Seamless integration of convolutional and back-propagation neural networks for regional multi-step-ahead PM2.5 forecasting

Kow, Pu-Yun; Wang, Yi-Shin; Zhou, Yanlai; Kao, I-Feng; Issermann, Maikel; Chang, Li-Chiu; Chang, Fi‐John

doi:10.1016/j.jclepro.2020.121285

Cited by 78 publications

(21 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Combined with feature extraction based on the ensemble empirical mode decomposition approach, Bai et al applied the LSTM approach to PM 2.5 concentration prediction [22]. The hybrid model based on a BP neural network and convolutional neural network can make accurate PM 2.5 predictions in [41]. A hybrid prediction model using land use regression and a chemical transport model can be found in [42].…”

Section: Related Workmentioning

confidence: 99%

A Simple Dendritic Neural Network Model-Based Approach for Daily PM2.5 Concentration Prediction

Song

Tang

et al. 2021

Electronics

View full text Add to dashboard Cite

Air pollution in cities has a massive impact on human health, and an increase in fine particulate matter (PM2.5) concentrations is the main reason for air pollution. Due to the chaotic and intrinsic complexities of PM2.5 concentration time series, it is difficult to utilize traditional approaches to extract useful information from these data. Therefore, a neural model with a dendritic mechanism trained via the states of matter search algorithm (SDNN) is employed to conduct daily PM2.5 concentration forecasting. Primarily, the time delay and embedding dimensions are calculated via the mutual information-based method and false nearest neighbours approach to train the data, respectively. Then, the phase space reconstruction is performed to map the PM2.5 concentration time series into a high-dimensional space based on the obtained time delay and embedding dimensions. Finally, the SDNN is employed to forecast the PM2.5 concentration. The effectiveness of this approach is verified through extensive experimental evaluations, which collect six real-world datasets from recent years. To the best of our knowledge, this study is the first attempt to utilize a dendritic neural model to perform real-world air quality forecasting. The extensive experimental results demonstrate that the SDNN offers very competitive performance relative to the latest prediction techniques.

show abstract

Section: Related Workmentioning

confidence: 99%

A Simple Dendritic Neural Network Model-Based Approach for Daily PM2.5 Concentration Prediction

Song

Tang

et al. 2021

Electronics

View full text Add to dashboard Cite

show abstract

“…Xie et al [16] applied a manifold learning-locally linear embedding method to reconstruct low-dimensional meteorological factors as the DBN's input for daily single-step PM 2.5 forecasting in Chongqing, China. Kow et al [17] utilized CNN and backpropagation (CNN-BP) to extract the hidden features of multi-sites in Korea with multivariate factors, including temperature, humidity, CO, and PM 10 , for multi-step and multi-sites hourly PM 2.5 forecasting. Park et al [18] applied CNN with nearby locations' meteorological data for daily single-step PM 2.5 forecasting.…”

Section: Introductionmentioning

confidence: 99%

Accurate Multi-Site Daily-Ahead Multi-Step PM2.5 Concentrations Forecasting Using Space-Shared CNN-LSTM

Shao¹,

Kim²

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Accurate multi-step PM 2.5 (particulate matter with diameters ≤ 2.5 um) concentration prediction is critical for humankinds' health and air population management because it could provide strong evidence for decisionmaking. However, it is very challenging due to its randomness and variability. This paper proposed a novel method based on convolutional neural network (CNN) and long-short-term memory (LSTM) with a space-shared mechanism, named space-shared CNN-LSTM (SCNN-LSTM) for multi-site dailyahead multi-step PM 2.5 forecasting with self-historical series. The proposed SCNN-LSTM contains multi-channel inputs, each channel corresponding to one-site historical PM 2.5 concentration series. In which, CNN and LSTM are used to extract each site's rich hidden feature representations in a stack mode. Especially, CNN is to extract the hidden short-time gap PM 2.5 concentration patterns; LSTM is to mine the hidden features with long-time dependency. Each channel extracted features are merged as the comprehensive features for future multi-step PM 2.5 concentration forecasting. Besides, the space-shared mechanism is implemented by multi-loss functions to achieve space information sharing. Therefore, the final features are the fusion of short-time gap, long-time dependency, and space information, which enables forecasting more accurately. To validate the proposed method's effectiveness, the authors designed, trained, and compared it with various leading methods in terms of RMSE, MAE, MAPE, and R 2 on four real-word PM 2.5 data sets in Seoul, South Korea. The massive experiments proved that the proposed method could accurately forecast multi-site multi-step PM 2.5 concentration only using self-historical PM 2.5 concentration time series and running once. Specifically, the proposed method obtained averaged RMSE of 8.05, MAE of 5.04, MAPE of 23.96%, and R 2 of 0.7 for four-site daily ahead 10-hour PM 2.5 concentration forecasting.

show abstract

“…Xulin Liu et al [10] established CNN-Seq2seq to predict PM 2.5 concentration within an hour, and the effect was better than the combined Seq2seq model of a machine learning model and non-CNN extracting variable features. Kow et al [11] proposed that CNN-BP can adequately handle heterogeneous inputs with large time lags, cope with the curse of dimensionality, and achieve multiregion simultaneous multistep prediction of PM 2.5 concentration; the prediction performance is better than the BPNN, random forest, and LSTM models. To achieve a grid format prediction of PM 2.5 concentration, Guo et al [12] established a ConvLSTM deep neural network model using a convolution module to extract spatial features along with LSTM extracting time features.…”

Section: Introductionmentioning

confidence: 99%

Prediction of PM2.5 Concentration Based on the LSTM-TSLightGBM Variable Weight Combination Model

2021

View full text Add to dashboard Cite

PM2.5 is one of the main pollutants that cause air pollution, and high concentrations of PM2.5 seriously threaten human health. Therefore, an accurate prediction of PM2.5 concentration has great practical significance for air quality detection, air pollution restoration, and human health. This paper uses the historical air quality concentration data and meteorological data of the Beijing Olympic Sports Center as the research object. This paper establishes a long short-term memory (LSTM) model with a time window size of 12, establishes a T-shape light gradient boosting machine (TSLightGBM) model that uses all information in the time window as the next period of prediction input, and establishes a LSTM-TSLightGBM model pair based on an optimal weighted combination method. PM2.5 hourly concentration is predicted. The prediction results on the test set show that the mean squared error (MAE), root mean squared error (RMSE), and symmetric mean absolute percentage error (SMAPE) of the LSTM-TSLightGBM model are 11.873, 22.516, and 19.540%, respectively. Compared with LSTM, TSLightGBM, the recurrent neural network (RNN), and other models, the LSTM-TSLightGBM model has a lower MAE, RMSE, and SMAPE, and higher prediction accuracy for PM2.5 and better goodness-of-fit.

show abstract

Seamless integration of convolutional and back-propagation neural networks for regional multi-step-ahead PM2.5 forecasting

Cited by 78 publications

References 55 publications

A Simple Dendritic Neural Network Model-Based Approach for Daily PM2.5 Concentration Prediction

A Simple Dendritic Neural Network Model-Based Approach for Daily PM2.5 Concentration Prediction

Accurate Multi-Site Daily-Ahead Multi-Step PM2.5 Concentrations Forecasting Using Space-Shared CNN-LSTM

Prediction of PM2.5 Concentration Based on the LSTM-TSLightGBM Variable Weight Combination Model

Contact Info

Product

Resources

About