A new hybrid prediction model of PM2.5 concentration based on secondary decomposition and optimized extreme learning machine

Yang, Huirong; Zhao, Junlin; Li, Guohui

doi:10.1007/s11356-022-20375-y

Cited by 13 publications

(2 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yang et al exploited a new hybrid prediction model for PM2.5 concentration prediction. The original data is decomposed with the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method, and extreme learning machine optimized by chimp optimization algorithm is developed for better prediction performance (Yang et al 2022 ). Zhang et al proposed a hybrid intelligent model to predict PM2.5 concentration using CEEMDAN method and fuzzy c-means (FCM) clustering algorithm (Zhang et al 2022 ).…”

Section: Introductionmentioning

confidence: 99%

PM2.5 concentration prediction using weighted CEEMDAN and improved LSTM neural network

Zhang

Liu

Feng

et al. 2023

Environ Sci Pollut Res

View full text Add to dashboard Cite

As the core of pollution prevention and management, accurate PM2.5 concentration prediction is crucial for human survival. However, due to the nonstationarity and nonlinearity of PM2.5 concentration data, the accurate prediction for PM2.5 concentration remains a challenge. In this study, a PM2.5 concentration prediction method using weighted complementary ensemble empirical mode decomposition with adaptive noise (WCEEMDAN) and improved long and short-term memory (ILSTM) neural network is proposed. Firstly, a novel WCEEMDAN method is proposed to correctly identify the non-stationary and non-linear characteristics and divide the PM2.5 sequences into various layers. Through the correlation analysis with PM2.5 data, these sub-layers are given different weights. Secondly, the adaptive mutation particle swarm optimization (AMPSO) algorithm is developed to obtain the main hyperparameters of the long short-term memory network (LSTM) neural network, improving the prediction accuracy of PM2.5 concentration. The optimization convergence speed and accuracy are improved by adjusting the inertia weight and introducing the mutation mechanism to enhance the global optimization ability. Finally, three groups of PM2.5 concentration data are utilized to verify the effectiveness of the proposed model. Compared with other methods, the experimental results demonstrate the superiority of the proposed model. The source code can be downloaded from https://github.com/zhangli190227/WCEENDAM-ILSTM .

show abstract

Section: Introductionmentioning

confidence: 99%

PM2.5 concentration prediction using weighted CEEMDAN and improved LSTM neural network

Zhang

Liu

Feng

et al. 2023

Environ Sci Pollut Res

View full text Add to dashboard Cite

show abstract

“…Empirical Mode Decomposition (EMD) proposed by Huang et al is a data processing method that decomposes signals into different time and frequency domains, and then reduces nonlinearity in the signal 16 , 17 . However, due to the modal aliasing problem of EMD, some scholars try to make predictions with EEMD to process data 18 , 19 . In addition, Yang et al used decomposition methods such as EEMD to reduce the nonlinearity of the data by using signal decomposition to deepen their understanding of the data 20 .…”

mentioning

confidence: 99%

PM2.5 concentration prediction based on EEMD-ALSTM

Liu,

Ji,

Wang

2024

Sci Rep

View full text Add to dashboard Cite

The concentration prediction of PM2.5 plays a vital role in controlling the air and improving the environment. This paper proposes a prediction model (namely EEMD-ALSTM) based on Ensemble Empirical Mode Decomposition (EEMD), Attention Mechanism and Long Short-Term Memory network (LSTM). Through the combination of decomposition and LSTM, attention mechanism is introduced to realize the prediction of PM2.5 concentration. The advantage of EEMD-ALSTM model is that it decomposes and combines the original data using the method of ensemble empirical mode decomposition, reduces the high nonlinearity of the original data, and Specially reintroduction the attention mechanism, which enhances the extraction and retention of data features by the model. Through experimental comparison, it was found that the EEMD-ALSTM model reduced its MAE and RMSE by about 15% while maintaining the same R2 correlation coefficient, and the stability of the model in the prediction process was also improved significantly.

show abstract

State-of-art in modelling particulate matter (PM) concentration: a scoping review of aims and methods

Gianquintieri,

Oxoli,

Caiani

et al. 2024

Environ Dev Sustain

View full text Add to dashboard Cite

Air pollution is the one of the most significant environmental risks to health worldwide. An accurate assessment of population exposure would require a continuous distribution of measuring ground-stations, which is not feasible. Therefore, significant efforts are spent in implementing air-quality models. However, a complex scenario emerges, with the spread of many different solutions, and a consequent struggle in comparison, evaluation and replication, hindering the definition of the state-of-art. Accordingly, aim of this scoping review was to analyze the latest scientific research on air-quality modelling, focusing on particulate matter, identifying the most widespread solutions and trying to compare them. The review was mainly focused, but not limited to, machine learning applications. An initial set of 940 results published in 2022 were returned by search engines, 142 of which resulted significant and were analyzed. Three main modelling scopes were identified: correlation analysis, interpolation and forecast. Most of the studies were relevant to east and south-east Asia. The majority of models were multivariate, including (besides ground stations) meteorological information, satellite data, land use and/or topography, and more. 232 different algorithms were tested across studies (either as single-blocks or within ensemble architectures), of which only 60 were tested more than once. A performance comparison showed stronger evidence towards the use of Random Forest modelling, in particular when included in ensemble architectures. However, it must be noticed that results varied significantly according to the experimental set-up, indicating that no overall best solution can be identified, and a case-specific assessment is necessary.

show abstract

A new hybrid prediction model of PM2.5 concentration based on secondary decomposition and optimized extreme learning machine

Cited by 13 publications

References 57 publications

PM2.5 concentration prediction using weighted CEEMDAN and improved LSTM neural network

PM2.5 concentration prediction using weighted CEEMDAN and improved LSTM neural network

PM2.5 concentration prediction based on EEMD-ALSTM

State-of-art in modelling particulate matter (PM) concentration: a scoping review of aims and methods

Contact Info

Product

Resources

About