Analysis and accurate prediction of ambient PM2.5 in China using Multi-layer Perceptron

Feng, Rui; Gao, Han; Luo, Kun; Fan, Jianren

doi:10.1016/j.atmosenv.2020.117534

Cited by 34 publications

(32 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to its capability of self-learning and self-adapting, more research on this algorithm has been successfully implemented to solve real-world problems. It also able to perform more efficient and accurate numerous classification [9−11], prediction [12,13] and many more compared to other classification techniques [14].…”

Section: Introductionmentioning

confidence: 99%

Students’ learning habit factors during COVID-19 pandemic using multilayer perceptron (MLP)

Mangshor¹,

Ibrahim²,

Sabri³

et al. 2021

IJATEE

View full text Add to dashboard Cite

Rapid dissemination of coronavirus disease 2019 (COVID-19) across the globe has necessitated the introduction of social distance interventions to slow the spread of the disease. Online learning has become essential, considering the implications of this virus to be spread among the students during physical classes. Hence, educational institutions have shifted the traditional physical classes to online classes. Due to this implementation worldwide, a study on student learning habits is crucial to analyse students learning habits as it is one of the main factors that affecting students' performance in learning. Fifteen independent variables as inputs to one of the well-known Artificial Neural Network algorithms, Multilayer Perceptron (ANN-MLP) has been used to investigate the student's learning habit factors during the COVID-19 pandemic. Through analysing original survey data from 420 secondary students (Grade 6-12) in Hanoi shows that the ANN-MLP model is stable for both ANN-MLP optimization algorithms which are for Adjusted Normalized, to be concise. The hours spend for self-learning before COVID-19 is observed to be the most influential factors of student's learning habit during COVID-19 pandemic. Moreover, the promising Sum of Squares Error (SSE) and Relative Error (RE) values obtained signify that the ANN-MLP model is appropriate in identifying the student's learning habit factors during COVID-19 pandemic.

show abstract

Section: Introductionmentioning

confidence: 99%

Students’ learning habit factors during COVID-19 pandemic using multilayer perceptron (MLP)

Mangshor¹,

Ibrahim²,

Sabri³

et al. 2021

IJATEE

View full text Add to dashboard Cite

show abstract

“…Several previous works investigated PM in the megacities of China via outdoor observation 17 – 19 . Machine learning, orchestrated for developing algorithms automatically from large datasets, removes the need for an air pollution emission inventory which is a linchpin for conventional atmospheric models, thus becoming a more flexible approach 20 – 23 . Compared to inventory-predicated air quality models, machine learning offers an alternative and more accurate method to interpret air pollutant concentration, which now is a popular topic in atmospheric research field.…”

Section: Introductionmentioning

confidence: 99%

Exploring the spatial heterogeneity and temporal homogeneity of ambient PM10 in nine core cities of China

Feng

Zhou

Shi

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

We focus on the causes of fluctuations in wintertime PM10 in nine regional core cities of China using two machine learning models, Random Forest (RF) and Recurrent Neural Network (RNN). RF and RNN both show high performance in predicting hourly PM10 using only gaseous air pollutants (SO2, NO2 and CO) as inputs, showing the predominance of the secondary inorganic aerosol and implying the existence of thermodynamic equilibrium between gaseous air pollutants and PM10. Also, we find the following results. The correlation of gaseous air pollutants and PM10 were more relevant than that of meteorological conditions and PM10. CO was the predominant factor for PM10 in the Beijing-Tianjin-Hebei Plain and the Yangtze River Delta while SO2 and NO2 were also important features for PM10 in the Pearl River Delta and Sichuan Basin. The spatial heterogeneity and temporal homogeneity of PM10 in China are revealed. The long-range transported PM10 was substantiated to be insignificant, except in the sandstorms. The severity of PM10 was attributable to the lopsided shift of thermodynamic equilibrium and the phenology of indigenous flora.

show abstract

“…A number of prior research works have forecasted air-quality variables (Huang & Kuo, 2018;Zhao et al, 2019;Feng et al, 2020). For example, Huang and Kuo (2018) proposed a deep Convolution Neural Network-LSTM model that was specifically designed for sequence prediction problems to forecast particulate matter concentrations of equal to or less than 2.5 μm (PM 2.5 ).…”

Section: Introductionmentioning

confidence: 99%

“…Also, most of these models only forecasted one timestep ahead in time. Though, Feng et al (2020) proposed a model which forecasted multiple-step ahead in time, but they only investigated a multi-layer perceptron (MLP) model. Furthermore, an investigation of ensemble models via calibration of individual models has also been less explored.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modelling Particulate Matter Using Multivariate and Multistep Recurrent Neural Networks

Saini

Chaturvedi

Dutt

2021

Front. Environ. Sci.

View full text Add to dashboard Cite

Air quality is a major problem in the world, having severe health implications. Long-term exposure to poor air quality causes pulmonary and cardiovascular diseases. Several studies have also found that deteriorating air quality also causes substantial economic losses. Thus, techniques that can forecast air quality with higher accuracy may help reduce health and economic consequences. Prior research has utilized state-of-the-art artificial neural network and recurrent neural network models for forecasting air quality. However, a comprehensive investigation of different architectures of recurrent neural network, especially LSTMs and ensemble techniques, has been less explored. Also, there have been less explorations of long-term air quality forecasts via these methods exists. This research proposes the development and calibration of recurrent neural network models and their ensemble, which can forecast air quality in terms of PM2.5 concentration 6 hours ahead in time. For forecasting air quality, a vanilla-LSTM, a stack-LSTM, a bidirectional-LSTM, a CNN-LSTM, and an ensemble of individual LSTM models were trained on the UCI Machine Learning Beijing dataset. Data were split into two parts, where 80% of data were used for training the models, while the remaining 20% were used for validating the models. For comparative analysis, four regression losses were calculated, namely root mean squared error, mean absolute percentage error, mean absolute error and Pearson’s correlation coefficient. Results revealed that among all models, the ensemble model performed the best in predicting the PM2.5 concentrations. Furthermore, the ensemble model outperformed other models reported in literature by a long margin. Among the individual models, the bidirectional-LSTM performed the best. We highlight the implications of this research on long-term forecasting of air quality via recurrent and ensemble techniques.

show abstract

Analysis and accurate prediction of ambient PM2.5 in China using Multi-layer Perceptron

Cited by 34 publications

References 97 publications

Students’ learning habit factors during COVID-19 pandemic using multilayer perceptron (MLP)

Students’ learning habit factors during COVID-19 pandemic using multilayer perceptron (MLP)

Exploring the spatial heterogeneity and temporal homogeneity of ambient PM10 in nine core cities of China

Modelling Particulate Matter Using Multivariate and Multistep Recurrent Neural Networks

Contact Info

Product

Resources

About