Assessing the impact of clean air action on air quality trends in Beijing using a machine learning technique

3.1

 Observed levels of air pollution in Beijing during 2013–2017

The annual mean concentration of PM2.5 and PM10 in Beijing
measured from the 12 national air quality monitoring stations declined by 34
and 19 % from 88 and 110 µg m−3 in 2013 to 58 and 89 µg m−3 in 2017, respectively. Similarly, the annual mean levels of
NO2 and CO decreased by 16 and 33 % from 54 µg m−3 and
1.4 mg m−3 to 45 µg m−3 and 0.9 mg m−3 while the
annual mean concentration of SO2 showed a dramatic drop by 68 % from
23 µg m−3 in 2013 to 8.0 µg m−3 in 2017. Along with
the decrease in annual mean concentration, the number of haze days (defined
as PM2.5>75 µg m−3 here) also decreased
(Fig. S7). These results confirm a significant improvement of air quality
and that Beijing appeared to have achieved its PM2.5 target under the
action plan (annual average PM2.5 target for Beijing is 60 µg m−3 in 2017). On the other hand, the annual mean concentration of
PM2.5 is still substantially higher than China’s national ambient air
quality standard (NAAQS-II) of 35 µg m−3 (Table S3) and the WHO guideline of 10 µg m−3. While PM10, PM2.5, SO2, NO2, and CO showed a decreasing trend, the annual average concentration of O3 increased slightly by 4.9 % from 58 µg m−3 in 2013 to 61 µg m−3 in 2017. The number of days exceeding NAAQS-II
standards for O3 8 h averages (160 µg m−3) during the period 2013–2017 was 329, accounting for 18 % of total days.

3.2

 Air quality trends after weather normalization

A key aspect in evaluating the effectiveness of air quality policies is to
quantify separately the impact of emission reduction and meteorological
conditions on air quality (Carslaw and Taylor, 2009; Henneman et al.,
2017b), as these are the key factors regulating air quality. By applying a
random forest algorithm, we showed the normalized air quality parameters,
under the 30-year average (1988–2017) meteorological conditions (Fig. 2).
The temporal variations in ambient concentrations of monthly average
PM2.5, PM10, CO, and NO2 do not show a smooth trend from 2013
to 2017 because of the spikes during pollution events. However, after the
weather normalization, we can clearly see the decreasing real trend (Fig. 2). The trends of the normalized air quality parameters represent the
effects of emission control and, in some cases, associated chemical
processes (for example, for ozone, PM2.5, PM10). SO2 showed a dramatic decrease while ozone increased year by year (Fig. 2). The
normalized annual average levels of PM2.5, PM10, SO2,
NO2, and CO decreased by 7.4, 7.6, 3.1, 2.5, and 94 µg m−3 year−1, respectively, whereas the level of O3 increased by 1.0 µg m−3 year−1.

Download Print Version | Download XLSX

Table 1 compares the trends of air pollutants before and after
normalization, which are largely different depending on meteorological
conditions. For example, the annual average concentration of fine particles
(PM2.5) after weather normalization was 61 µg m−3 in 2017, which was higher than their observed level of 58 µg m−3 by 5.2 %. This suggests that Beijing would have missed its PM2.5 target
of 60 µg m−3 if not for the favourable meteorological conditions
in winter 2017 and the emission reduction contributed to 10 µg m−3 out of the 13 µg m−3 (77 %) PM2.5 reduction (71
to 58 µg m−3) from 2016 to 2017. Overall, the emission control
led to a 34 %, 24 %, 17 %, 68 %, and 33 % reduction in normalized
mass concentration of PM2.5, PM10, NO2, SO2, and CO,
respectively, from 2013 to 2017 (Table 1).

When meteorological conditions were randomly selected from 2013 to 2017
(instead of 1998–2017) in the RF model, the normalized level of PM2.5
in 2017 was 60 µg m−3, which is 1 µg m−3 difference
to that using 1998–2017 data. This difference is due to the variation in the
long-term climatology (1998–2017) to the 5-year period (2013–2017).

The observed PM2.5 mass concentration decreased by 30 µg m−3 from 2013 to 2017, whereas the normalized values decreased by 32 µg m−3. Similarly, the observed PM10 and SO2 mass concentration decreased by 30 and 15.5 µg m−3 from 2013 to 2017, whereas the normalized values were 33 and 17.9 µg m−3. These results suggest that the effect of emission reduction would have contributed to an even
better improvement in air quality (except ozone) from 2013 to 2017 if not
for meteorological variations year by year.

Download

Figure 3 shows that the action plan has led to a major improvement in
the air quality of Beijing at the urban, suburban, and rural sites,
particularly for SO2 (16 %–18 % year−1), CO (8 %–9 % year−1), and PM2.5 (6-8 % year−1). The action plan also
led to a decrease in PM10 and NO2 but to a lesser extent than that of CO, SO2, and PM2.5, indicating that PM10 and NO2 were affected by other less well-controlled sources or different atmospheric processes. Urban sites showed a bigger decrease in PM2.5, PM10, and SO2 concentrations in comparison to the rural and suburban sites (Fig. 3).

3.3

 Impact of meteorological conditions on PM

2.5

levels: a comparison with results from the CMAQ-WRF model

We compared our RF modelling results with those from an independent method
by Cheng et al. (2019), who evaluated the de-weathered trend by simulating
the monthly average PM2.5 mass concentrations in 2017 by the CMAQ model
with meteorological conditions of 2013, 2016, and 2017 from the WRF model.
The WRF-CMAQ results predict that the annual average PM2.5
concentration of Beijing in 2017 is 61.8 and 62.4 µg m−3 under the 2013 and 2016 meteorological conditions, respectively, both of which are
higher than the measured value – 58 µg m−3. Thus, the modelled
results are similar to those from the machine learning technique, which gave
a weather-normalized PM2.5 mass concentration of 61 µg m−3
in 2017.

Download

Figure 4 also shows that the PM2.5 concentrations would have been
significantly higher in November and December 2017 if under the
meteorological conditions of 2016. In contrast, the PM2.5
concentrations would have been lower in spring 2017 under the meteorological
conditions of 2016 or the 30-year normalized meteorological data. The more
favourable meteorological conditions in the two winter months contributed
appreciably to the lower measured annual average PM2.5 level in 2017.
This also suggests that the monthly levels of PM2.5 strongly depend upon
the monthly variation in weather.

Comparison of model uncertainties from the two methods

Figure 5 compares observation and prediction of monthly concentrations of
PM2.5 by the WRF-CMAQ model and the RF model. The correlation
coefficients between monthly values was 0.82, whereas that from the
random forest method is > 0.99 for both the training and test
data sets. The difference between the monthly observed PM2.5 values and
those simulated by the WRF-CMAQ model ranged from 3 % to 33.6 %, resulting
in a 7.8 % difference in the yearly value. In contrast, the deviation
between observed and predicted PM2.5 value from the RF model ranges
from 0.4 % to 7.9 % with an average of 1.5 %. In the modelled concentration
of PM2.5 from the random forest technique, standard deviation of the
1000 predicted concentrations of PM2.5 in 2017 is only 0.35 µg m−3, accounting for 0.6 % of the observed PM2.5 concentration.

Download

3.4

 Evaluating the effectiveness of the mitigation measures in the Clean Air Action Plan

The weather-normalized air quality trend (Fig. 2) allows us to assess the
effectiveness of various policy measures to improve air quality to some
extent. In particular, the SO2 normalized trend clearly shows that the peak monthly concentration in the winter months decreased from 60 µg m−3 in January 2013 to less than 10 µg m−3 in December 2017
(Fig. 2). This indicates that the control of emissions from
winter-specific sources was highly successful in reducing SO2
concentrations. The Multi-resolution Emission Inventory for China (MEIC)
shows a major decrease in SO2 emissions from heating (both industrial
and centralized heating) and residential sectors (mainly coal combustion)
(Fig. S8), which is consistent with the trend analyses. On the other hand,
the “baseline” SO2 concentration – defined as the minimum monthly
concentration in the summer (Fig. 2) – also decreased somewhat during the
same period. SO2 in the summer mainly came from non-seasonal sources
including power plants, industry, and transportation (Fig. S9). Overall,
the MEIC estimated that SO2 emissions decreased by 71 % from 2013 to 2017 (Fig. S8), which is close to the 67 % decrease in the weather-normalized concentration of SO2 (Table 1). According to the Beijing
Statistical Yearbooks (2012–2017), coal consumption in Beijing declined
remarkably by 56 % in 6 years as shown in Fig. 6 (Karplus et al., 2018; BMBS, 2013–2017). The slightly
faster decrease in SO2 concentrations relative to coal consumption
(Fig. S9) was attributed to the adoption of clean coal technologies that were enforced by the “Action Plan for Transformation and Upgrading
of Coal Energy Conservation and Emission Reduction (2014–2020)” (Karplus
et al., 2018; Chang et al., 2016). In summary, energy restructuring, e.g.,
replacement of coal with natural gas (Fig. 6; Sect. S2), is a highly
effective measure in reducing ambient SO2 pollution in Beijing.

Download

Coal combustion is not only a major source of SO2, but also an
important source of NOx and primary particulate matter (PM) in Beijing (Streets and Waldhoff, 2000; Zíková et al., 2016; Lu et al., 2013; Huang et al., 2014). Precursor gases including SO2 and NOx from coal combustion also contribute to secondary aerosol formation (Lang et al., 2017). The MEIC emission inventory showed that 8.8 %–29 % of NOx was emitted from heating, power, and residential activities, primarily associated with coal combustion. As shown in Fig. S9, the normalized NO2 concentration is also decreasing, but much slower than that of SO2. Most notably, the level of SO2 dropped rapidly in 2014 but the level of NO2 decreased by a small proportion. The different trends between SO2 and NO2 indicate that other sources (e.g. traffic emissions, Fig. S9) or atmospheric processes have a greater influence on ambient concentration of NO2 than coal combustion.
For example, the chemistry of the NO–NO2–O3 system will tend to
“buffer” changes in NO2 causing non-linearity in NOx−NO2
relationships (Marr and Harley, 2002). NO2 concentrations
decreased more rapidly from January 2015, specifically by 17 %, 18 %,
10 %, and 15 % (Fig. 2) in the first 6 months of 2015, which suggests
that emission control measures implemented in 2015 were effective. These
measures include regulations on spark ignition light vehicles to meet the
national fifth phase standard and expanded traffic restrictions to certain
vehicles, including banning entry of high polluting and non-local vehicles
to the city within the sixth ring road during daytime and the phasing out of 1
million old vehicles (Yang et al., 2015) (Sect. S2).

Normalized PM2.5 decreased faster than NO2, but more slowly than
SO2 (Fig. S9). Yearly peak normalized PM2.5 concentrations
decreased from 2013–2014 to 2015–2016 but slighted rebounded in 2016–2017. The
monthly normalized peak PM2.5 concentration decreased from 115 µg m−3 in January 2013 to 60 µg m−3 in December 2017. The biggest drop
is seen in winter 2017, which decreased by more than half from the peak
value in winter 2016, suggesting that the “no coal zone” policy (Sect. S2) to reduce pollutant emissions from winter-specific sources (i.e.,
heating and residential sectors) was highly effective in reducing
PM2.5. The normalized “baseline” concentration – minimum monthly
average concentration in the summer – also decreased from 71 µg m−3 in summer 2013 to 42 µg m−3 in summer 2017. This
suggests that non-heating emission sources, including industry, industrial
heating, and power plants also contributed to the decrease in PM2.5 from
2013 to 2017. These are broadly consistent with the PM2.5 and SO2 emission trends in MEIC (Fig. S8). A small peak in both PM2.5 and CO in June–July seen in Fig. 2 from 2013 to 2016 attributed to agricultural burning almost disappeared over the period of the measurements and
simulations in 2017, suggesting the ban on open burning is effective.

The normalized trend of PM10 is similar to that of PM2.5, except
that the rate of decrease is slower. The trend agrees well with PM10
primary emissions for the summer (Fig. S8). The biggest drop in peak
monthly PM10 concentration is seen in winter 2017, which decreased by
more than half from the peak value in winter 2016, suggesting that no coal
zone policy (Sect. S2) to reduce pollutant emissions from winter-specific
sources (i.e., heating and residential sectors) was highly effective in
reducing PM10, as with PM2.5. The rate of decrease in peak monthly
PM10 emission is slower than that of weather-normalized PM10
concentrations, which may suggest an underestimation of the decrease by the
MEIC. The normalized baseline concentration (minimum monthly average
concentration, Fig. 2) – also decreased substantially from 2013 to 2017.
This indicates that non-heating emission sources, including industry,
industrial heating, and power plants also contributed to the decrease in
PM10. This is consistent with the trends in MEIC (Fig. S8). The peaks
in the spring are attributed to Asian dust events.

The normalized CO trend shows that the peak CO concentration decreased by
approximately 50 % from 2013 to 2017 with the largest drop from 2016 to
2017 (Fig. 2). The decreasing trend in total emission of CO in the MEIC is
slower from 2015 to 2017, suggesting that CO emission in the MEIC may be
overestimated in these 2 years. During 2013–2016, the CO level decreased
by 26 % and 34 % for winter and summer. Similar to the normalized
PM2.5 trend, a small peak of CO concentration occurred in June–July
during 2013–2016, which is likely associated with open biomass burning
around the Beijing region. This peak disappeared in 2017. A major decrease
in normalized CO levels in winter 2017 is mainly attributed to the no-coal zone
policy (see below Sect. S2; Fig. S8).

3.5

 Implications and future perspectives

We have applied a machine-learning-based model to identify the key
mitigation measures contributing to the reduction of air pollutant
concentrations in Beijing. However, three challenges remain. Firstly, it is
not always straightforward to link a specific mitigation measure to
improvement in air quality quantitatively. This is because often more than
two measures were implemented on a similar timescale, making it difficult to
disentangle the impacts. Secondly, we were not able to compare the
calculated benefit for each mitigation measure with that intended by the
government due to a lack of information about the implemented policies, for
example, the start and end dates of air pollution control actions. If data on the
intended benefits are known, this will further enhance the value of this
type of study. Thirdly, the ozone level increased slightly during 2013–2017,
especially for the summer periods (Table 1). Because ozone is a secondary
pollutant, interpretation of the effects of emission changes of precursor
pollutants is complex and beyond the scope of this study.

Our results confirm that the action plan has led to a major
improvement in the real (normalized) air quality of Beijing (Fig. 3).
However, it would have failed to meet the target for annual average
PM2.5 concentrations if not for better-than-average air pollutant
dispersion (meteorological) conditions in 2017. This suggests that future
target setting should consider meteorological conditions. Major challenges
remain in reducing the PM2.5 levels to below Beijing’s own targets,
as well as China’s national air quality standard and WHO guidelines. Another
challenge is to reduce the NO2 and O3 levels, which show little
decrease or even an increase from 2013 to 2017. The lessons learned in
Beijing thus far may prove beneficial to other cities as they develop their
own clean air strategies.