Regional Air Quality Forecast Using a Machine Learning Method and the WRF Model over the Yangtze River Delta, East China

Jia, Mengwei; Cheng, Xiao; Zhao, Tianliang; Yin, Cong; Zhang, Xiangzhi; Wu, Xianghua; Wang, Liming; Zhang, Renjian

doi:10.4209/aaqr.2019.05.0275

Cited by 10 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prediction of the 2016 ozone season using generalized additive models are in good agreement with the relevant measurement results (R 2 = 0.70) (Pernak et al, 2019). The average consistency index between PM 2.5 prediction and observation for the four seasons in the Yangtze Delta is between 74% and 77%, using machine learning and WRF (Jia et al, 2019). The best estimation of PM 2.5 (R 2 = 0.84) is obtained by using artificial neural network (Bai et al, 2020).…”

Section: Comparison With Other Modelssupporting

confidence: 73%

Air Pollution Forecasting Using Artificial and Wavelet Neural Networks with Meteorological Conditions

Guo

et al. 2020

Aerosol Air Qual. Res.

View full text Add to dashboard Cite

Air quality forecasting is a significant method of protecting public health because it provides early warning of harmful air pollutants. In this study, we used correlation analysis and artificial neural networks (ANNs; including wavelet ANNs [WANNs]) to identify the linear and nonlinear associations, respectively, between the air pollution index (API) and meteorological variables in Xi'an and Lanzhou. Evaluating twelve algorithms and nineteen network topologies for the ANN and WANN models, we discovered that the optimal input variables for an API forecasting model were the APIs from the 3 preceding days and sixteen selected meteorological factors. Additionally, the API could be accurately predicted based solely on the value recorded 3 days earlier. Based on the correlation coefficients between the air pollution index of the targeted day and the tested variables, the API displayed the closest relationship with the API 1 day earlier as well as stronger correlations with the average temperature, average water vapor pressure, minimum temperature, maximum temperature, API 2 days earlier, and API 3 days earlier. When Bayesian regularization was applied as a training algorithm, the WANN and ANN models accurately reproduced the APIs in both Xi'an and Lanzhou, although the WANN model (R = 0.8846 for Xi'an and R = 0.8906 for Lanzhou) performed better than the ANN (R = 0.8037 for Xi'an and R = 0.7742 for Lanzhou) during the forecasting stage. These results demonstrate that WANNs are effective in short-term API forecasting because they can recognize historic patterns and thereby identify nonlinear relationships between the input and output variables. Thus, our study may provide a theoretical basis for environmental management policies.

show abstract

Section: Comparison With Other Modelssupporting

confidence: 73%

Air Pollution Forecasting Using Artificial and Wavelet Neural Networks with Meteorological Conditions

Guo

et al. 2020

Aerosol Air Qual. Res.

View full text Add to dashboard Cite

show abstract

“…Each of these vectors contains ten elements with nine 24 h forecasts by each CAMS model (referred as time t = 1 in Figure 2) and the present observation (referred as time t = 0 in Figure 2). This choice differs from previous studies in which the input states of machine learning algorithms used to predict PM 10 levels were derived either only from previous observations at monitoring stations [12,30] or only from models forecasts [9,31]. Here, we show that the combination of the last available observation and the ensemble of CAMS model forecasts improves the ANN forecast performance.…”

Section: Definition Of Input State For the Annmentioning

confidence: 71%

“…However, the performance of the network often depends on architectural features, as well as the quality of the acquired data. One of the shortcomings in existing works that we have addressed is the reliance on traditional time series forecasting methods that consider only historical measurements up to a specific time point [12,30] or deterministic model forecasts [9,31]. In contrast, our new architecture leverages the availability of observational and model data at different times, allowing for a more comprehensive and dynamic analysis of the underlying patterns and trends, as shown in Section 2.3.…”

Section: Introductionmentioning

confidence: 99%

Forecasting PM10 Levels Using Machine Learning Models in the Arctic: A Comparative Study

Fazzini,

Montuori,

Pasini

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

In this study, we present a statistical forecasting framework and assess its efficacy using a range of established machine learning algorithms for predicting Particulate Matter (PM) concentrations in the Arctic, specifically in Pallas (FI), Reykjavik (IS), and Tromso (NO). Our framework leverages historical ground measurements and 24 h predictions from nine models by the Copernicus Atmosphere Monitoring Service (CAMS) to provide PM10 predictions for the following 24 h. Furthermore, we compare the performance of various memory cells based on artificial neural networks (ANN), including recurrent neural networks (RNNs), gated recurrent units (GRUs), long short-term memory networks (LSTMs), echo state networks (ESNs), and windowed multilayer perceptrons (MLPs). Regardless of the type of memory cell chosen, our results consistently show that the proposed framework outperforms the CAMS models in terms of mean squared error (MSE), with average improvements ranging from 25% to 40%. Furthermore, we examine the impact of outliers on the overall performance of the model.

show abstract

“…It is important to note that the parameterization (Equation 2) presented in this study was used to illustrate the effect of H BL on aerosol and CCN loading during late winter under the given local aerosol emissions in Delhi. For effective parameterizations to be used in regional climate models, however, parameterization of large-scale multidimensional data including other meteorological factors using artificial intelligence (Czernecki et al, 2021;Jia et al, 2019) is recommended. Similar comprehensive measurements over larger spatial extent, both vertical and horizontal, representing diverse environmental conditions Fit to 7 and seasons as long-term measurements are important to further validate and prove the relevance of such parameterizations in prognostic modeling.…”

Section: Resultsmentioning

confidence: 99%

Planetary Boundary Layer Height Modulates Aerosol—Water Vapor Interactions During Winter in the Megacity of Delhi

et al. 2021

View full text Add to dashboard Cite

The megacity of Delhi is located within the Indo-Gangetic Plain (IGP) and is one of the major sources of anthropogenic air pollution. It is a continental metropolitan area in a large valley south of the Himalayas, which causes the air masses to be constrained within the IGP (Figure 1). The air masses are vulnerable to high levels of particulate matter emissions from the megacity all year round (Bhandari et al., 2020), since it is a fast-growing urban agglomeration (Jain et al., 2016;Paul et al., 2021). During winter, a strong radiative thermal inversion causes the megacity to be enveloped by a shallow planetary boundary layer (PBL) in the nighttime, resulting in high relative humidity (RH) and aerosol mass burden (Arun et al., 2018;Murthy et al., 2020). The cold, humid and polluted conditions coupled with low wind speeds make the landlocked atmosphere conducive to fog and haze formation (Dhangar et al., 2021;Dumka et al., 2019;Ojha et al., 2020). Moreover, the aerosols in Delhi have enhanced water uptake ability as reported in the companion study by Gunthe et al. (2021), which can facilitate multiphase processes for formation of aerosols and thereby cause drastic visibility deterioration.

show abstract

Regional Air Quality Forecast Using a Machine Learning Method and the WRF Model over the Yangtze River Delta, East China

Cited by 10 publications

References 37 publications

Air Pollution Forecasting Using Artificial and Wavelet Neural Networks with Meteorological Conditions

Air Pollution Forecasting Using Artificial and Wavelet Neural Networks with Meteorological Conditions

Forecasting PM10 Levels Using Machine Learning Models in the Arctic: A Comparative Study

Planetary Boundary Layer Height Modulates Aerosol—Water Vapor Interactions During Winter in the Megacity of Delhi

Contact Info

Product

Resources

About