concentration at the target station from the previous 1 h was identified as a key contributor in the model. Other influencing factors included PM2.5 concentrations at neighboring stations, PM10, CO, O3, total hydrocarbon compounds, and wind direction.
期刊介绍:
Urban Climate serves the scientific and decision making communities with the publication of research on theory, science and applications relevant to understanding urban climatic conditions and change in relation to their geography and to demographic, socioeconomic, institutional, technological and environmental dynamics and global change. Targeted towards both disciplinary and interdisciplinary audiences, this journal publishes original research papers, comprehensive review articles, book reviews, and short communications on topics including, but not limited to, the following:
Urban meteorology and climate[...]
Urban environmental pollution[...]
Adaptation to global change[...]
Urban economic and social issues[...]
Research Approaches[...]