{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T04:47:04Z","timestamp":1776401224419,"version":"3.51.2"},"reference-count":61,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T00:00:00Z","timestamp":1672963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42271332"],"award-info":[{"award-number":["42271332"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41971280"],"award-info":[{"award-number":["41971280"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Atmospheric fine particles (PM2.5) have been found to be harmful to the environment and human health. Recently, remote sensing technology and machine learning models have been used to monitor PM2.5 concentrations. Partial dependence plots (PDP) were used to explore the meteorology mechanisms between predictor variables and PM2.5 concentration in the \u201cblack box\u201d models. However, there are two key shortcomings in the original PDP. (1) it calculates the marginal effect of feature(s) on the predicted outcome of a machine learning model, therefore some local effects might be hidden. (2) it requires that the feature(s) for which the partial dependence is computed are not correlated with other features, otherwise the estimated feature effect has a great bias. In this study, the original PDP\u2019s shortcomings were analyzed. Results show the contradictory correlation between the temperature and the PM2.5 concentration that can be given by the original PDP. Furthermore, the spatiotemporal heterogeneity of PM2.5-AOD relationship cannot be displayed well by the original PDP. The drawbacks of the original PDP make it unsuitable for exploring large-area feature effects. To resolve the above issue, multi-way PDP is recommended, which can characterize how the PM2.5 concentrations changed with the temporal and spatial variations of major meteorological factors in China.<\/jats:p>","DOI":"10.3390\/rs15020358","type":"journal-article","created":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T04:47:08Z","timestamp":1673239628000},"page":"358","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["Clarifying Relationship between PM2.5 Concentrations and Spatiotemporal Predictors Using Multi-Way Partial Dependence Plots"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5744-5711","authenticated-orcid":false,"given":"Haoze","family":"Shi","sequence":"first","affiliation":[{"name":"College of Global Change and Earth System Science, Beijing Normal University, Beijing 100875, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3922-8710","authenticated-orcid":false,"given":"Naisen","family":"Yang","sequence":"additional","affiliation":[{"name":"Environment Research Institute, Shandong University, Qingdao 266237, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5111-2959","authenticated-orcid":false,"given":"Xin","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Global Change and Earth System Science, Beijing Normal University, Beijing 100875, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0115-9067","authenticated-orcid":false,"given":"Hong","family":"Tang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.atmosenv.2013.04.028","article-title":"Estimation of the contribution of road traffic emissions to particulate matter concentrations from field measurements: A review","volume":"77","author":"Pant","year":"2013","journal-title":"Atmos. Environ."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3762","DOI":"10.1021\/acs.est.5b05833","article-title":"Global estimates of fine particulate matter using a combined geophysical-statistical method with information from satellites, models, and monitors","volume":"50","author":"Martin","year":"2016","journal-title":"Environ. Sci. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.jastp.2016.02.022","article-title":"Impact of Land-Use and Land-Cover Change on urban air quality in representative cities of China","volume":"142","author":"Sun","year":"2016","journal-title":"J. Atmos. Sol.-Terr. Phys."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Jandacka, D., and Durcanska, D. (2021). Seasonal Variation, Chemical Composition, and PMF-Derived Sources Identification of Traffic-Related PM1, PM2.5, and PM2.5\u201310 in the Air Quality Management Region of \u017dilina, Slovakia. Int. J. Environ. Res. Public Health, 18.","DOI":"10.3390\/ijerph181910191"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wang, S., Kaur, M., Li, T., and Pan, F. (2021). Effect of Different Pollution Parameters and Chemical Components of PM2.5 on Health of Residents of Xinxiang City, China. Int. J. Environ. Res. Public Health, 18.","DOI":"10.3390\/ijerph18136821"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"107542","DOI":"10.1016\/j.envint.2022.107542","article-title":"Projecting future health burden associated with exposure to ambient PM2.5 and ozone in China under different climate scenarios","volume":"169","author":"Wang","year":"2022","journal-title":"Environ. Int."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"107020","DOI":"10.1016\/j.envint.2021.107020","article-title":"Global health burden of ambient PM2.5 and the contribution of anthropogenic black carbon and organic aerosols","volume":"159","author":"Chowdhury","year":"2022","journal-title":"Environ. Int."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1016\/j.envpol.2017.01.050","article-title":"Air pollution characteristics and their relation to meteorological conditions during 2014\u20132015 in major Chinese cities","volume":"223","author":"He","year":"2017","journal-title":"Environ. Pollut."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"5343","DOI":"10.5194\/acp-18-5343-2018","article-title":"Understanding meteorological influences on PM2.5 concentrations across China: A temporal and spatial perspective","volume":"18","author":"Chen","year":"2018","journal-title":"Atmos. Chem. Phys."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1016\/j.chemosphere.2017.05.133","article-title":"Spatio-temporal variations of PM2. 5 emission in China from 2005 to 2014","volume":"183","author":"Jin","year":"2017","journal-title":"Chemosphere"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"106011","DOI":"10.1016\/j.envint.2020.106011","article-title":"Understanding global PM2. 5 concentrations and their drivers in recent decades (1998\u20132016)","volume":"144","author":"Lim","year":"2020","journal-title":"Environ. Int."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"112827","DOI":"10.1016\/j.rse.2021.112827","article-title":"A review of statistical methods used for developing large-scale and long-term PM2.5 models from satellite data","volume":"269","author":"Ma","year":"2022","journal-title":"Remote Sens. Environ."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"119347","DOI":"10.1016\/j.envpol.2022.119347","article-title":"Ultrahigh-resolution PM2.5 estimation from top-of-atmosphere reflectance with machine learning: Theories, methods, and applications","volume":"306","author":"Yang","year":"2022","journal-title":"Environ. Pollut."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"112828","DOI":"10.1016\/j.rse.2021.112828","article-title":"Geographical and temporal encoding for improving the estimation of PM2.5 concentrations in China using end-to-end gradient boosting","volume":"269","author":"Yang","year":"2022","journal-title":"Remote Sens. Environ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"112136","DOI":"10.1016\/j.rse.2020.112136","article-title":"Reconstructing 1-km-resolution high-quality PM2.5 data records from 2000 to 2018 in China: Spatiotemporal variations and policy implications","volume":"252","author":"Wei","year":"2021","journal-title":"Remote Sens. Environ."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3067","DOI":"10.5194\/essd-12-3067-2020","article-title":"A homogenized daily in situ PM2.5 concentration dataset from the national air quality monitoring network in China","volume":"12","author":"Bai","year":"2020","journal-title":"Earth Syst. Sci. Data"},{"key":"ref_17","first-page":"1","article-title":"Multivariate adaptive regression splines","volume":"19","author":"Friedman","year":"1991","journal-title":"Ann. Stat."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1016\/j.scitotenv.2018.10.344","article-title":"Using meteorological normalisation to detect interventions in air quality time series","volume":"653","author":"Grange","year":"2019","journal-title":"Sci. Total Environ."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Liu, Y., Cao, G., and Zhao, N. (2020). Integrate machine learning and geostatistics for high-resolution mapping of ground-level PM2.5 concentrations. Spatiotemporal Analysis of Air Pollution and Its Application in Public Health, Elsevier.","DOI":"10.1016\/B978-0-12-815822-7.00006-6"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"117757","DOI":"10.1016\/j.atmosenv.2020.117757","article-title":"Prediction of PM2.5 concentrations at the locations of monitoring sites measuring PM10 and NOx, using generalized additive models and machine learning methods: A case study in London","volume":"240","author":"Analitis","year":"2020","journal-title":"Atmos. Environ."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"105716","DOI":"10.1016\/j.jaerosci.2020.105716","article-title":"The effects of meteorological conditions and long-range transport on PM2.5 levels in Hanoi revealed from multi-site measurement using compact sensors and machine learning approach","volume":"152","author":"Ly","year":"2021","journal-title":"J. Aerosol Sci."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5813","DOI":"10.5194\/acp-13-5813-2013","article-title":"Ozone and fine particle in the western Yangtze River Delta: An overview of 1 yr data at the SORPES station","volume":"13","author":"Ding","year":"2013","journal-title":"Atmos. Chem. Phys."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"4093","DOI":"10.1002\/2015JD024645","article-title":"Intensification of aerosol pollution associated with its feedback with surface solar radiation and winds in Beijing","volume":"121","author":"Yang","year":"2016","journal-title":"J. Geophys. Res. Atmos."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"6301","DOI":"10.5194\/acp-14-6301-2014","article-title":"10-Year spatial and temporal trends of PM2.5 concentrations in the southeastern US estimated using high-resolution satellite data","volume":"14","author":"Hu","year":"2014","journal-title":"Atmos. Chem. Phys."},{"key":"ref_25","unstructured":"Lyapustin, A., and Wang, Y. (2018). MCD19A2 MODIS\/Terra+ Aqua Land Aerosol Optical Depth Daily L2G global 1km SIN Grid V006 [data set], NASA EOSDIS Land Processes DAAC."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.rse.2019.01.033","article-title":"Comparison and evaluation of MODIS Multi-angle Implementation of Atmospheric Correction (MAIAC) aerosol product over South Asia","volume":"224","author":"Mhawish","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_27","unstructured":"Sulla-Menashe, D., and Friedl, M. (2019). MCD12Q1 MODIS\/Terra+ Aqua Land Cover Type Yearly L3 Global 500m SIN Grid V006, NASA EOSDIS Land Processes DAAC."},{"key":"ref_28","first-page":"62","article-title":"Why VIIRS data are superior to DMSP for mapping nighttime lights","volume":"35","author":"Elvidge","year":"2013","journal-title":"Proc. Asia-Pac. Adv. Netw."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.atmosenv.2012.11.043","article-title":"New Directions: Satellite driven PM2.5 exposure models to support targeted particle pollution health effects research","volume":"68","author":"Liu","year":"2013","journal-title":"Atmos. Environ."},{"key":"ref_30","unstructured":"Jarvis, A., Reuter, H.I., Nelson, A., and Guevara, E. (2022, April 01). Hole-Filled SRTM for the Globe Version 4. Available from the CGIAR-CSI SRTM 90m Database. 2008; Volume 15. Available online: http:\/\/srtm.csi.cgiar.org."},{"key":"ref_31","unstructured":"Didan, K. (2015). Mod13a3 Modis\/Terra Vegetation Indices Monthly L3 Global 1km Sin Grid V006, NASA EOSDIS Land Processes DAAC."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"105558","DOI":"10.1016\/j.envint.2020.105558","article-title":"Influence of meteorological conditions on PM2. 5 concentrations across China: A review of methodology and mechanism","volume":"139","author":"Chen","year":"2020","journal-title":"Environ. Int."},{"key":"ref_33","unstructured":"Mu\u00f1oz Sabater, J. (2019). ERA5-Land Hourly Data from 1981 to Present, Copernicus Climate Change Service (C3S) Climate Data Store (CDS)."},{"key":"ref_34","unstructured":"Hersbach, H., Bell, B., Berrisford, P., Biavati, G., Hor\u00e1nyi, A., Mu\u00f1oz Sabater, J., Nicolas, J., Peubey, C., Radu, R., and Rozum, I. (2018). ERA5 Hourly Data on Single Levels from 1979 to Present, Copernicus Climate Change Service (C3S) Climate Data Store (CDS)."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"111221","DOI":"10.1016\/j.rse.2019.111221","article-title":"Estimating 1-Km-Resolution PM2.5 concentrations across China using the space-time random forest approach","volume":"231","author":"Wei","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"128801","DOI":"10.1016\/j.chemosphere.2020.128801","article-title":"Satellite-based ground PM2.5 estimation using a gradient boosting decision tree","volume":"268","author":"Zhang","year":"2021","journal-title":"Chemosphere"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"134003","DOI":"10.1016\/j.chemosphere.2022.134003","article-title":"Spatiotemporal PM2.5 estimations in China from 2015 to 2020 using an improved gradient boosting decision tree","volume":"296","author":"He","year":"2022","journal-title":"Chemosphere"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1080\/15481603.2019.1703288","article-title":"Estimating ground-level particulate matter concentrations using satellite-based data: A review","volume":"57","author":"Shin","year":"2020","journal-title":"GIScience Remote Sens."},{"key":"ref_40","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Breiman, L., Friedman, J.H., Olshen, R.A., and Stone, C.J. (2017). Classification and Regression Trees, Routledge.","DOI":"10.1201\/9781315139470"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"105801","DOI":"10.1016\/j.envint.2020.105801","article-title":"Construction of a virtual PM2. 5 observation network in China based on high-density surface meteorological observations using the Extreme Gradient Boosting model","volume":"141","author":"Gui","year":"2020","journal-title":"Environ. Int."},{"key":"ref_43","first-page":"76","article-title":"Estimation of hourly ground-level PM2. 5 concentration based on himawari-8 apparent reflectance","volume":"59","author":"Fan","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2152","DOI":"10.1021\/acs.est.0c05815","article-title":"High-resolution spatiotemporal modeling for ambient PM2.5 exposure assessment in china from 2013 to 2019","volume":"55","author":"Huang","year":"2021","journal-title":"Environ. Sci. Technol."},{"key":"ref_45","unstructured":"Molnar, C. (2020). Interpretable Machine Learning, Lulu Press."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"de Leeuw, G., van der A, R., Bai, J., Xue, Y., Varotsos, C., Li, Z., Fan, C., Chen, X., Christodoulakis, I., and Ding, J. (2021). Air Quality over China. Remote Sens., 13.","DOI":"10.3390\/rs13173542"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"3593","DOI":"10.1080\/01431160600617236","article-title":"Long-range persistence in global Aerosol Index dynamics","volume":"27","author":"Varotsos","year":"2006","journal-title":"Int. J. Remote Sens."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.atmosenv.2012.05.015","article-title":"An observational study of the atmospheric ultra-fine particle dynamics","volume":"59","author":"Varotsos","year":"2012","journal-title":"Atmos. Environ."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1016\/j.scitotenv.2014.11.007","article-title":"Spatial and seasonal variations of PM2. 5 mass and species during 2010 in Xi\u2019an, China","volume":"508","author":"Wang","year":"2015","journal-title":"Sci. Total Environ."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"140837","DOI":"10.1016\/j.scitotenv.2020.140837","article-title":"Meteorological influences on PM2. 5 and O3 trends and associated health burden since China\u2019s clean air actions","volume":"744","author":"Chen","year":"2020","journal-title":"Sci. Total Environ."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"121826","DOI":"10.1016\/j.jclepro.2020.121826","article-title":"Effects of heating activities in winter on characteristics of PM2.5-Bound Pb, Cd and lead isotopes in cities of China","volume":"265","author":"Deng","year":"2020","journal-title":"J. Clean. Prod."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"102316","DOI":"10.1016\/j.jhealeco.2020.102316","article-title":"The winter choke: Coal-fired heating, air pollution, and mortality in China","volume":"71","author":"Fan","year":"2020","journal-title":"J. Health Econ."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"792","DOI":"10.1016\/j.envpol.2019.02.081","article-title":"Examining the spatially varying effects of factors on PM2.5 concentrations in Chinese cities using geographically weighted regression modeling","volume":"248","author":"Wang","year":"2019","journal-title":"Environ. Pollut."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"7997","DOI":"10.5194\/acp-17-7997-2017","article-title":"Opposite long-term trends in aerosols between low and high altitudes: A testimony to the aerosol\u2013PBL feedback","volume":"17","author":"Dong","year":"2017","journal-title":"Atmos. Chem. Phys."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.atmosres.2018.08.029","article-title":"Aerosol vertical distribution and optical properties of different pollution events in Beijing in autumn 2017","volume":"215","author":"Sheng","year":"2019","journal-title":"Atmos. Res."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"8995","DOI":"10.5194\/acp-18-8995-2018","article-title":"Vertical distributions of aerosol optical properties during the spring 2016 ARIAs airborne campaign in the North China Plain","volume":"18","author":"Wang","year":"2018","journal-title":"Atmos. Chem. Phys."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"134634","DOI":"10.1016\/j.scitotenv.2019.134634","article-title":"The impact of aerosol on MODIS cloud detection and property retrieval in seriously polluted East China","volume":"711","author":"Zhang","year":"2020","journal-title":"Sci. Total Environ."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1126\/science.1227079","article-title":"Detecting causality in complex ecosystems","volume":"338","author":"Sugihara","year":"2012","journal-title":"Science"},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.atmosenv.2017.02.023","article-title":"Spatiotemporal prediction of continuous daily PM2.5 concentrations across China using a spatially explicit machine learning algorithm","volume":"155","author":"Zhan","year":"2017","journal-title":"Atmos. Environ."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"156740","DOI":"10.1016\/j.scitotenv.2022.156740","article-title":"Slower than expected reduction in annual PM2.5 in Xi\u2019an revealed by machine learning-based meteorological normalization","volume":"841","author":"Wang","year":"2022","journal-title":"Sci. Total Environ."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1016\/j.rse.2017.07.023","article-title":"Full-coverage high-resolution daily PM2.5 estimation using MAIAC AOD in the Yangtze River Delta of China","volume":"199","author":"Xiao","year":"2017","journal-title":"Remote Sens. Environ."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/2\/358\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:02:11Z","timestamp":1760119331000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/2\/358"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,6]]},"references-count":61,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,1]]}},"alternative-id":["rs15020358"],"URL":"https:\/\/doi.org\/10.3390\/rs15020358","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,6]]}}}