Machine learning algorithms to forecast air quality: a survey

Núñez, Manuel; Merayo, Mercedes G.; Núñez, Manuel

doi:10.1007/s10462-023-10424-4

Cited by 77 publications

(18 citation statements)

References 168 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, all three methods of clustering presented in [2,3] and this study can be applied to the immensely popular task of forecasting air pollution in Beijing [87][88][89]. Unsupervised machine learning holds promise for addressing similar problems in meteorology, pollution control, and other environmental sciences [90].…”

Section: Prelude and Performance: Unsupervised Machine Learning And T...mentioning

confidence: 94%

Hints of Earlier and Other Creation: Unsupervised Machine Learning in Financial Time-Series Analysis

Chen

Agiropoulos

2023

Itise 2023

View full text Add to dashboard Cite

show abstract

Section: Prelude and Performance: Unsupervised Machine Learning And T...mentioning

confidence: 94%

Hints of Earlier and Other Creation: Unsupervised Machine Learning in Financial Time-Series Analysis

Chen

Agiropoulos

2023

Itise 2023

View full text Add to dashboard Cite

show abstract

“…Air quality assessment has heavily relied on conventional methods for an extensive period. These traditional methodologies to air quality prediction involve using mathematical and statistical techniques [14]. They typically start with designing a physical model and encoding data using mathematical equations.…”

Section: Literature Surveymentioning

confidence: 99%

EcoSense: A Revolution in Urban Air Quality Forecasting for Smart Cities

Chatterjee,

Thara,

et al. 2024

Preprint

View full text Add to dashboard Cite

The Smart City (SC) framework, renowned for enhancing lives and bolstering public safety, encounters challenges due to its reliance on IoT devices, contributing to electronic waste and resource consumption. Integrating weather research and a weather-smart grid into the SC framework becomes crucial to address these issues and safeguard the environment and residents’ well-being. This study proposes a novel approach, EcoSense: A Revolution in Urban Air Quality Forecasting for Smart Cities, which incorporates Bi-directional Stacked LSTM with a Weather-Smart Grid (BlaSt). BlaSt utilizes temporal aggregation and lagged features to capture temporal dependencies and trends in air quality data, considering air pollutants and meteorological factors for future air pollutant concentration prediction. The model is designed for 1-hour prediction intervals and outperforms traditional methods by leveraging feature attribute values, enhancing accuracy, and reducing computational complexity. Experimental results demonstrate the improved accuracy and computational efficiency of the BlaSt model compared to conventional models. Additionally, it effectively handles extensive air quality data and exhibits promising predictive capabilities for future data.

show abstract

“…The authors found that there were more studies focused on pollutants such as O 3 , NO 2 , PM 10 , and PM 2.5 , while fewer studies covered CAQI prediction. We refer interested readers to a comprehensive review [20] of 155 papers that provides a detailed analysis of air quality prediction using ML techniques.…”

Section: Related Workmentioning

confidence: 99%

Hybrid LSTM Model to Predict the Level of Air Pollution in Montenegro

Ratković,

Kovač,

Simeunović

2023

Applied Sciences

View full text Add to dashboard Cite

Air pollution is a critical environmental concern that poses significant health risks and affects multiple aspects of human life. ML algorithms provide promising results for air pollution prediction. In the existing scientific literature, Long Short-Term Memory (LSTM) predictive models, as well as their combination with other statistical and machine learning approaches, have been utilized for air pollution prediction. However, these combined algorithms may not always provide suitable results due to the stochastic nature of the factors that influence air pollution, improper hyperparameter configurations, or inadequate datasets and data characterized by great variability and extreme dispersion. The focus of this paper is applying and comparing the performance of Support Vector Machine and hybrid LSTM regression models for air pollution prediction. To identify optimal hyperparameters for the LSTM model, a hybridization with the Genetic Algorithm is proposed. To mitigate the risk of overfitting, the bagging technique is employed on the best LSTM model. The proposed predicitive model aims to determine the Common Air Quality Index level for the next hour in Niksic, Montenegro. With the hybridization of the LSTM algorithm and by applying the bagging technique, our approach aims to significantly enhance the accuracy and reliability of hourly air pollution prediction. The major contribution of this paper is in the application of advanced machine learning analysis and the combination of the LSTM, Genetic Algorithm, and bagging techniques, which have not been previously employed in the analysis of air pollution in Montenegro. The proposed model will be made available to interested management structures, local governments, national entities, or other relevant institutions, empowering them to make effective pollution level predictions and take appropriate measures.

show abstract

Machine learning algorithms to forecast air quality: a survey

Cited by 77 publications

References 168 publications

Hints of Earlier and Other Creation: Unsupervised Machine Learning in Financial Time-Series Analysis

Hints of Earlier and Other Creation: Unsupervised Machine Learning in Financial Time-Series Analysis

EcoSense: A Revolution in Urban Air Quality Forecasting for Smart Cities

Hybrid LSTM Model to Predict the Level of Air Pollution in Montenegro

Contact Info

Product

Resources

About