Air Pollution Concentration Forecast Method Based on the Deep Ensemble Neural Network

Guo, Canyang; Liu, Genggeng; Chen, Chi‐Hua

doi:10.1155/2020/8854649

Cited by 26 publications

(12 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The learning rate is set to 0.001, and the epochs are set to 300 using Adam Optimizer. The adaptive moment estimation (Adam) algorithm is used to replace stochastic gradient descent (SGD) to update the weights to get higher accuracy (Guo et al, 2020 ). The error in forecasting the concentrations of PM 2.5 and PM 10 during the complete lockdown (case study 1) and partial lockdown (case study 2) using this deep TL model, TLS-BDLSTM, is estimated.…”

Section: Resultsmentioning

confidence: 99%

Prediction and assessment of the impact of COVID-19 lockdown on air quality over Kolkata: a deep transfer learning approach

Dutta

Pal

2022

Environ Monit Assess

View full text Add to dashboard Cite

The present study focuses on the prediction and assessment of the impact of lockdown because of coronavirus pandemic on the air quality during three different phases, viz., normal periods (1 January 2018–23 March 2020), complete lockdown (24 March 2020–31 May 2020), and partial lockdown (1 June 2020–30 September 2020). We identify the most important air pollutants influencing the air quality of Kolkata during three different periods using Random Forest, a tree-based machine learning (ML) algorithm. It is found that the ambient air quality of Kolkata is mainly affected with the aid of particulate matter or PM (PM 10 and PM 2.5 ). However, the effect of the lockdown is most prominent on PM 2.5 which spreads in the air of Kolkata due to diesel-driven vehicles, domestic and commercial combustion activities, road dust, and open burning. To predict urban PM 2.5 and PM 10 concentrations 24 h in advance, we use a deep learning (DL) model, namely, stacked-bidirectional long short-term memory (stacked-BDLSTM). The model is trained during the normal periods, and it shows the superiority over some supervised ML models, like support vector machine, K-nearest neighbor classifier, multilayer perceptron, long short-term memory, and statistical time series forecasting model autoregressive integrated moving average. This pre-trained stacked-BDLSTM is applied to predict the concentrations of PM 2.5 and PM 10 during the pandemic situation of two cases, viz., complete lockdown and partial lockdown using a deep model-based transfer learning (TL) approach (TLS-BDLSTM). Transfer learning aims to utilize the information gained from one problem to improve the predictive performance of a learning model for a different but related problem. Our work helps to demonstrate how TL is useful when there is a scarcity of data during the COVID-19 pandemic regarding the drastic change in concentration of pollutants. The results reveal the best prediction performance of TLS-BDLSTM with a lead time of 24 h as compared to some well-known traditional ML and statistical models and the pre-trained stacked-BDLSTM. The prediction is then validated using the real-time data obtained during the complete lockdown due to COVID second wave (16 May–15 June 2021) with different time steps, e.g., 24 h, 48 h, 72 h, and 96–120 h. TLS-BDLSTM involving transfer learning is seen to outperform the said comparing methods in modeling the long-term temporal dependency of multivariate time series data and boost the forecast efficiency not only in single step, but also in multiple steps. The proposed methodologies are effective, consistent, and can be used by operational organizations to utilize in monitoring and management of air quality.

show abstract

Section: Resultsmentioning

confidence: 99%

Prediction and assessment of the impact of COVID-19 lockdown on air quality over Kolkata: a deep transfer learning approach

Dutta

Pal

2022

Environ Monit Assess

View full text Add to dashboard Cite

show abstract

“… Liu et al (2022) optimize the trajectory for digital twin robots by the genetic algorithm (GA). Guo et al (2020) proposed an air pollution forecast model using a deep ensemble NN that combines the efficiency of GRU, LSTM, and recurrent neural networks (RNNs) to predict PM 2.5 concentrations which is presented.…”

Section: Related Workmentioning

confidence: 99%

Prediction and Sensitivity Analysis of CO2 Capture by Amine Solvent Scrubbing Technique Based on BP Neural Network

Chang

Huang

2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

With the rapid development of artificial intelligence, bionic algorithm has been gradually applied in various fields, and neural network has become an important and hot issue in the field of scientific research and engineering in recent years. This article proposes a BP neural network model to predict the capture ability and sensitivity of CO2 in monoethanolamine (MEA) aqueous scrubbing technique from a 2 × 1,000 MW coal-fired power plant expansion project in eastern China. The predicted values agree well with the experimental data with a satisfactory mean square root error (MSRE) ranging from 0.001945 to 0.002372, when the change in the circulation amount of MEA and the accuracy of prediction results of the back propagation neural network (BPNN) algorithm is as high as 96.6%. The sensitivity analysis results suggested that the flue gas amount has a marginal effect on the system performance, while further attention should be paid to the MEA circulation amount, which is crucial to the CO2 capture amount. The temperature profiles show the typical behavior of the reactive absorption column where a temperature bulge can be seen at the bottom of the column due to the high L/G ratio of the experimental and prediction results. The coefficients of correlation R2 with the change of MEA circulation amount, change of CO2 concentration, and steam consumption are 0.97722, 0.99801, and 0.98258, respectively. These results have demonstrated that the present study has established the BPNN algorithm as a consistent, reliable, and robust system identification tool for CO2 capture by the amine solvent scrubbing technique of operation in coal-fired power plants.

show abstract

“…Another RNN based model was proposed in [24] to forecast the concentration level of PM 10 at different future time steps (6, 12, and 24 h). On the other hand, Guo et al [25] proposed a feature engineering pipeline as well as a deep ensemble network algorithm which combines RNN, LSTM, and GRU networks to predict the PM 2.5 concentration of the next hour. During the data analysis step, the authors used the Pearson correlation coefficient to evaluate the correlation of PM 2.5 with meteorological data, season data, and time stamp data.…”

Section: Introductionmentioning

confidence: 99%

Attention-Based Distributed Deep Learning Model for Air Quality Forecasting

et al. 2022

View full text Add to dashboard Cite

Air quality forecasting has become an essential factor in facilitating sustainable development worldwide. Several countries have implemented monitoring stations to collect air pollution particle data and meteorological information using parameters such as hourly timespans. This research focuses on unravelling a new framework for air quality prediction worldwide and features Busan, South Korea as its model city. The paper proposes the application of an attention-based convolutional BiLSTM autoencoder model. The proposed deep learning model has been trained on a distributed framework, referred to data parallelism, to forecast the intensity of particle pollution ( and ). The algorithm automatically learns the intrinsic correlation among the particle pollution in different locations. Each location’s meteorological and traffic data is extensively exploited to improve the model’s performance. The model has been trained using air quality particle data and car traffic information. The traffic information is obtained by a device which counts cars passing a specific area through the YOLO algorithm, and then sends the data to a stacked deep autoencoder to be encoded alongside the meteorological data before the final prediction. In addition, multiple one-dimensional CNN layers are used to obtain the local spatial features jointly with a stacked attention-based BiLSTM layer to figure out how air quality particles are correlated in space and time. The evaluation of the new attention-based convolutional BiLSTM autoencoder model was derived from data collected and retrieved from comprehensive experiments conducted in South Korea. The results not only show that the framework outperforms the previous models both on short- and long-term predictions but also indicate that traffic information can improve the accuracy of air quality forecasting. For instance, during prediction, the proposed attention-based model obtained the lowest MAE (5.02 and 22.59, respectively, for short-term and long-term prediction), RMSE (7.48 and 28.02) and SMAPE (17.98 and 39.81) among all the models, which indicates strong accuracy between observed and predicted values. It was also found that the newly proposed model had the lowest average training time compared to the baseline algorithms. Furthermore, the proposed framework was successfully deployed in a cloud server in order to provide future air quality information in real time and when needed.

show abstract

Air Pollution Concentration Forecast Method Based on the Deep Ensemble Neural Network

Cited by 26 publications

References 27 publications

Prediction and assessment of the impact of COVID-19 lockdown on air quality over Kolkata: a deep transfer learning approach

Prediction and assessment of the impact of COVID-19 lockdown on air quality over Kolkata: a deep transfer learning approach

Prediction and Sensitivity Analysis of CO2 Capture by Amine Solvent Scrubbing Technique Based on BP Neural Network

Attention-Based Distributed Deep Learning Model for Air Quality Forecasting

Contact Info

Product

Resources

About