A hybrid deep learning framework for urban air quality forecasting

Aggarwal, Apeksha; Toshniwal, Durga

doi:10.1016/j.jclepro.2021.129660

Cited by 27 publications

(13 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aggarwal and Toshniwal [113] also used LSTM-based deep learning neural network for urban air quality forecasting at a variety of locations in India for monthly time periods, and used a particle swarm optimisation of the hyperparameters to further improve the accuracy. The results of the LSTM-based neural network gave a RMSE score of 14.17 μg m −3 , which outperformed existing models such as autoregressive integrated moving average (ARIMA) [114] and radial basis function neural network (RBFNN) [115], which had an RMSE score of 24.44 μg m −3 and 44.33 μg m −3 , respectively.…”

Section: Forecasting Aimentioning

confidence: 99%

Deep learning in airborne particulate matter sensing: a review

Grant-Jacob

Mills

2022

J. Phys. Commun.

View full text Add to dashboard Cite

Airborne particulate matter pollution is a global health problem that affects people from all demographics. To reduce the impact of such pollution and enable mitigation and policy planning, quantifying individuals’ exposure to pollution is necessary. To achieve this, effective monitoring of airborne particulates is required, through monitoring of pollution hotspots and sources. Furthermore, since pollution is a global problem, which varies from urban areas to city centres, industrial facilities to inside homes, a variety of sensors might be needed. Current sensing techniques either lack species resolution on a world scale, lack real-time capabilities, or are too expensive or too large for mass deployment. However, recent work using deep learning techniques has expanded the capability of current sensors and allowed the development of new techniques that have the potential for worldwide, species specific, real-time monitoring. Here, it is proposed how deep learning can enable sensor design for the development of small, low-cost sensors for real-time monitoring of particulate matter pollution, whilst unlocking the capability for predicting future particulate events and health inference from particulates, for both individuals and the environment in general.

show abstract

Section: Forecasting Aimentioning

confidence: 99%

Deep learning in airborne particulate matter sensing: a review

Grant-Jacob

Mills

2022

J. Phys. Commun.

View full text Add to dashboard Cite

show abstract

“…Zhou et al [ 24 ] constructed a deep multi-output LSTM (DM-LSTM) model through deep learning algorithms and predicted the concentration of relevant pollutants in Taipei, Taiwan, which significantly improved the accuracy and stability of air quality forecasting. Aggarwal et al [ 25 ] proposed a hybrid model (P-LSTM) based on LSTM and particle swarm optimization(PSO) to predict the air quality collected from 15 locations in India. Experimental results show that PSO can optimize LSTM network parameters and improve prediction performance.…”

Section: Introductionmentioning

confidence: 99%

A novel encoder-decoder model based on Autoformer for air quality index prediction

Feng

Zhang

2023

PLoS ONE

View full text Add to dashboard Cite

Rapid economic development has led to increasingly serious air quality problems. Accurate air quality prediction can provide technical support for air pollution prevention and treatment. In this paper, we proposed a novel encoder-decoder model named as Enhanced Autoformer (EnAutoformer) to improve the air quality index (AQI) prediction. In this model, (a) The enhanced cross-correlation (ECC) is proposed for extracting the temporal dependencies in AQI time series; (b) Combining the ECC with the cross-stage feature fusion mechanism of CSPDenseNet, the core module CSP_ECC is proposed for improving the computational efficiency of the EnAutoformer. (c) The time series decomposition and dilated causal convolution added in the decoder module are exploited to extract the finer-grained features from the original AQI data and improve the performance of the proposed model for long-term prediction. The real-world air quality datasets collected from Lanzhou are used to validate the performance of our prediction model. The experimental results show that our EnAutoformer model can greatly improve the prediction accuracy compared to the baselines and can be used as a promising alternative for complex air quality prediction.

show abstract

“…In recent years, various deep learning models have also been successfully employed for air quality PM2.5 prediction (Liao et al, 2020;Aggarwal and Toshniwal, 2021;Saini et al, 2021;Seng et al, 2021;Zaini et al, 2021). In particular, Ragab et al, presented a method of air pollution index (AQI) prediction by means of using one-dimensional convolutional neural network (1D-CNN) and exponential adaptive gradients optimization for Klang city, in Malaysia (Ragab et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

“…At present, several hybrid deep learning framework (Chang Y.-S. et al, 2020;Aggarwal and Toshniwal, 2021;Du et al, 2021;Zhang et al, 2021) have attracted extentive attention for air quality PM2.5 forecasting. Specially, a hybrid deep learning model, based on one-dimensional CNNs (1D-CNN) and bidirectional LSTMs for spatial-temporal feature learning, was developed for air quality prediction (Du et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Temporal Difference-Based Graph Transformer Networks For Air Quality PM2.5 Prediction: A Case Study in China

Zhang

Zhao

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

Air quality PM2.5 prediction is an effective approach for providing early warning of air pollution. This paper proposes a new deep learning model called temporal difference-based graph transformer networks (TDGTN) to learn long-term temporal dependencies and complex relationships from time series PM2.5 data for air quality PM2.5 prediction. The proposed TDGTN comprises of encoder and decoder layers associated with the developed graph attention mechanism. In particular, considering the similarity of different time moments and the importance of temporal difference between two adjacent moments for air quality PM2.5prediction, we first construct graph-structured data from original time series PM2.5 data at different moments without explicit graph structure. Then we improve the self-attention mechanism with the temporal difference information, and develop a new graph attention mechanism. Finally, the developed graph attention mechanism is embedded into the encoder and decoder layers of the proposed TDGTN to learn long-term temporal dependencies and complex relationships from a graph prospective on air quality PM2.5 prediction tasks. Experiment results on two collected real-world datasets in China, such as Beijing and Taizhou PM2.5 datasets, show that the proposed method outperforms other used methods on both short-term and long-term air quality PM2.5 prediction tasks.

show abstract

A hybrid deep learning framework for urban air quality forecasting

Cited by 27 publications

References 32 publications

Deep learning in airborne particulate matter sensing: a review

Deep learning in airborne particulate matter sensing: a review

A novel encoder-decoder model based on Autoformer for air quality index prediction

Temporal Difference-Based Graph Transformer Networks For Air Quality PM2.5 Prediction: A Case Study in China

Contact Info

Product

Resources

About