The estimation of hourly PM2.5 concentrations across China based on a Spatial and Temporal Weighted Continuous Deep Neural Network (STWC-DNN)

Wang, Zhen; Li, Ruiyuan; Chen, Ziyue; Yao, Qi; Gao, Bingbo; Xu, Miaoqing; Yang, Lin; Li, Manchun; Zhou, Chenghu

doi:10.1016/j.isprsjprs.2022.05.011

Cited by 23 publications

(6 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 28 ] 2021 Jing-Jin-Ji Region, China AQSTN-GCN H/S/T+1 19.00 12.03 0.30 0.94 Wang et al. [ 36 ] 2022 China STWC-DNN H/S/T+1 12.70 - - 0.92 Wang et al. [ 23 ] 2020 Shanghai, China Sequence-to-Sequence D/S/T+7 22.32 - - 0.52 Ni et al.…”

Section: Methods Reviewmentioning

confidence: 99%

See 1 more Smart Citation

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%

“…[ 35 ] and Wang et al. [ 36 ] captured the spatial and temporal features via CNN or DNN architecture. In summary, the strengths of these models are their ability to incorporate both spatial and temporal information to make accurate predictions of PM 2.5 concentrations or air quality.…”

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

“…Wang, Hu, Huang, et al (2022) developed a STenhanced neural network to reconstruct the annual PM2.5 levels in mainland China from 2014 to 2020. Wang, Li, Chen, et al (2022) proposed a ST weighted continuous deep neural network to estimate the hourly PM2.5 concentrations across China. Guo et al (2023) utilized an adaptive model coupled with ANN and wavelet analysis to predict daily PM2.5 concentrations with remote sensing and surface observation data across Beijing, China.…”

Section: Introductionmentioning

confidence: 99%

“…Wang, Li, Chen, et al. (2022) proposed a ST weighted continuous deep neural network to estimate the hourly PM2.5 concentrations across China. Guo et al.…”

Section: Introductionmentioning

confidence: 99%

Spatiotemporal stacking method with daily‐cycle restrictions for reconstructing missing hourly PM2.5 records

Chen,

2024

Transactions in GIS

View full text Add to dashboard Cite

The reliability of hourly PM2.5 data obtained from air quality monitoring stations is compromised as a result of the missing values, thereby impeding the thorough examination of crucial information. In this paper, we present a spatiotemporal (ST) stacking machine learning (ML) method with daily‐cycle restrictions for reconstructing missing hourly PM2.5 records. First, the ST neighbors for the target station with missing values are selected at a daily scale. Subsequently, the non‐null data within the ST neighbors undergo an iterative P‐BSHADE interpolation process for re‐interpolation. Next, a stacking ML model is constructed using the re‐interpolation values and several environmental factors associated with PM2.5 as the predictors, while the observed PM2.5 is taken as the independent variable. Finally, the missing values are reconstructed by inputting the predictors into the trained stacking model. The study utilized hourly PM2.5 data in the Beijing‐Tianjin‐Hebei region as a case study to assess the effectiveness of the proposed method, using daily missing ratios of 10%, 30%, and 50%, respectively. The accuracy of the proposed method was then compared to four contemporary ST interpolation methods. The results indicate that the proposed method exhibits superior performance compared to the classical methods. Specifically, it achieves a reduction in the average root mean square error and mean absolute error by at least 40.6% and 40.1%, respectively. Additionally, the proposed method demonstrates the successful recovery of extreme values in the hourly PM2.5 records, in contrast to the classical methods which often exhibit a tendency to overestimate low values and underestimate high values. Overall, the proposed method presents a viable and efficient approach to recover missing values in the hourly PM2.5 records that demonstrate evident daily periodic patterns.

show abstract

“…Many MLP-based models were developed, but the simple MLP structures were insufficient to capture adequate information from features. The two main types of MLP updates are the combination of other statistical or machine-learning models [29][30][31] and other attempts to adjust the DNNs. A normal way to update the DNN structure is to import sequential structures into the network so that temporal or sequential information could be learned by the network.…”

Section: Introductionmentioning

confidence: 99%

PD-LL-Transformer: An Hourly PM2.5 Forecasting Method over the Yangtze River Delta Urban Agglomeration, China

Zou,

Huang,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

As the urgency of PM2.5 prediction becomes increasingly ingrained in public awareness, deep-learning methods have been widely used in forecasting concentration trends of PM2.5 and other atmospheric pollutants. Traditional time-series forecasting models, like long short-term memory (LSTM) and temporal convolutional network (TCN), were found to be efficient in atmospheric pollutant estimation, but either the model accuracy was not high enough or the models encountered certain challenges due to their own structure or some specific application scenarios. This study proposed a high-accuracy, hourly PM2.5 forecasting model, poly-dimensional local-LSTM Transformer, namely PD-LL-Transformer, by deep-learning methods, based on air pollutant data and meteorological data, and aerosol optical depth (AOD) data retrieved from the Himawari-8 satellite. This research was based on the Yangtze River Delta Urban Agglomeration (YRDUA), China for 2020–2022. The PD-LL-Transformer had three parts: a poly-dimensional embedding layer, which integrated the advantages of allocating and embedding multi-variate features in a more refined manner and combined the superiority of different temporal processing methods; a local-LSTM block, which combined the advantages of LSTM and TCN; and a Transformer encoder block. Over the test set (the whole year of 2022), the model’s R2 was 0.8929, mean absolute error (MAE) was 4.4523 µg/m3, and root mean squared error (RMSE) was 7.2683 µg/m3, showing great accuracy for PM2.5 prediction. The model surpassed other existing models upon the same tasks and similar datasets, with the help of which a PM2.5 forecasting tool with better performance and applicability could be established.

show abstract

The estimation of hourly PM2.5 concentrations across China based on a Spatial and Temporal Weighted Continuous Deep Neural Network (STWC-DNN)

Cited by 23 publications

References 41 publications

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

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

Spatiotemporal stacking method with daily‐cycle restrictions for reconstructing missing hourly PM2.5 records

PD-LL-Transformer: An Hourly PM2.5 Forecasting Method over the Yangtze River Delta Urban Agglomeration, China

Contact Info

Product

Resources

About