<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>0187-6236</journal-id>
<journal-title><![CDATA[Atmósfera]]></journal-title>
<abbrev-journal-title><![CDATA[Atmósfera]]></abbrev-journal-title>
<issn>0187-6236</issn>
<publisher>
<publisher-name><![CDATA[Universidad Nacional Autónoma de México, Instituto de Ciencias de la Atmósfera y Cambio Climático]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S0187-62362023000300107</article-id>
<article-id pub-id-type="doi">10.20937/atm.53053</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Research on the usability of different machine learning methods in visibility forecasting]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Wen]]></surname>
<given-names><![CDATA[Wu]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Lei]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Chan]]></surname>
<given-names><![CDATA[P. W.]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[Yuan-Yuan]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Wei]]></surname>
<given-names><![CDATA[Min]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Chengdu University of Information Technology School of Computer Science ]]></institution>
<addr-line><![CDATA[Chengdu ]]></addr-line>
<country>China</country>
</aff>
<aff id="Af2">
<institution><![CDATA[,Sun Yat-Sen University School of Atmospheric Sciences ]]></institution>
<addr-line><![CDATA[Zhuhai ]]></addr-line>
<country>China</country>
</aff>
<aff id="Af3">
<institution><![CDATA[,Hong Kong Observatory  ]]></institution>
<addr-line><![CDATA[ Hong Kong]]></addr-line>
<country>China</country>
</aff>
<aff id="Af4">
<institution><![CDATA[,China Institute of Water Resources and Hydropower Research  ]]></institution>
<addr-line><![CDATA[Beijing ]]></addr-line>
<country>China</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>00</month>
<year>2023</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>00</month>
<year>2023</year>
</pub-date>
<volume>37</volume>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_arttext&amp;pid=S0187-62362023000300107&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_abstract&amp;pid=S0187-62362023000300107&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_pdf&amp;pid=S0187-62362023000300107&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[ABSTRACT Haze pollution, mainly characterized by low visibility, is one of the main environmental problems currently faced by China. Accurate haze forecasts facilitate the implementation of preventive measures to control the emission of air pollutants and thereby mitigate haze pollution. However, it is not easy to accurately predict low visibility events induced by haze, which requires not only accurate prediction for weather elements, but also refined and real-time updated source emission inventory. In order to obtain reliable forecasting tools, this paper studies the usability of several popular machine learning methods, such as support vector machine (SVM), k-nearest neighbor, and random forest, as well as several deep learning methods, on visibility forecasting. Starting from the main factors related to visibility, the relationships between wind speed, wind direction, temperature, humidity, and visibility are discussed. Training and forecasting were performed using the machine learning methods. The accuracy of these methods in visibility forecasting was confirmed through several parameters (i.e., root-mean-square error, mean absolute error, and mean absolute percentage error). The results show that: (1) among all meteorological parameters, wind speed was the best at reflecting the visibility change patterns; (2) long short-term memory recurrent neural networks (LSTM RNN), and gated recurrent unit (GRU) methods perform almost equally well on short-term visibility forecasts (i.e., 1, 3, and 6 h); (3) a classical machine learning method (i.e., the SVM) performs well in mid- and long-term visibility forecasts; (4) machine learning methods also have a certain degree of forecast accuracy even for long time periods (e.g., 7 2h).]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[RESUMEN La contaminación por neblina, caracterizada principalmente por la baja visibilidad, es uno de los principales problemas ambientales a los que se enfrenta China en la actualidad. El pronóstico exacto de la neblina es útil para la aplicación de medidas preventivas orientadas a controlar emisiones de contaminantes atmosféricos y aliviar la contaminación por neblina. Sin embargo, no es fácil predecir con precisión los acontecimientos de baja visibilidad causados por neblina, lo cual requiere no sólo un pronóstico riguroso de los factores meteorológicos, sino también una actualización detallada y en tiempo real de los inventarios de emisiones de las fuentes. Con el fin de obtener una herramienta de predicción fiable, se estudian varios métodos populares de aprendizaje automático, como la máquina vectorial de apoyo (SVM, por su sigla en inglés), el k-vecino más próximo, el bosque aleatorio y varios métodos de aprendizaje profundo. A partir de los principales factores que influyen en la visibilidad, se analizan las relaciones entre velocidad y dirección del viento, temperatura, humedad y visibilidad. El método de aprendizaje automático se utiliza para entrenamiento y pronóstico. La precisión de estos métodos para pronosticar la visibilidad se verifica mediante varios parámetros (error de raíz cuadrada media, error absoluto medio y error porcentual absoluto medio). Los resultados muestran que: 1) entre todos los parámetros meteorológicos, la velocidad del viento puede reflejar mejor la variación de la visibilidad; 2) el rendimiento de las redes neuronales recurrentes de memoria a largo-corto plazo (LSTM RNN) y el método de unidades recurrentes cerradas (GRU) en la predicción de visibilidad a corto plazo (es decir, 1, 3 y 6 h) es casi igual; 3) el método clásico de aprendizaje automático (SVM) funciona bien para el pronóstico de visibilidad a medio y largo plazo, y 4) el método de aprendizaje automático también tiene cierto grado de precisión en el pronóstico, incluso en un periodo de tiempo más largo (p. ej., 72 h).]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[visibility forecast]]></kwd>
<kwd lng="en"><![CDATA[deep learning]]></kwd>
<kwd lng="en"><![CDATA[machine learning]]></kwd>
<kwd lng="en"><![CDATA[time-series forecasting]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Aasim]]></surname>
</name>
<name>
<surname><![CDATA[Singh]]></surname>
<given-names><![CDATA[SN]]></given-names>
</name>
<name>
<surname><![CDATA[Abheejeet]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Repeated wavelet transform based ARIMA model for very short-term wind speed forecasting]]></article-title>
<source><![CDATA[Renewable Energy]]></source>
<year>2018</year>
<volume>136</volume>
<page-range>758-68</page-range></nlm-citation>
</ref>
<ref id="B2">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Baklanov]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Mestayer]]></surname>
<given-names><![CDATA[PG]]></given-names>
</name>
<name>
<surname><![CDATA[Clappier]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Zilitinkevich]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Joffre]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Mahura]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Nielsen]]></surname>
<given-names><![CDATA[NW]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Towards improving the simulation of meteorological fields in urban areas through updated/advanced surface fluxes description]]></article-title>
<source><![CDATA[Atmospheric Chemistry and Physics]]></source>
<year>2008</year>
<volume>8</volume>
<page-range>523-43</page-range></nlm-citation>
</ref>
<ref id="B3">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bray]]></surname>
<given-names><![CDATA[CD]]></given-names>
</name>
<name>
<surname><![CDATA[Battye]]></surname>
<given-names><![CDATA[W]]></given-names>
</name>
<name>
<surname><![CDATA[Aneja]]></surname>
<given-names><![CDATA[VP]]></given-names>
</name>
<name>
<surname><![CDATA[Tong]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Lee]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
<name>
<surname><![CDATA[Tang]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Nowak]]></surname>
<given-names><![CDATA[JB]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Evaluating ammonia (NH3) predictions in the NOAA National Air Quality Forecast Capability (NAQFC) using in-situ aircraft and satellite measurements from the CalNex2010 campaign]]></article-title>
<source><![CDATA[Atmospheric Environment]]></source>
<year>2017</year>
<volume>163</volume>
<page-range>65-76</page-range></nlm-citation>
</ref>
<ref id="B4">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Deng]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Ma]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Gao]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[The MR-CA models for analysis of pollution sources and prediction of PM2.5.]]></article-title>
<source><![CDATA[IEEE Transactions on Systems, Man, and Cybernetics: Systems]]></source>
<year>2017</year>
<volume>49</volume>
<page-range>814-20</page-range></nlm-citation>
</ref>
<ref id="B5">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Donnelly]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Misstear]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Broderick]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Real time air quality forecasting using integrated parametric and non-parametric regression techniques]]></article-title>
<source><![CDATA[Atmospheric Environment]]></source>
<year>2015</year>
<volume>103</volume>
<page-range>53-65</page-range></nlm-citation>
</ref>
<ref id="B6">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Doreswamy]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Harishkumar]]></surname>
<given-names><![CDATA[KS]]></given-names>
</name>
<name>
<surname><![CDATA[Yogesh]]></surname>
<given-names><![CDATA[KM]]></given-names>
</name>
<name>
<surname><![CDATA[Gad]]></surname>
<given-names><![CDATA[IM]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Forecasting air pollution particulate matter (PM2.5) using machine learning regression models]]></article-title>
<source><![CDATA[Procedia Computer Science]]></source>
<year>2020</year>
<volume>171</volume>
<page-range>2057-66</page-range></nlm-citation>
</ref>
<ref id="B7">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Dragomir]]></surname>
<given-names><![CDATA[EG]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Air quality index prediction using k-nearest neighbor technique]]></article-title>
<source><![CDATA[Bulletin of PG University of Ploiesti. Series Mathematics, Informatics, Physics]]></source>
<year>2010</year>
<volume>42</volume>
<page-range>103-8</page-range></nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Fan]]></surname>
<given-names><![CDATA[JX]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Q]]></given-names>
</name>
<name>
<surname><![CDATA[Hou]]></surname>
<given-names><![CDATA[JX]]></given-names>
</name>
<name>
<surname><![CDATA[Feng]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Karimian]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Lin]]></surname>
<given-names><![CDATA[SF]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A spatiotemporal prediction framework for air pollution based on deep RNN]]></article-title>
<source><![CDATA[ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences]]></source>
<year>2017</year>
<volume>4</volume>
<page-range>15-22</page-range></nlm-citation>
</ref>
<ref id="B9">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Feng]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Zheng]]></surname>
<given-names><![CDATA[HJ]]></given-names>
</name>
<name>
<surname><![CDATA[Gao]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[AR]]></given-names>
</name>
<name>
<surname><![CDATA[Huang]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[JX]]></given-names>
</name>
<name>
<surname><![CDATA[Luo]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Fan]]></surname>
<given-names><![CDATA[JR]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Recurrent neural network and random forest for analysis and accurate forecast of atmospheric pollutants: A case study in Hangzhou, China]]></article-title>
<source><![CDATA[Journal of Cleaner Production]]></source>
<year>2019</year>
<volume>231</volume>
<page-range>1005-15</page-range></nlm-citation>
</ref>
<ref id="B10">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Feng]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Q]]></given-names>
</name>
<name>
<surname><![CDATA[Zhu]]></surname>
<given-names><![CDATA[YJ]]></given-names>
</name>
<name>
<surname><![CDATA[Hou]]></surname>
<given-names><![CDATA[JX]]></given-names>
</name>
<name>
<surname><![CDATA[Jin]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[JJ]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Artificial neural networks forecasting of PM2.5 pollution using air mass trajectory based geographic model and wavelet transformation]]></article-title>
<source><![CDATA[Atmospheric Environment]]></source>
<year>2015</year>
<volume>107</volume>
<page-range>118-28</page-range></nlm-citation>
</ref>
<ref id="B11">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Gennaro]]></surname>
<given-names><![CDATA[GD]]></given-names>
</name>
<name>
<surname><![CDATA[Trizioa]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Gilioa]]></surname>
<given-names><![CDATA[AD]]></given-names>
</name>
<name>
<surname><![CDATA[Pey]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Pérez]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
<name>
<surname><![CDATA[Cusack]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Alastuey]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Querol]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Neural network model for the prediction of PM10 daily concentrations in two sites in the Western Mediterranean]]></article-title>
<source><![CDATA[Science of The Total Environment]]></source>
<year>2013</year>
<volume>463</volume>
<page-range>875-83</page-range></nlm-citation>
</ref>
<ref id="B12">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Graves]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Schmidhuber]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Framewise phoneme classification with bidirectional LSTM and other neural network architectures]]></article-title>
<source><![CDATA[Neural Networks]]></source>
<year>2005</year>
<volume>18</volume>
<page-range>602-10</page-range></nlm-citation>
</ref>
<ref id="B13">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Gupta]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
<name>
<surname><![CDATA[Christopher]]></surname>
<given-names><![CDATA[SA]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Particulate matter air quality assessment using integrated surface, satellite, and meteorological products: Multiple regression approach]]></article-title>
<source><![CDATA[Journal of Geophysical Research: Atmospheres]]></source>
<year>2009</year>
<volume>114</volume>
<page-range>1-13</page-range></nlm-citation>
</ref>
<ref id="B14">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Huang]]></surname>
<given-names><![CDATA[CJ]]></given-names>
</name>
<name>
<surname><![CDATA[Kuo]]></surname>
<given-names><![CDATA[PH.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[ReNet: A deep CNN-LSTM model for particulate matter (PM2.5) forecasting in smart cities]]></article-title>
<source><![CDATA[Sensors]]></source>
<year>2018</year>
<volume>18</volume>
<page-range>2-22</page-range></nlm-citation>
</ref>
<ref id="B15">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Khaled]]></surname>
<given-names><![CDATA[BS]]></given-names>
</name>
<name>
<surname><![CDATA[Abdullah]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Urban air pollution monitoring system with forecasting models]]></article-title>
<source><![CDATA[IEEE Sensors Journal]]></source>
<year>2016</year>
<volume>16</volume>
<page-range>2598-606</page-range></nlm-citation>
</ref>
<ref id="B16">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kim]]></surname>
<given-names><![CDATA[YH]]></given-names>
</name>
<name>
<surname><![CDATA[Fu]]></surname>
<given-names><![CDATA[JS]]></given-names>
</name>
<name>
<surname><![CDATA[Miller]]></surname>
<given-names><![CDATA[TL]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Improving ozone modeling in complex terrain at a fine grid resolution: Part I - examination of analysis nudging and all PBL schemes associated with LSMs in meteorological model]]></article-title>
<source><![CDATA[Atmospheric Environment]]></source>
<year>2010</year>
<volume>44</volume>
<page-range>523-32</page-range></nlm-citation>
</ref>
<ref id="B17">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kim]]></surname>
<given-names><![CDATA[YH]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Convolutional neural networks for sentence classification]]></article-title>
<source><![CDATA[Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2014)]]></source>
<year>2014</year>
<page-range>1746-51</page-range><publisher-loc><![CDATA[Doha, Qatar ]]></publisher-loc>
</nlm-citation>
</ref>
<ref id="B18">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kuremoto]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Kimura]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Kobayashi]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Obayashi]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Time series forecasting using a deep belief network with restricted Boltzmann machines]]></article-title>
<source><![CDATA[Neurocomputing]]></source>
<year>2014</year>
<volume>137</volume>
<page-range>47-56</page-range></nlm-citation>
</ref>
<ref id="B19">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lai]]></surname>
<given-names><![CDATA[YC]]></given-names>
</name>
<name>
<surname><![CDATA[David]]></surname>
<given-names><![CDATA[AD]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Use of the autoregressive integrated moving average (ARIMA) model to forecast near-term regional temperature and precipitation]]></article-title>
<source><![CDATA[Weather and Forecasting]]></source>
<year>2020</year>
<volume>33</volume>
<page-range>959-76</page-range></nlm-citation>
</ref>
<ref id="B20">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[XL]]></given-names>
</name>
<name>
<surname><![CDATA[Luo]]></surname>
<given-names><![CDATA[AR]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[JG]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Air pollutant concentration forecast based on support vector regression and quantum-behaved particle swarm optimization]]></article-title>
<source><![CDATA[Environmental Modeling &amp; Assessment]]></source>
<year>2019</year>
<volume>24</volume>
<page-range>205-22</page-range></nlm-citation>
</ref>
<ref id="B21">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[YY]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[WH]]></given-names>
</name>
<name>
<surname><![CDATA[Chan]]></surname>
<given-names><![CDATA[PW]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[YS]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Rapid identification of rainstorm disaster risks based on an artificial intelligence technology using the 2DPCA method]]></article-title>
<source><![CDATA[Atmospheric Research]]></source>
<year>2019</year>
<volume>227</volume>
<page-range>157-64</page-range></nlm-citation>
</ref>
<ref id="B22">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[YY]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[YS]]></given-names>
</name>
<name>
<surname><![CDATA[Chan]]></surname>
<given-names><![CDATA[PW]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[WH]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Dynamic spatial-temporal precipitation distribution models for short-duration rainstorms in Shenzhen, China based on machine learning]]></article-title>
<source><![CDATA[Atmospheric Research]]></source>
<year>2020</year>
<volume>237</volume>
</nlm-citation>
</ref>
<ref id="B23">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[YY]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[YS]]></given-names>
</name>
<name>
<surname><![CDATA[Chan]]></surname>
<given-names><![CDATA[PW]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[WH]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Estimation of precipitation induced by tropical cyclones based on machine-learning-enhanced analogue identification of numerical prediction]]></article-title>
<source><![CDATA[Meteorological Applications]]></source>
<year>2021</year>
<volume>28</volume>
</nlm-citation>
</ref>
<ref id="B24">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lu]]></surname>
<given-names><![CDATA[WZ]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[WJ]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Potential assessment of the &#8220;support vector machine&#8221; method in forecasting ambient air pollutant trends]]></article-title>
<source><![CDATA[Chemosphere]]></source>
<year>2005</year>
<volume>59</volume>
<page-range>693-701</page-range></nlm-citation>
</ref>
<ref id="B25">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Pérez]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
<name>
<surname><![CDATA[Reyes]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[An integrated neural network model for PM10 forecasting]]></article-title>
<source><![CDATA[Atmospheric Environment]]></source>
<year>2006</year>
<volume>40</volume>
<page-range>2845-51</page-range></nlm-citation>
</ref>
<ref id="B26">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ren]]></surname>
<given-names><![CDATA[SQ]]></given-names>
</name>
<name>
<surname><![CDATA[He]]></surname>
<given-names><![CDATA[KM]]></given-names>
</name>
<name>
<surname><![CDATA[Girshick]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Sun]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Faster R-CNN: Towards real-time object detection with region proposal networks]]></article-title>
<source><![CDATA[Advances in Neural Information Processing Systems]]></source>
<year>2017</year>
<volume>39</volume>
<page-range>1137-49</page-range></nlm-citation>
</ref>
<ref id="B27">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sharma]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
<name>
<surname><![CDATA[Taneja]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Sagar]]></surname>
<given-names><![CDATA[V]]></given-names>
</name>
<name>
<surname><![CDATA[Bhatt]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Forecasting air pollution load in Delhi using data analysis tools]]></article-title>
<source><![CDATA[Procedia Computer Science]]></source>
<year>2018</year>
<volume>132</volume>
<page-range>1077-85</page-range></nlm-citation>
</ref>
<ref id="B28">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Th]]></surname>
<given-names><![CDATA[Slini]]></given-names>
</name>
<name>
<surname><![CDATA[Karatzas]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Moussiopoulos]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Statistical analysis of environmental data as the basis of forecasting: An air quality application]]></article-title>
<source><![CDATA[Science of The total Environment]]></source>
<year>2002</year>
<volume>288</volume>
<page-range>227-37</page-range></nlm-citation>
</ref>
<ref id="B29">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sotomayor-Olmedo]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Aceves-Fernández]]></surname>
<given-names><![CDATA[MA]]></given-names>
</name>
<name>
<surname><![CDATA[Gorrostieta-Hurtado]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Pedraza-Ortega]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Ramos-Arreguín]]></surname>
<given-names><![CDATA[JM]]></given-names>
</name>
<name>
<surname><![CDATA[Vargas-Soto]]></surname>
<given-names><![CDATA[JE]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Forecast urban air pollution in Mexico City by using support vector machines: A kernel performance approach]]></article-title>
<source><![CDATA[International Journal of Intelligence Science]]></source>
<year>2013</year>
<volume>3</volume>
<page-range>126-35</page-range></nlm-citation>
</ref>
<ref id="B30">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sun]]></surname>
<given-names><![CDATA[HW]]></given-names>
</name>
<name>
<surname><![CDATA[Gui]]></surname>
<given-names><![CDATA[DW]]></given-names>
</name>
<name>
<surname><![CDATA[Yan]]></surname>
<given-names><![CDATA[BW]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Liao]]></surname>
<given-names><![CDATA[WH]]></given-names>
</name>
<name>
<surname><![CDATA[Zhu]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Lu]]></surname>
<given-names><![CDATA[CW]]></given-names>
</name>
<name>
<surname><![CDATA[Zhao]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Assessing the potential of random forest method for estimating solar radiation using air pollution index]]></article-title>
<source><![CDATA[Energy Conversion and Management]]></source>
<year>2016</year>
<volume>119</volume>
<page-range>121-9</page-range></nlm-citation>
</ref>
<ref id="B31">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Tao]]></surname>
<given-names><![CDATA[Q]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Denis]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Air pollution forecasting using a deep learning model based on 1D convnets and bidirectional GRU]]></article-title>
<source><![CDATA[IEEE Access]]></source>
<year>2019</year>
<volume>7</volume>
<page-range>6690-8</page-range></nlm-citation>
</ref>
<ref id="B32">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Tong]]></surname>
<given-names><![CDATA[WT]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[LX]]></given-names>
</name>
<name>
<surname><![CDATA[Zhou]]></surname>
<given-names><![CDATA[XL]]></given-names>
</name>
<name>
<surname><![CDATA[Hamilton]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Deep learning PM2.5 concentrations with bidirectional LSTM RNN]]></article-title>
<source><![CDATA[Air Quality, Atmosphere &amp; Health]]></source>
<year>2019</year>
<volume>12</volume>
<page-range>411-23</page-range></nlm-citation>
</ref>
<ref id="B33">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Visin]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Kastner]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Cho]]></surname>
<given-names><![CDATA[K]]></given-names>
</name>
<name>
<surname><![CDATA[Matteucci]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Courville]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Bengio]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[ReNet: A recurrent neural network-based alternative to convolutional networks]]></article-title>
<source><![CDATA[arXiv]]></source>
<year>2015</year>
<volume>1505</volume>
<page-range>00393</page-range></nlm-citation>
</ref>
<ref id="B34">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Woody]]></surname>
<given-names><![CDATA[MC]]></given-names>
</name>
<name>
<surname><![CDATA[Wong]]></surname>
<given-names><![CDATA[HW]]></given-names>
</name>
<name>
<surname><![CDATA[West]]></surname>
<given-names><![CDATA[JJ]]></given-names>
</name>
<name>
<surname><![CDATA[Arunachalamas]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Multiscale predictions of aviation-attributable PM2.5 for U.S. airports modeled using CMAQ with plume-in-grid and an aircraft-specific 1-D emission model]]></article-title>
<source><![CDATA[Atmospheric Environment]]></source>
<year>2016</year>
<volume>147</volume>
<page-range>384-94</page-range></nlm-citation>
</ref>
<ref id="B35">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Yildirim]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Bayramoglu]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Adaptive neuro-fuzzy based modeling for prediction of air pollution daily levels in city of Zonguldak]]></article-title>
<source><![CDATA[Chemosphere]]></source>
<year>2006</year>
<volume>63</volume>
<page-range>1575-82</page-range></nlm-citation>
</ref>
<ref id="B36">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Yue]]></surname>
<given-names><![CDATA[SC]]></given-names>
</name>
<name>
<surname><![CDATA[Chiao]]></surname>
<given-names><![CDATA[HT]]></given-names>
</name>
<name>
<surname><![CDATA[Satheesh]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Huang]]></surname>
<given-names><![CDATA[YP]]></given-names>
</name>
<name>
<surname><![CDATA[Tsai]]></surname>
<given-names><![CDATA[YT]]></given-names>
</name>
<name>
<surname><![CDATA[Lin]]></surname>
<given-names><![CDATA[KM]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[An LSTM-based aggregated model for air pollution forecasting]]></article-title>
<source><![CDATA[Atmospheric Pollution Research]]></source>
<year>2020</year>
<volume>11</volume>
<page-range>1451-63</page-range></nlm-citation>
</ref>
<ref id="B37">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhao]]></surname>
<given-names><![CDATA[JC]]></given-names>
</name>
<name>
<surname><![CDATA[Deng]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Cai]]></surname>
<given-names><![CDATA[YY]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Long short-term memory-Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction]]></article-title>
<source><![CDATA[Chemosphere]]></source>
<year>2019</year>
<volume>220</volume>
<page-range>486-92</page-range></nlm-citation>
</ref>
<ref id="B38">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhou]]></surname>
<given-names><![CDATA[GQ]]></given-names>
</name>
<name>
<surname><![CDATA[Xu]]></surname>
<given-names><![CDATA[JM]]></given-names>
</name>
<name>
<surname><![CDATA[Xie]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Chang]]></surname>
<given-names><![CDATA[LY]]></given-names>
</name>
<name>
<surname><![CDATA[Gao]]></surname>
<given-names><![CDATA[W]]></given-names>
</name>
<name>
<surname><![CDATA[Gu]]></surname>
<given-names><![CDATA[YX]]></given-names>
</name>
<name>
<surname><![CDATA[Zhou]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Numerical air quality forecasting over eastern China: an operational application of WRF-Chem]]></article-title>
<source><![CDATA[Atmospheric Environment]]></source>
<year>2017</year>
<volume>153</volume>
<page-range>94-108</page-range></nlm-citation>
</ref>
<ref id="B39">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhou]]></surname>
<given-names><![CDATA[QP]]></given-names>
</name>
<name>
<surname><![CDATA[Jiang]]></surname>
<given-names><![CDATA[HY]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[JZ]]></given-names>
</name>
<name>
<surname><![CDATA[Zhou]]></surname>
<given-names><![CDATA[JL]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A hybrid model for PM2.5 forecasting based on ensemble empirical mode decomposition and a general regression neural network]]></article-title>
<source><![CDATA[Science of The Total Environment]]></source>
<year>2014</year>
<volume>496</volume>
<page-range>264-74</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
