A Novel Air Quality Early-Warning System Based on Artificial Intelligence

Mo, Xinyue; Li, Huan; Zhi, Qu

doi:10.3390/ijerph16193505

Cited by 25 publications

(18 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to these measures, an early warning system can be established to detect respiratory disorders by tracking annual PM 10 data in the region. 41 Such a system can ensure the use of the best scientific tools to inform all those concerned about possible health exposures in a timely manner. Such a warning system can help in the planning of temporary relocation of the affected inhabitants of the region.…”

Section: Discussionmentioning

confidence: 99%

The relationship between particulate matter and childhood respiratory complaints and peak expiratory flows in Harran agricultural area

Ali-Sak¹,

Kurtuluş²,

Ocaklı³

et al. 2021

Turk J Pediatr

View full text Add to dashboard Cite

Background. In recent years, many studies have evaluated the increasing incidence of asthma and chronic respiratory diseases among children living close to rural areas with pesticide application. Pesticide exposure in 266 children (126 girls and 140 boys) in Şanlıurfa, a cotton-producing province in Turkey, was explored in this work. Four different villages spread over 40 km2 were included. Methods. Measurements of peak expiratory flow (PEF) in 266 children were conducted in late June, before intensive pesticide applications in the cotton-producing fields. The measurements were repeated for 72 of 266 children after pesticide application in late August. PEF, particulate matter with diameter less than 2.5 μm (PM 2.5 ), particulate matter with diameter less than 10 μm (PM 10 ), temperature, humidity, and wind speed were measured. Results. After pesticide application, mean PM 2.5 and PM 10 values were significantly increased compared to before pesticide application (p < 0.001 for both parameters). After pesticide exposure, nasal discharge, sneezing, burning and itching in the eyes, cough, sputum production, wheezing, shortness of breath and chest tightness were significantly increased (p < 0.001). The mean PEF value was demonstrated to decrease significantly after pesticide application (p < 0.001). Moreover, significant negative correlations were noted between PEF and PM 10 and between PEF and PM 2.5 (p < 0.001). Conclusions. Intensive pesticide application causes respiratory dysfunction and increased respiratory complaints in children living near the affected agricultural areas, and impacts quality of life adversely. The results of this work can be used to develop an early warning system and methods to prevent respiratory disorders in children residing in the study area.

show abstract

Section: Discussionmentioning

confidence: 99%

The relationship between particulate matter and childhood respiratory complaints and peak expiratory flows in Harran agricultural area

Ali-Sak¹,

Kurtuluş²,

Ocaklı³

et al. 2021

Turk J Pediatr

View full text Add to dashboard Cite

show abstract

“…Existing PM 2.5 forecasting methods mainly include statistical forecasting, numerical forecasting, and machine learning methods [5,6]. Statistical method is a forecasting method that establishes mathematical relationships between PM 2.5 concentrations and influencing factors based on historical and related data, through regression analysis, time series analysis, and other methods, without considering physicochemical processes.…”

Section: Introductionmentioning

confidence: 99%

Prediction of PM2.5 Concentration Based on Deep Learning, Multi-Objective Optimization, and Ensemble Forecast

Gao,

Mo,

2024

Sustainability

View full text Add to dashboard Cite

Accurate and stable prediction of atmospheric PM2.5 concentrations is crucial for air pollution prevention and control. Existing studies usually rely on a single model or use a single evaluation criterion in multi-model ensemble weighted forecasts, neglecting the dual needs for accuracy and stability in PM2.5 forecast. In this study, a novel ensemble forecast model is proposed that overcomes these drawbacks by simultaneously taking into account both forecast accuracy and stability. Specifically, four advanced deep learning models—Long Short-Term Memory Network (LSTM), Graph Convolutional Network (GCN), Transformer, and Graph Sample and Aggregation Network (GraphSAGE)—are firstly introduced. And then, two combined models are constructed as predictors, namely LSTM–GCN and Transformer–GraphSAGE. Finally, a combined weighting strategy is adopted to assign weights to these two combined models using a multi-objective optimization algorithm (MOO), so as to carry out more accurate and stable predictions. The experiments are conducted on the dataset from 36 air quality monitoring stations in Beijing, and results show that the proposed model achieves more accurate and stable predictions than other benchmark models. It is hoped that this proposed ensemble forecast model will provide effective support for PM2.5 pollution forecast and early warning in the future.

show abstract

“…Li et al (Li et al, 2020) designed a geographically and temporally weighted generalized regression neural network (GTW-GRNN) to estimate ground NO 2 concentrations by integrating ground NO 2 station measurements. Mo et al (Mo et al, 2019) (Chakma et al, 2017) collected street view photos containing sky, buildings and pollution category labels in Beijing from 2013 to 2017 to train convolutional neural network (CNN), and the accuracy of the model in predicting air pollution category through photos can reach 68.74%. Kim et al (Kim et al, 2018) compared the performance of traditional machine learning model multilayer perceptron, deep learning model Elman neural network and long-short term memory network (LSTM) in predicting ozone concentration, and the experiment shows that the performance of LSTM is better and the error growth rate of LSTM is smaller with the increase of prediction time.…”

Section: Introductionmentioning

confidence: 99%

Design a regional and multistep air quality forecast model based on deep learning and domain knowledge

Zhang

2022

Front. Earth Sci.

View full text Add to dashboard Cite

Air pollution is an issue across the world. It not only directly affects the environment and human health, but also influences the regional and even global climate by changing the atmospheric radiation budget, resulting in extensive and serious adverse effects. It is of great significance to accurately predict the concentration of pollutant. In this study, the domain knowledge of Atmospheric Sciences, advanced deep learning methods and big data are skillfully combined to establish a novel integrated model TSTM, derived from its fundamental features of Time, Space, Type and Meteorology, to achieve regional and multistep air quality forecast. Firstly, Expectation Maximization and Min-Max algorithms are used for the interpolation and normalization of data. Secondly, feature selection and construction are accomplished based on domain knowledge and correlation coefficient, and then Sliding Time Window algorithm is employed to build the supervised learning task. Thirdly, the features of pollution source and meteorological condition are learned and predicted by CNN-BiLSTM-Attention model, the integrated model of convolutional neural network and Bidirectional long short-term memory network based on Sequence to Sequence framework with Attention mechanism, and then Convolutional Long Short-Term Memory Neural Network (ConvLSTM) integrates the two determinant features to obtain predicted pollutant concentration. The multiple-output strategy is also employed for the multistep prediction. Lastly, the forecast performance of TSTM for pollutant concentration, air quality and heavy pollution weather is tested systematically. Experiments are conducted in Beijing-Tianjin-Hebei Air Pollution Transmission Channel (“2+26” cities) of China for multistep prediction of hourly concentration of six conventional air pollutants. The results show that the performance of TSTM is better than other benchmark models especially for heavy pollution weather and it has good robustness and generalization ability.

show abstract

A Novel Air Quality Early-Warning System Based on Artificial Intelligence

Cited by 25 publications

References 38 publications

The relationship between particulate matter and childhood respiratory complaints and peak expiratory flows in Harran agricultural area

The relationship between particulate matter and childhood respiratory complaints and peak expiratory flows in Harran agricultural area

Prediction of PM2.5 Concentration Based on Deep Learning, Multi-Objective Optimization, and Ensemble Forecast

Design a regional and multistep air quality forecast model based on deep learning and domain knowledge

Contact Info

Product

Resources

About