MGC-LSTM: a deep learning model based on graph convolution of multiple graphs for PM2.5 prediction

Liu, Xia; Li, Weide

doi:10.1007/s13762-022-04553-6

Cited by 8 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 48 ] 2022 Santiago, Chile LSTM H/S/T+1 9.85 4.40 - 0.74 Liu et al. [ 71 ] 2022 Jing-Jin-Ji Region, China MGC-LSTM H/S/T+1 2.91 2.16 12.96 - Hu et al. [ 63 ] 2022 Beijing, China Conv1D-LSTM H/S/T+1 20.76 11.20 - 0.96 Wu et al.…”

Section: Methods Reviewmentioning

confidence: 99%

Deep-learning architecture for PM2.5 concentration prediction: A review

Zhou,

Wang,

Zhu

et al. 2024

Environmental Science and Ecotechnology

View full text Add to dashboard Cite

Section: Methods Reviewmentioning

confidence: 99%

Deep-learning architecture for PM2.5 concentration prediction: A review

Zhou,

Wang,

Zhu

et al. 2024

Environmental Science and Ecotechnology

View full text Add to dashboard Cite

“…LSTM is a deep learning method, a variant of RNN. Compared to ordinary RNN, LSTM performs better in longer sequences, effectively solving the gradient explosion and vanishing problems generated by RNN [49], and it is widely used in time-series prediction. LSTM is divided into three stages internally, allowing control of information through the forget gate, the input gate, and the output gate.…”

Section: Long Short-term Memory (Lstm)mentioning

confidence: 99%

Air Quality Index Prediction in Six Major Chinese Urban Agglomerations: A Comparative Study of Single Machine Learning Model, Ensemble Model, and Hybrid Model

Zhang,

Duan,

Sun

et al. 2023

Atmosphere

View full text Add to dashboard Cite

Air pollution is a hotspot of wide concern in Chinese cities. With the worsening of air pollution, urban agglomerations face an increasingly complex environment for air quality monitoring, hindering sustainable and high-quality development in China. More effective methods for predicting air quality are urgently needed. In this study, we employed seven single models and ensemble learning algorithms and constructed a hybrid learning algorithm, the LSTM-SVR model, totaling eight machine learning algorithms, to predict the Air Quality Index in six major urban agglomerations in China. We comprehensively compared the predictive performance of the eight algorithmic models in different urban agglomerations. The results reveal that, in areas with higher levels of air pollution, the situation for model prediction is more complicated, leading to a decline in predictive accuracy. The constructed hybrid model LSTM-SVR demonstrated the best predictive performance, followed by the ensemble model RF, both of which effectively enhanced the predictive accuracy in heavily polluted areas. Overall, the predictive performance of the hybrid and ensemble models is superior to that of the single-model prediction methods. This study provides AI technological support for air quality prediction in various regions and offers a more comprehensive discussion of the performance differences between different types of algorithms, contributing to the practical application of air pollution control.

show abstract

“…Eslami et al (2020) used a deep convolutional neural network to predict the hourly O 3 across 25 observation stations over Seoul, South Korea. Xiao et al (2020) and Liu and Li (2022) proposed two deep learning methods based on the Long-Short Term Memory (LSTM) neural network to predict the PM2.5 concentrations in the Beijing-Tianjin-Hebei region of China. Yang et al (2021) explored the traffic impacts on air quality by a random forest model under the pandemic scenario in Los Angeles.…”

Section: Introductionmentioning

confidence: 99%

Machine learning-based ozone and PM2.5 forecasting: Application to multiple AQS sites in the Pacific Northwest

et al. 2023

View full text Add to dashboard Cite

Air quality in the Pacific Northwest (PNW) of the U.S has generally been good in recent years, but unhealthy events were observed due to wildfires in summer or wood burning in winter. The current air quality forecasting system, which uses chemical transport models (CTMs), has had difficulty forecasting these unhealthy air quality events in the PNW. We developed a machine learning (ML) based forecasting system, which consists of two components, ML1 (random forecast classifiers and multiple linear regression models) and ML2 (two-phase random forest regression model). Our previous study showed that the ML system provides reliable forecasts of O3 at a single monitoring site in Kennewick, WA. In this paper, we expand the ML forecasting system to predict both O3 in the wildfire season and PM2.5 in wildfire and cold seasons at all available monitoring sites in the PNW during 2017–2020, and evaluate our ML forecasts against the existing operational CTM-based forecasts. For O3, both ML1 and ML2 are used to achieve the best forecasts, which was the case in our previous study: ML2 performs better overall (R2 = 0.79), especially for low-O3 events, while ML1 correctly captures more high-O3 events. Compared to the CTM-based forecast, our O3 ML forecasts reduce the normalized mean bias (NMB) from 7.6 to 2.6% and normalized mean error (NME) from 18 to 12% when evaluating against the observation. For PM2.5, ML2 performs the best and thus is used for the final forecasts. Compared to the CTM-based PM2.5, ML2 clearly improves PM2.5 forecasts for both wildfire season (May to September) and cold season (November to February): ML2 reduces NMB (−27 to 7.9% for wildfire season; 3.4 to 2.2% for cold season) and NME (59 to 41% for wildfires season; 67 to 28% for cold season) significantly and captures more high-PM2.5 events correctly. Our ML air quality forecast system requires fewer computing resources and fewer input datasets, yet it provides more reliable forecasts than (if not, comparable to) the CTM-based forecast. It demonstrates that our ML system is a low-cost, reliable air quality forecasting system that can support regional/local air quality management.

show abstract

MGC-LSTM: a deep learning model based on graph convolution of multiple graphs for PM2.5 prediction

Cited by 8 publications

References 30 publications

Deep-learning architecture for PM2.5 concentration prediction: A review

Deep-learning architecture for PM2.5 concentration prediction: A review

Air Quality Index Prediction in Six Major Chinese Urban Agglomerations: A Comparative Study of Single Machine Learning Model, Ensemble Model, and Hybrid Model

Machine learning-based ozone and PM2.5 forecasting: Application to multiple AQS sites in the Pacific Northwest

Contact Info

Product

Resources

About