3.1 ATSR ADV

The ATSR instruments, ATSR-2 on board the European Remote Sensing satellite ERS-2 (1995–2003) and AATSR on board the Environmental Satellite (Envisat) (2002–2012), hereafter together referred as ATSR, were developed to provide high-accuracy measurements of the sea surface temperature. However, they were also successfully used for atmospheric aerosol retrievals (e.g., Flowerdew and Haigh, 1996; Veefkind et al., 1998; Sayer et al., 2010; de Leeuw et al., 2015; Kolmonen et al., 2016; Popp et al., 2016). Together, these instruments provided 17 years of global data. Both satellites flew in a sun-synchronous descending orbit with a daytime Equator crossing time of 10:30 LT (local time) for ERS-2 and 10:00 LT for Envisat. The ATSR is a dual view instrument. One view is near-nadir and the other is at a 55^∘ forward angle. The time between the two views is ca. 150 s along the track. The nominal resolution at nadir is 1×1 km² and the swath width is 512 km, which results in global coverage in 5–6 days. ATSR has three wave bands in the visible–near-infrared (centered near 555, 659 and 865 nm) and four bands in the mid- to thermal-infrared (centered near 1600, 3700, 10 850 and 12 000 nm).

Over land, the ATSR ADV AOD retrieval algorithm uses the two ATSR views simultaneously to eliminate the contribution of land surface reflectance to the top of atmosphere radiation and to retain the path radiance in cloud-free scenes (Veefkind et al., 1998; Kolmonen et al., 2016; Sogacheva et al., 2017) following Flowerdew and Haigh (1996).

ATSR-2 AOD data are available for the period from June 1995 to December 2003, with some gaps in 1995 (from January to May, globally) and 1996 (from January to June, globally); toward the end of the period (approximately from autumn 2002) the data are also less reliable. AATSR data are available for the May 2002–April 2012 period, but some data are missing in 2002; therefore, we only use AATSR data from August 2002 onward. The consistency between the ATSR-2 and AATSR datasets was discussed in Popp et al. (2016). Over China, the difference between the ADV AOD values retrieved from ATSR-2 and AATSR is small, as shown by pixel-by-pixel and monthly aggregate comparisons as well as validation results (Part 1). This allows for the combination of the ATSR-2 and AATSR AOD time series into one dataset without offset correction over China.

The L3 (averaged on a grid of 1^∘ × 1^∘) seasonal aggregates were obtained for winter (DJF), spring (MAM), summer (JJA) and autumn (SON) by averaging the L3 monthly aggregates to corresponding seasons. The annual AOD data were obtained by averaging the monthly AOD data. In the following, the ATSR ADV version 2.31 AOD product will be referred to as ADV.

3.2 MODIS

The MODIS/Terra sensor (Salomonson et al., 1989) aboard NASA's Terra satellite has been flying in a near-polar sun-synchronous circular orbit for more than 15 years (since December 1999). MODIS/Terra has a daytime Equator crossing time at 10:30 LT (descending orbit), a viewing swath of 2330 km (cross track) and provides near-global coverage on a daily basis. Its detectors measure 36 spectral bands between 0.405 and 14.385 µm, and it acquires data at three spatial resolutions (250, 500 and 1000 m).

MODIS AOD is retrieved using two separate algorithms, dark target (DT) and deep blue (DB). Furthermore, two different DT algorithms are utilized, one for retrieval over land (Kaufman et al., 1997; Remer et al., 2005; Levy et al., 2013) and one for retrieval over water surfaces (Tanré et al., 1997; Remer et al., 2005; Levy et al., 2013). The DB algorithm (Hsu et al., 2004, 2013) was traditionally used over bright surfaces where DT performance is limited (e.g., deserts, arid and semiarid areas) and was further developed for returning aerosol measurements over all land types (Sayer et al., 2014). Hereafter, the MODIS/Terra AOD C6.1 DTDB merged AOD product will be referred to as MODIS.

3.3 ADV and MODIS validation results

AOD Level 2 (L2, 0.1^∘ × 0.1^∘ resolution) validation with the AERONET L2.0 (quality-assured) AOD over China for ADV (de Leeuw et al., 2018) and MODIS C6.1 is discussed in detail in Part 1. The locations of the AERONET stations used in this study for validation are shown in Fig. 2. Note that the number of the AERONET stations is limited over northwest of China (de Leeuw et al., 2018; Part 1).Validation results are briefly summarized in this section. For all available collocations between ADV and AERONET and between MODIS and AERONET (Table 1, “All points”), the MODIS algorithm performs slightly better than ADV. The correlation coefficients are 0.88 for ADV and 0.92 for MODIS (note, that as MODIS has better coverage compared with ADV (Part 1), the number of validation points for MODIS is considerably larger). Both algorithms show a similar (in absolute numbers) bias, which is negative for ADV (−0.06) and positive for MODIS (0.07). The AOD standard deviation (δ) and root mean square error (rms) are slightly lower for MODIS. Similar in absolute values but different in sign, the AOD bias was obtained also for “fine-dominated” (AOD>0.2, AE>1) and for “coarse-dominated” (AOD>0.2, AE<1) aerosol conditions (−0.11 and 0.10 for ADV and MODIS, respectively).

Table 1ADV and MODIS AOD validation results over China for the 2000–2011 overlap period. Statistics (number of points – N, correlation coefficient – R, bias, standard deviation – σ and root mean square error – rms) for all validation points, separated by “fine-dominated” (AOD>0.2, AE>1) and “coarse-dominated” (AOD>0.2, AE<1) aerosols, and collocated points (*when ADV and MODIS overpasses are within ±90 min of each other and ADV, MODIS and AERONET retrieve AOD). For collocated points, statistics are also aggregated seasonally for winter (DJF), spring (MAM), summer (JJA) and autumn (SON).

Download Print Version | Download XLSX

To compare the performance of the two algorithms when both ADV and MODIS retrieve AOD, we carried out the AOD validation for cases where the difference between ATSR and MODIS/Terra overpasses was less than 90 min and both ADV and MODIS successfully retrieved AOD around AERONET (Table 1, “Collocated points”). Altogether, 255 collocations exist between ADV, MODIS and AERONET for the ATSR and MODIS/Terra overlap period (2000–2011) over China. Validation was carried out for all collocated points and for each of the four seasons: DJF, MAM, JJA and SON. For all collocated points, the correlation coefficients (R) were similar for ADV and MODIS (0.92 and 0.93, respectively), ADV was biased negatively (−0.11), and MODIS was biased positively (0.06). In winter, MODIS showed a strong negative bias in AOD (−0.17), while the correlation for MODIS was higher than for ADV (0.96 and 0.92, respectively). Note, that the number of collocated points was low (10) in winter. In spring, R was the same (0.81) for MODIS and ADV, while the bias was 0 for ADV and 0.013 for MODIS. Interestingly, both MODIS and ADV showed a similar tendency to underestimate AERONET AOD for AOD>0.6 in spring. In summer, R was slightly higher for MODIS; biases for ADV and MODIS were equal in an absolute sense but opposite in sign (negative for ADV and positive for MODIS). In autumn, R was a higher for ADV (0.92 versus 0.88 for MODIS), and the bias was negative for ADV (−0.02) and positive for MODIS (0.05).

In summary, MODIS showed a better performance for the “All points” selection (Table 1). A similar (in absolute numbers) bias, which is negative for ADV and positive for MODIS, is considered in Sect. 4, where a method for combining the two datasets is presented. For collocated points, ADV and MODIS showed similar performance.

4.1 Method

The combined AOD (AOD_comb) database for the period from 1995 to 2017 was compiled from AOD estimated for three periods. The first period (T1) is the pre-EOS period (1995–1999), when only ATSR was available, the second period (T2) is the ATSR and MODIS/Terra overlap period (2000–2011) and the third (T3) is the post-ENVISAT (2012–2017) period, when only MODIS/Terra was available:

First, we introduce the combined AOD for the overlap period T2, when AOD for both ADV (AOD_ADV) and MODIS (AOD_MOD) was available. AOD for each year (AOD_T2,y) is calculated as a mean of AOD_ADV,y and AOD_MOD,y:

Simple averaging was applied, as ADV and MODIS show similar biases of opposite signs (Sect. 2.3 and Part 1).

Using ADV and MODIS yearly AOD from T2, the AOD correction (AOD_corr) was calculated as the mean difference between ADV and MODIS for the overlapping period:

where N is the length of the overlapping period in years.

For the respective ADV and MODIS datasets, the AOD correction was scaled by the corresponding AOD averaged over the overlapping period:

For T1 and T3, the AOD relative correction (AOD_{rel_corr}) was applied as positive correction for ADV AOD, which is usually low compared with AERONET AOD (Eq. 6), and as negative correction for MODIS AOD, which is usually higher compared with AERONET AOD (Eq. 7):

The spatial distributions of the relative correction for MODIS AOD (AOD_{rel_corr,MODIS}) are shown in Fig. 3 for annual and seasonal AOD aggregates. As expected, the highest AOD relative correction (30–40 %) corresponds to the areas where the agreement is lower between ADV and MODIS AOD (Fig. 10 in Part 1), e.g., over bright surface areas, such as Tibetan Plateau, the Taklamakan and Gobi deserts and the Harbin area. The reasons for the disagreement between ADV AOD and MODIS AOD, which are mostly related to the coverage and validation results, are discussed in detail in Part 1 and Sect. 3.3 of the current paper. For seasonal aggregates, the highest correction (ca. 45 %) is obtained over the Tibetan Plateau in autumn, when the AOD is lower compared with spring and summer (Fig. 10 in Part 1). In summer, the correction is smaller, as the agreement between the ADV and MODIS AOD is better in summer than in other seasons (Fig. 10 in Part 1). Over SE China, the AOD correction is lower (between 10 % and 20 % of AOD). The ADV AOD relative correction shows similar spatial patterns and is consequently not discussed here.

Figure 3AOD relative correction for MODIS seasonal (DJF, MAM, JJA and SON) and annual (Year) AOD for the combined AOD dataset obtained using the method introduced in Sect. 4.1.

Download

The method was applied pixel-wise to L3 annual and seasonal AOD aggregates from ADV and MODIS to build the yearly and seasonal database of the combined AOD. For each season, the AOD relative correction was computed separately, as introduced above for the annual AOD.

4.2 Results

The time series of the seasonally and annually averaged AOD from ADV (red circles), MODIS (green circles) and combined AOD (yellow diamonds) are shown for all of China and for SE China in Fig. 4. Since ADV was negatively biased and MODIS was positively biased with respect to the AERONET AOD, and the biases were similar in absolute value, the combined time series in the pre-EOS and post-Envisat periods are practically corrected by increasing ADV and lowering MODIS AOD using the AOD correction introduced in Sect. 4.1. As expected, the similar interannual variations in the separate datasets are reproduced in the combined time series.

For all seasons, except spring, the difference between ADV and MODIS AOD is small; therefore, the combined time series closely resembles both the ADV and MODIS AOD. In spring, the combined time series show, on average, lower AOD compared with MODIS (which, in relative numbers, is about 10–20 % lower than the MODIS AOD). However, as for annual aggregates, the interannual variability for seasonal combined AOD is similar for both ADV and MODIS.

The annual and seasonal AOD tendencies for the combined time series are estimated in Sect. 5.

Figure 4ADV (red circles), MODIS (green circles) and combined from ADV and MODIS (yellow diamonds) seasonal and annual AOD time series for China (a) and SE China (b) for winter (DJF), spring (MAM), summer (JJA), autumn (SON) and the whole year (Year). The method used to combine the ADV and MODIS time series is presented in Sect. 4.1.

Download

Figure 5Density scatterplot of ADV AOD (a), MODIS AOD (b) and combined AOD (c) versus AOD from AERONET stations over China for the T2 period (2000–2011). The filled circles are the averaged AOD binned in 0.1 AERONET AOD intervals (0.25 for AERONET AOD>1.0) and the vertical lines on each circle represent the 1σ standard deviation. Statistics in the upper left corner indicate correlation coefficient R, standard deviation, root mean square error (rms) and the number of data points (N). The color bar on the right indicates the number of data points in each bin.

Download

4.3 Combined AOD comparison with AERONET

The combined AOD datasets were built from the L3 data for the seasonal and annual aggregates; thus, a comparison with the AERONET is possible for the corresponding aggregates only. We call the current exercise a comparison rather than a validation, as the temporal coverage in seasonal and annual aggregates for AERONET, ADV, MODIS and combined AOD is different which might bias the aggregated values. The combined AOD was constructed from three periods (T1, T2 and T3, see Sect. 4.1 for details), where different corrections were applied; thus, we perform the AOD comparison for the corresponding periods, as well as for the full ATSR and full MODIS periods.

For T1, the number of AERONET locations is limited to perform the comparison (Part 1). For T2, the agreement between AERONET and combined AOD seasonal and annual aggregates (Fig. 5, Table A1) is slightly better than between AERONET and ADV or MODIS separately. R is higher in DJF, JJA and “Year”, 1σ and rms are lower for all seasons and “Year”. For T3 (Table A1), R is considerably higher in spring (0.49 and 0.61 for MODIS and combined, respectively). AOD standard deviation (σ) and rms are lower for all seasons for combined AOD compared with MODIS AOD.

For 1998–2012, which covers the period when both AERONET and ADV are available, correlation R is higher for combined AOD in winter, autumn and “Year”; rms is lower in all seasons and “Year” for the combined AOD compared with ADV AOD.

For 2000–2017, which covers the period when both AERONET and MODIS are available, comparison results for the combined AOD and MODIS AOD are similar to T3.

5.1 Evolution of AOD over China: annual anomaly maps

To study the temporal evolution of the AOD over China during the whole period (WP) from 1995 to 2017, anomaly maps (Fig. 6) were created by subtracting the multiyear aggregate for the WP from the yearly aggregates. The evolution of the AOD can be followed for different regions; thus, regions with similar or different evolution of the AOD can be identified.

Strong negative anomalies over SE China (and the north of India and Bangladesh, which are outside the scope of this paper) in 1995–2001 show that the AOD was lower compared to the AOD averaged over the WP during this time. Towards 2006, the AOD anomalies became less negative: the yearly AOD increased and the anomaly decreased. Starting from 2006, a positive AOD anomaly, which show that the yearly AOD was higher than the AOD averaged over 2000–2011, was observed over SE China. Between 2006 and 2011, the positive anomalies remained high. Starting in 2011, the anomaly changed from positive to negative, i.e., the AOD decreased. However, from 2015 the anomaly was mostly negative and became stronger towards 2017, which was the last year in our studies.

The AOD anomaly pattern in SE China was very variable. In the BTH area (region 1), the anomaly was strongly negative in 1995, which was the beginning of the time series, and gradually decreased towards 2006, when it became positive. In the area over the YRD (region 2) which encompasses large urban and industrial developments such as Shanghai and Nanjing, the multiyear average appeared to be quite representative of the AOD with negative anomalies until 2000; after 2000 the anomalies fluctuated around zero with neither very high nor very low values.

Similar AOD behavior was observed in the Sichuan/Chongqing area (region 6) with a strong positive anomaly in 1997 and 1999, followed by negative anomalies in 2000–2002. After 2002, no significant deviations were observed until 2005 when the AOD exceeded the multiyear average; this situation then persisted, with small fluctuations, until 2014 when a strong negative anomaly expanded over the wider region of SE China (from 2015 to 2017).

A “belt” of positive AOD anomalies were observed east of the Taklamakan Desert in 2001, which was likely due to the most intensive dust event during the period of interest. The widespread positive AOD anomalies in 1998 and 2003 in the northeast of China were likely the consequence of forest fires over Russia.

Figure 6AOD anomaly maps for the years from 1995 to 2017 calculated for combined AOD. Anomalies were calculated for each year by subtracting the multiyear (1995–2017) average from the annual aggregates.

Download

Although meteorological conditions play an important role in mixing and transporting pollutants, increasing local aerosol emission from human activities has generally been considered to be the dominant cause of increasing wintertime haze over China in past decades (Yin et al., 2017). One can isolate meteorological changes from emissions changes by normalizing the aerosol concentrations using aerosol concentration efficiencies (Yang et al., 2018). However, the contribution of wind and its associated languishing patterns explain 10 % of the historical increase of regional AOD, while other meteorological contributions show no significant trends over 35 years (Gu et al., 2018).

In the Beijing area, the variation of the AOD has been significantly affected by anthropogenic aerosol emissions (Gu et al., 2018) during the last few decades. In the current paper, we aim to show that changes in the AOD follow the emission control policy in China. Below we present a short overview of the emission regulation policies in China over the last 2 decades.

5.2 Emissions regulation policies in China over the last 2 decades

Jin et al. (2016) showed the following regarding the emission regulation policies in China: (1) the early policies, before 2005, were ineffective at reducing emissions; (2) from 2006 to 2012, new instruments, which interact with political incentives, were introduced in the 11th Five-Year Plan. However, emission control policies on air pollution have not been strongly reconsidered in the 11th Five-Year Plan; thus, no significant reduction in air pollution has been observed. Therefore, regional air pollution problems dominated by fine particulate matter (PM_2.5) and ground level ozone (O₃) have emerged. Nevertheless, the national goal of reducing total sulphur dioxide (SO₂) emissions by 10 % has been achieved (Lin et al., 2010).

Jin et al. (2016) also showed that SO₂ emissions, as well as smoke and dust emissions, have been gradually decreasing since 2006. However, the reduction of the total emission of SO₂, a single primary pollutant, does not necessarily improve air quality. NO_x emissions continued to grow which was explained by the growing number of vehicles – mainly in megacities. Total NO_x emissions in East China reached their peak levels in 2012, and have stopped increasing since then (van der A et al., 2017). This stagnation NO_x emissions was concurrent with the introduction of regulations requiring the installation of filtering systems, mainly at power plants but also for heavy industry. These regulations for NO_x were announced in 2013 in the Air Pollution Prevention and Control Action Plan (CAAC, 2013).

Figure 7AOD tendencies (per year, see color bar) from seasonally and annually aggregated combined AOD time series for two periods: 1995–2006 (P1, a) and 2011–2017 (P2, b).

Download

Figure 8AOD relative tendencies (per year, see color bar) from seasonally and annually aggregated combined AOD time series for two periods: 1995–2006 (P1, a) and 2011–2017 (P2, b).

Download

The “total control” of SO₂ and NO_x has been strengthened and accelerated in China (Zhang et al., 2017). For example, the change in standards for cars from 2011 to 2015 reduced the maximum amount of NO_x emissions allowed for on-road vehicles by 50 % (Wu et al., 2017). Further emission control scenarios exist in China regarding the coal-burning thermal power plants.

The newly designed control policies considered in Wang et al. (2018) are predicted to lead to reductions in January PM_2.5, PM₁₀, NO₂ and SO₂ levels of between −8.6 % and −14.8 % in Beijing. However, regional differences in emission controls currently exist. For example, stricter regulations for on-road vehicles (e.g., a ban on older polluting cars) have been introduced on a city level, e.g., in Beijing, rather than nationwide (van der A et al., 2017).

In June 2013, the State Council issued the Action Plan for Air Pollution Prevention and Control. This document laid out the roadmap for air pollution prevention and control across China for the 2013–2017 period. In 2016, the second report was published (http://cleanairasia.org/wp-content/uploads/2016/08/China-Air-2016-Report-Full.pdf, last access: 21 November 2018) showing the considerable emission reductions and improved air quality. The air quality mostly improved in developed regions. This report finds that cities which failed to attain the 2015 air quality target show slow progress and still suffer from poor air quality; these cities are concentrated in Henan Province, Shandong Province and in the northeast of China. The abovementioned locations all had less experience regarding air pollution, in addition to an insufficient capacity to carry out air pollution prevention and control compared with more developed regions such as the BTH. Such regional differences might result in some deviation of regional emission tendencies compared to those averaged over the whole of China.

Therefore, three periods, closely related to the Five-Year Plan initiative (before 2006, 2006–2011 and after 2011), can be identified, when the emission reduction policies in China are considered.

5.3 AOD seasonal and annual tendencies for the selected periods: 1995–2006 and 2011–2017

In addition to selecting the study periods based on emission reduction policy according to the Five-Year Plan initiative, we performed statistical tests, where we looked at the AOD tendencies, the uncertainties and the errors on an annual/seasonal basis for different periods for all selected regions. The results (not shown here) prove that, with some exception (1–2 year shifts for a few regions, depending on the season) years 2006 and 2011 can be chosen as a pivot points for the AOD tendencies in China.

Linear regression was applied to individual L3 pixels of the combined AOD time series to estimate the AOD tendencies over China for two periods: 1995–2006 (P1) and 2011–2017 (P2). For P1 and P2, the AOD tendencies (dAOD) per year were estimated, as P2 is too short to estimate the decadal tendencies. Results for the 2006–2011 period are not shown here as the AOD tendency during that period was close to zero. We also estimated the AOD relative tendencies, which are the ratios of tendencies and the corresponding time series averages (Schönwiese and Rapp, 1997). The AOD tendencies and the AOD relative tendencies for annual aggregates for P1 and P2 are shown in Figs. 7 and 8, respectively. To avoid a high but scientifically unimportant AOD relative change over a fairly clean background, the relative tendencies are shown if the corresponding time series AOD averages were above 0.1. AOD positive tendencies are denoted by red; AOD negative tendencies are denoted by blue.

In P1 (Figs. 7a and 8a), the AOD increase in summer (JJA) and autumn (SON) of 0.1 to 0.5 (ca. 3–7 % of the AOD averaged over the corresponding period) per year contributed most to the annual AOD increase over SE China. In spring (MAM), the AOD tendency was positive over the Yangtze River Delta, northern China and the western Tibetan Plateau, (between 0.1 and 0.3, or 2–4 %, per year) and negative over other parts of China. In winter (DJF), when the satellite data coverage is low compared with other seasons (Part 1), irregular patterns of both positive and negative AOD tendencies are observed over China.

For annual aggregates, an increase in the AOD of 0.02 to 0.04 (3–6 %) per year (Fig. 8a) was observed in P1 over SE China. Over western China, the AOD tendencies were slightly negative (between 0 and −0.01 per year). Over northern China they were slightly positive (between 0 and 0.4 per year) for most of the pixels.

In P2 (Figs. 7b and 8b), the AOD tendencies were opposite in sign, compared with P1. The strongest AOD decrease (up to −0.16 per year) was observed over the northern part of SE China in summer. The AOD decrease was slightly lower for other seasons over SE China, while for central and western China the AOD tendencies were close to zero in P2. The relative AOD tendency was between −5 % and −10 % per year in winter and spring over SE China and more than −10 % per year over the Sichuan region in summer and autumn. For annual AOD aggregates, the AOD decrease of −0.02 to −0.04 per year (Fig. 7b), with an average reduction of 30 %–50 % between 2011 and 2017, was observed in P2 over SE China. In the Sichuan and Henan regions the AOD decrease more with a reduction of −0.1 per year. The most negative AOD tendency (more than −10 % per year) is observed in northern China over the eastern inner Mongolia area (Fig. 8b). A small AOD decrease is observed over the Taklamakan Desert; a small AOD increase was observed over the most northeastern part of China. Over other areas, the AOD tendencies in P2 were close to zero.

To reveal more detailed differences in AOD tendencies over China, we apply a similar fits to the annual and seasonal AOD averaged over the selected regions in China. The results are presented and discussed in Sect. 5.4.

5.4 AOD tendencies for the selected regions

5.4.1 Annual AOD tendencies

In Fig. 9 we show the annual AOD combined time series (black line) for China, SE China and the 10 selected regions (corresponding red numbers in the left upper corner of each region), which are defined in Sect. 2 and Fig. 2. For P1 and P2, we also show the AOD tendencies per year and the corresponding relative AOD tendencies. The AOD tendencies and the metrics describing the linear fit for P1 and P2 are summarized in the Appendix (Table A2).

As expected, the AOD tendencies and the AOD relative tendencies were positive in P1 in all of the chosen regions, except for the sparsely populated Tibetan Plateau (region 8), where the AOD is very low and varies very little from year to year. The maximum AOD increase in P1 (0.020, or 4 %, per year) was observed in the Shanghai area (region 2) and the PRD and the Guangxi Province (region 7). In the BTH (region 1), and in Hunan and Guizhou (region 4), dAOD was also high (0.016, or 3 %, per year). Those regions strongly contributed to the AOD increase in SE China (0.014, or 3 %, per year). In regions 1, 2, 4, 7 and for all of China, AOD tendency uncertainties were within 25 % of the AOD tendency in P1. For regions 3, 5, 6 and SE China, the uncertainties related to the tendency estimation were between 25 % and 50 % of the AOD tendency. In regions 8–10, the uncertainties were higher, which can be explained by the low AOD and the lower AOD coverage.

In P2, the AOD decrease was observed in all selected regions and thus also in SE China and all of China. In absolute numbers, dAOD was almost twice as high in P2 as in P1. The most rapid AOD decrease (ca. −0.045, or −8 %, per year) was observed in the central regions of SE China (regions 4 and 6), while for the rest of SE China, including regions 1, 2, 3, 5 and 7, dAOD was about −0.03, or ca. −6 %, per year. For regions 8–10, which are less populated and less industrialized, the dAOD was lower (−0.002, −0.014 and −0.004, respectively, or −2 %, −5 % and −1 % per year). Uncertainties related to the AOD tendency estimation were within 25 % of the AOD tendency in regions 1 to 7, SE China and China. In regions 8 and 10, where AOD is low, the uncertainties were above 50 %.

Figure 9Time series (black line) of the annually averaged AOD combined from ATSR and MODIS for China, SE China and 10 selected regions (see Fig. 2, corresponding red numbers in the left upper corner of each region). Results for the linear fitting of AOD are shown for two periods, P1 (1995–2011) and P2 (2011–2017), marked using grey lines in upper left subplot. Fitting lines (dashed lines) and AOD tendencies (numbers) are shown when the AOD tendency was positive (red) and when AOD tendency was negative (blue). The corresponding relative AOD tendencies for each fit are shown in brackets (in black; %).

Download

Figure 10The AOD seasonal long-time series (solid lines), the linear fits (dashed lines) and the AOD tendency (numbers) for P1 (1995–2011) and P2 (2011–2017; shown using grey lines in the upper left subplot) are shown using different colors for each season (DJF – blue, winter; MAM – purple, spring; JJA – green, summer; and SON – cyan, autumn). The corresponding relative AOD tendencies for each fit are shown in brackets (in black; %).

Download