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

Abstract. The contribution of meteorology and emissions to long-term PM2.5 trends is critical for air quality management but has not yet been fully analyzed. Here, we used the combination of a machine learning model, statistical method, and chemical transport model to quantify the meteorological impacts on PM2.5 pollution during 2000–2018. Specifically, we first developed a two-stage machine learning PM2.5 prediction model with a synthetic minority oversampling technique to improve the satellite-based PM2.5 estimates over highly polluted days, thus allowing us to better characterize the meteorological effects on haze events. Then we used two methods to examine the meteorological contribution to PM2.5: a generalized additive model (GAM) driven by the satellite-based full-coverage daily PM2.5 retrievals and the Weather Research and Forecasting/Community Multiscale Air Quality (WRF/CMAQ) modeling system. We found good agreements between GAM estimations and the CMAQ model estimations of the meteorological contribution to PM2.5 on a monthly scale (correlation coefficient between 0.53–0.72). Both methods revealed the dominant role of emission changes in the long-term trend of PM2.5 concentration in China during 2000–2018, with notable influence from the meteorological condition. The interannual variabilities in meteorology-associated PM2.5 were dominated by the fall and winter meteorological conditions, when regional stagnant and stable conditions were more likely to happen and when haze events frequently occurred. From 2000 to 2018, the meteorological contribution became more unfavorable to PM2.5 pollution across the North China Plain and central China but were more beneficial to pollution control across the southern part, e.g., the Yangtze River Delta. The meteorology-adjusted PM2.5 over eastern China (denoted East China in figures) peaked in 2006 and 2011, mainly driven by the emission peaks in primary PM2.5 and gas precursors in these years. Although emissions dominated the long-term PM2.5 trends, the meteorology-driven anomalies also contributed −3.9 % to 2.8 % of the annual mean PM2.5 concentrations in eastern China estimated from the GAM. The meteorological contributions were even higher regionally, e.g., −6.3 % to 4.9 % of the annual mean PM2.5 concentrations in the Beijing-Tianjin-Hebei region, −5.1 % to 4.3 % in the Fenwei Plain, −4.8 % to 4.3 % in the Yangtze River Delta, and −25.6 % to 12.3 % in the Pearl River Delta. Considering the remarkable meteorological effects on PM2.5 and the possible worsening trend of meteorological conditions in the northern part of China where air pollution is severe and population is clustered, stricter clean air actions are needed to avoid haze events in the future.

Download Full-text

Ambient PM2.5 Estimates and Variations during COVID-19 Pandemic in the Yangtze River Delta Using Machine Learning and Big Data

Remote Sensing ◽

10.3390/rs13081423 ◽

2021 ◽

Vol 13 (8) ◽

pp. 1423

Author(s):

Debin Lu ◽

Wanliu Mao ◽

Lilin Zheng ◽

Wu Xiao ◽

Liang Zhang ◽

...

Keyword(s):

Machine Learning ◽

Air Pollution ◽

Big Data ◽

Yangtze River ◽

Regression Models ◽

Yangtze River Delta ◽

River Delta ◽

The Yangtze River ◽

The Yrd ◽

The Yangtze River Delta

The lockdown of cities in the Yangtze River Delta (YRD) during COVID-19 has provided many natural and typical test sites for estimating the potential of air pollution control and reduction. To evaluate the reduction of PM2.5 concentration in the YRD region by the epidemic lockdown policy, this study employs big data, including PM2.5 observations and 29 independent variables regarding Aerosol Optical Depth (AOD), climate, terrain, population, road density, and Gaode map Point of interesting (POI) data, to build regression models and retrieve spatially continuous distributions of PM2.5 during COVID-19. Simulation accuracy of multiple machine learning regression models, i.e., random forest (RF), support vector regression (SVR), and artificial neural network (ANN) were compared. The results showed that the RF model outperformed the SVR and ANN models in the inversion of PM2.5 in the YRD region, with the model-fitting and cross-validation coefficients of determination R2 reached 0.917 and 0.691, mean absolute error (MAE) values were 1.026 μg m−3 and 2.353 μg m−3, and root mean square error (RMSE) values were 1.413 μg m−3, and 3.144 μg m−3, respectively. PM2.5 concentrations during COVID-19 in 2020 have decreased by 3.61 μg m−3 compared to that during the same period of 2019 in the YRD region. The results of this study provide a cost-effective method of air pollution exposure assessment and help provide insight into the atmospheric changes under strong government controlling strategies.

Download Full-text

Evaluating the energy efficiency of wastewater treatment plants in the Yangtze River Delta: Perspectives on regional discrepancies

Applied Energy ◽

10.1016/j.apenergy.2021.117087 ◽

2021 ◽

Vol 297 ◽

pp. 117087

Author(s):

Runyao Huang ◽

Ziheng Shen ◽

Hongtao Wang ◽

Jin Xu ◽

Zisheng Ai ◽

...

Keyword(s):

Energy Efficiency ◽

Wastewater Treatment ◽

Yangtze River ◽

Wastewater Treatment Plants ◽

Yangtze River Delta ◽

River Delta ◽

The Yangtze River ◽

The Yangtze River Delta

Download Full-text

Current Status and Temporal Trend of Potentially Toxic Elements Pollution in Agricultural Soil in the Yangtze River Delta Region: A Meta-Analysis

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18031033 ◽

2021 ◽

Vol 18 (3) ◽

pp. 1033

Author(s):

Shufeng She ◽

Bifeng Hu ◽

Xianglin Zhang ◽

Shuai Shao ◽

Yefeng Jiang ◽

...

Keyword(s):

Yangtze River ◽

Agricultural Soil ◽

Toxic Elements ◽

Temporal Trend ◽

Meta Analysis ◽

Yangtze River Delta ◽

Potentially Toxic Elements ◽

River Delta ◽

The Yangtze River ◽

The Yangtze River Delta

Potentially toxic elements (PTEs) pollution in the agricultural soil of China, especially in developed regions such as the Yangtze River Delta (YRD) in eastern China, has received increasing attention. However, there are few studies on the long-term assessment of soil pollution by PTEs over large regions. Therefore, in this study, a meta-analysis was conducted to evaluate the current state and temporal trend of PTEs pollution in the agricultural land of the Yangtze River Delta. Based on a review of 118 studies published between 1993 and 2020, the average concentrations of Cd, Hg, As, Pb, Cr, Cu, Zn, and Ni were found to be 0.25 mg kg−1, 0.14 mg kg−1, 8.14 mg kg−1, 32.32 mg kg−1, 68.84 mg kg−1, 32.58 mg kg−1, 92.35 mg kg−1, and 29.30 mg kg−1, respectively. Among these elements, only Cd and Hg showed significant accumulation compared with their background values. The eastern Yangtze River Delta showed a relatively high ecological risk due to intensive industrial activities. The contents of Cd, Pb, and Zn in soil showed an increasing trend from 1993 to 2000 and then showed a decreasing trend. The results obtained from this study will provide guidance for the prevention and control of soil pollution in the Yangtze River Delta.

Download Full-text

The Evolution of the Interactive Relationship between Urbanization and Land-Use Transition: A Case Study of the Yangtze River Delta

Land ◽

10.3390/land10080804 ◽

2021 ◽

Vol 10 (8) ◽

pp. 804

Author(s):

Bo Niu ◽

Dazhuan Ge ◽

Rui Yan ◽

Yingyi Ma ◽

Dongqi Sun ◽

...

Keyword(s):

Land Use ◽

Land Use Change ◽

Yangtze River ◽

Yangtze River Delta ◽

River Delta ◽

Socioeconomic Factor ◽

The Yangtze River ◽

Land Use Transition ◽

The Yangtze River Delta ◽

Interaction Relationship

In recent years, the impact of land-use systems on global climate change has become increasingly significant, and land-use change has become a hot issue of concern to academics, both within China and abroad. Urbanization, as an important socioeconomic factor, plays a vital role in promoting land-use transition, which also shows a significant spatial dependence on urbanization. This paper constructs a theoretical framework for the interaction relationship between urbanization and land-use transition, taking the Yangtze River Delta as an example, and measures the level of urbanization from the perspective of population urbanization, economic urbanization and social urbanization, while also evaluating the level of land-use morphologies from the perspective of dominant and recessive morphologies of land-use. We construct a PVAR model and coupled coordination model based on the calculated indexes for empirical analysis. The results show that the relationship between urbanization and land-use transition is not a simple linear relationship, but tends to be complex with the process of urbanization, and reasonable urbanization and land-use morphologies will promote further benign coupling in the system. By analyzing the interaction relationship between urbanization and land-use transition, this study enriches the study of land-use change and provides new pathways for thinking about how to promote high-quality urbanization.

Download Full-text