Air Quality Prediction in Beijing: Machine and Deep Learning Analysis

In densely populated urban hubs like Beijing, the presence of PM2.5, a critical air quality metric, poses significant hazards to human health and the environment. This study delves into predictive modeling approaches for forecasting PM2.5 concentrations in response to escalating concerns.We analyze...

Full description

Saved in:
Bibliographic Details
Main Authors: Das Shuvendu, Singh Karanvir, Kaur Kiranjeet
Format: Article
Language:English
Published: EDP Sciences 2024-01-01
Series:ITM Web of Conferences
Subjects:
Online Access:https://www.itm-conferences.org/articles/itmconf/pdf/2024/11/itmconf_icaetm2024_01012.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850247547795275776
author Das Shuvendu
Singh Karanvir
Kaur Kiranjeet
author_facet Das Shuvendu
Singh Karanvir
Kaur Kiranjeet
author_sort Das Shuvendu
collection DOAJ
description In densely populated urban hubs like Beijing, the presence of PM2.5, a critical air quality metric, poses significant hazards to human health and the environment. This study delves into predictive modeling approaches for forecasting PM2.5 concentrations in response to escalating concerns.We analyze a wide range of approaches, including RDF, CNN, STM and fundamental statistical techniques, by closely analyzing Beijing’s PM2.5 concentrations and historical meteorological information. According to our research, CNN outperforms LSTM and shows excellent accuracy in forecasting PM2.5 levels. While random forest and linear regression exhibit competitiveness, their predictive prowess falls short in comparison. Conversely, less precise statistical techniques reliant on mean pollution levels are employed. The research outcomes offer significant insights to environmental authorities and policymakers regarding the effectiveness of various predictive modeling strategies for PM2.5 forecasting. Particularly noteworthy are the remarkable capabilities of deep learning techniques, notably CNN and LSTM, in discerning intricate correlations within environmental datasets. These strategies have the potential to address the urgent problem of air pollution and lessen its detrimental impact on both human health and the environment by increasing the precision of air quality predictions.
format Article
id doaj-art-5f306b0b732e4e59be7a76542efddea8
institution OA Journals
issn 2271-2097
language English
publishDate 2024-01-01
publisher EDP Sciences
record_format Article
series ITM Web of Conferences
spelling doaj-art-5f306b0b732e4e59be7a76542efddea82025-08-20T01:58:55ZengEDP SciencesITM Web of Conferences2271-20972024-01-01680101210.1051/itmconf/20246801012itmconf_icaetm2024_01012Air Quality Prediction in Beijing: Machine and Deep Learning AnalysisDas Shuvendu0Singh Karanvir1Kaur Kiranjeet2Department of Computer Science and Engineering Brainware UniversityDepartment of Computer Science and Engineering Chandigarh UniversityDepartment of Computer Science and Engineering Chandigarh UniversityIn densely populated urban hubs like Beijing, the presence of PM2.5, a critical air quality metric, poses significant hazards to human health and the environment. This study delves into predictive modeling approaches for forecasting PM2.5 concentrations in response to escalating concerns.We analyze a wide range of approaches, including RDF, CNN, STM and fundamental statistical techniques, by closely analyzing Beijing’s PM2.5 concentrations and historical meteorological information. According to our research, CNN outperforms LSTM and shows excellent accuracy in forecasting PM2.5 levels. While random forest and linear regression exhibit competitiveness, their predictive prowess falls short in comparison. Conversely, less precise statistical techniques reliant on mean pollution levels are employed. The research outcomes offer significant insights to environmental authorities and policymakers regarding the effectiveness of various predictive modeling strategies for PM2.5 forecasting. Particularly noteworthy are the remarkable capabilities of deep learning techniques, notably CNN and LSTM, in discerning intricate correlations within environmental datasets. These strategies have the potential to address the urgent problem of air pollution and lessen its detrimental impact on both human health and the environment by increasing the precision of air quality predictions.https://www.itm-conferences.org/articles/itmconf/pdf/2024/11/itmconf_icaetm2024_01012.pdfair quality monitoringair quality indexmachine learningdeep learning regression
spellingShingle Das Shuvendu
Singh Karanvir
Kaur Kiranjeet
Air Quality Prediction in Beijing: Machine and Deep Learning Analysis
ITM Web of Conferences
air quality monitoring
air quality index
machine learning
deep learning regression
title Air Quality Prediction in Beijing: Machine and Deep Learning Analysis
title_full Air Quality Prediction in Beijing: Machine and Deep Learning Analysis
title_fullStr Air Quality Prediction in Beijing: Machine and Deep Learning Analysis
title_full_unstemmed Air Quality Prediction in Beijing: Machine and Deep Learning Analysis
title_short Air Quality Prediction in Beijing: Machine and Deep Learning Analysis
title_sort air quality prediction in beijing machine and deep learning analysis
topic air quality monitoring
air quality index
machine learning
deep learning regression
url https://www.itm-conferences.org/articles/itmconf/pdf/2024/11/itmconf_icaetm2024_01012.pdf
work_keys_str_mv AT dasshuvendu airqualitypredictioninbeijingmachineanddeeplearninganalysis
AT singhkaranvir airqualitypredictioninbeijingmachineanddeeplearninganalysis
AT kaurkiranjeet airqualitypredictioninbeijingmachineanddeeplearninganalysis