{"id":{"repo_id":"nus","oai_identifier":"oai:scholarbank.nus.edu.sg:10635/309519"},"canonical_url":"https://search.dev.ndltd.org/etd/nus/oai:scholarbank.nus.edu.sg:10635/309519","repository":{"repo_id":"nus","name":"National University of Singapore","base_url":"https://scholarbank.nus.edu.sg/oai/request"},"display":{"title":"ENHANCING pm2.5 AIR POLLUTION ANALYSIS IN BEIJING: A TRANSITION FROM NON-PARAMETRIC REGRESSION TO ADVANCED MACHINE LEARNING METHODOLOGY","abstract":"This study presents a machine learning approach to analyzing PM2.5 pollution in Beijing, transitioning from traditional non-parametric methods to the advanced Random Forest Plus (RF+) methodology. The original research, which used non-parametric regression and bandwidth selection frequency, to assess PM2.5 levels as well as feature importance, may result in overfitting, lack of interpretability and computational inefficiency. Our research aims to address these limitations by making use of the RF+ framework, due its robustness in high-dimensional data and its ability to provide interpretable feature importance measures. We will reanalyze the same PM2.5 dataset used in the original study, applying the RF+ method to enhance the predictive accuracy and interpretability of the results. This study not only tries provide a more reliable assessment of PM2.5 pollution in Beijing but also serves as a case study for the application of advanced machine learning techniques in environmental science.","abstract_html":"This study presents a machine learning approach to analyzing PM2.5 pollution in Beijing, transitioning from traditional non-parametric methods to the advanced Random Forest Plus (RF+) methodology. The original research, which used non-parametric regression and bandwidth selection frequency, to assess PM2.5 levels as well as feature importance, may result in overfitting, lack of interpretability and computational inefficiency. Our research aims to address these limitations by making use of the RF+ framework, due its robustness in high-dimensional data and its ability to provide interpretable feature importance measures. We will reanalyze the same PM2.5 dataset used in the original study, applying the RF+ method to enhance the predictive accuracy and interpretability of the results. This study not only tries provide a more reliable assessment of PM2.5 pollution in Beijing but also serves as a case study for the application of advanced machine learning techniques in environmental science.","abstract_has_math":false,"creators":["ZENG ZITONG"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-04-01","date_published":"2024-04-01","updated_at":"2026-07-24T03:30:47Z","subjects":["causal inference","data science","machine learning","statistics"],"languages":[],"rights":[],"rights_urls":["https://scholarbank.nus.edu.sg/bitstreams/d118acc5-ec83-437e-b30f-42515d2728ae/download"],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["ZENG ZITONG"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2024-04-01"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://scholarbank.nus.edu.sg/handle/10635/309519"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["causal inference","data science","machine learning","statistics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["https://scholarbank.nus.edu.sg/bitstreams/d118acc5-ec83-437e-b30f-42515d2728ae/download"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://scholarbank.nus.edu.sg/bitstreams/77c2dcc1-396d-41af-b9b1-8fb8d30994e8/download"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This study presents a machine learning approach to analyzing PM2.5 pollution in Beijing, transitioning from traditional non-parametric methods to the advanced Random Forest Plus (RF+) methodology. The original research, which used non-parametric regression and bandwidth selection frequency, to assess PM2.5 levels as well as feature importance, may result in overfitting, lack of interpretability and computational inefficiency. Our research aims to address these limitations by making use of the RF+ framework, due its robustness in high-dimensional data and its ability to provide interpretable feature importance measures. We will reanalyze the same PM2.5 dataset used in the original study, applying the RF+ method to enhance the predictive accuracy and interpretability of the results. This study not only tries provide a more reliable assessment of PM2.5 pollution in Beijing but also serves as a case study for the application of advanced machine learning techniques in environmental science."]},{"key":"dc:format.checksum.md5","label":"Dc Format Checksum Md5","values":["9f3c6f2aa8f96291ef77b0a18484521d","c8f394443d0b09abb6a262a62dbac24a","919e0ef5c0f37c9d80a73e90f711739b"]},{"key":"dc:title","label":"Title","values":["ENHANCING pm2.5 AIR POLLUTION ANALYSIS IN BEIJING: A TRANSITION FROM NON-PARAMETRIC REGRESSION TO ADVANCED MACHINE LEARNING METHODOLOGY"]}]}],"canonical_facts":{"dc:creator":["ZENG ZITONG"],"dc:date.issued":["2024-04-01"],"dc:description.abstract":["This study presents a machine learning approach to analyzing PM2.5 pollution in Beijing, transitioning from traditional non-parametric methods to the advanced Random Forest Plus (RF+) methodology. The original research, which used non-parametric regression and bandwidth selection frequency, to assess PM2.5 levels as well as feature importance, may result in overfitting, lack of interpretability and computational inefficiency. Our research aims to address these limitations by making use of the RF+ framework, due its robustness in high-dimensional data and its ability to provide interpretable feature importance measures. We will reanalyze the same PM2.5 dataset used in the original study, applying the RF+ method to enhance the predictive accuracy and interpretability of the results. This study not only tries provide a more reliable assessment of PM2.5 pollution in Beijing but also serves as a case study for the application of advanced machine learning techniques in environmental science."],"dc:format.checksum.md5":["9f3c6f2aa8f96291ef77b0a18484521d","c8f394443d0b09abb6a262a62dbac24a","919e0ef5c0f37c9d80a73e90f711739b"],"dc:identifier.uri":["https://scholarbank.nus.edu.sg/bitstreams/77c2dcc1-396d-41af-b9b1-8fb8d30994e8/download"],"dc:relation.isreferencedby":["https://scholarbank.nus.edu.sg/handle/10635/309519"],"dc:rights":["https://scholarbank.nus.edu.sg/bitstreams/d118acc5-ec83-437e-b30f-42515d2728ae/download"],"dc:subject":["causal inference","data science","machine learning","statistics"],"dc:title":["ENHANCING pm2.5 AIR POLLUTION ANALYSIS IN BEIJING: A TRANSITION FROM NON-PARAMETRIC REGRESSION TO ADVANCED MACHINE LEARNING METHODOLOGY"],"dc:type":["Thesis"]},"updated_at":"2026-07-24T03:30:47Z"}