Name
Abstract | ||
|---|---|---|
High levels of surface ozone (O
<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub>
) pollution threaten human and environmental health. Chongqing, a mountainous municipality located in southwest China, is exposed to serious O
<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub>
pollution and requires more studies. Due to its complex terrain and always foggy weather, it is difficult to maintain many
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in situ</i>
sites in Chongqing, and chemical transportation model (CTM) simulations are also challenged. The recently launched (in 2017) Sentinel-5p satellite provides O
<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub>
columns with advanced spatiotemporal resolution. Without the dependence on CTMs, we linked O
<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub>
columns and surface monitoring data from 2019 to 2021 in virtue of a deep forest machine learning model. Compared with another widely used machine learning model and previous studies, our results showed great advantages in estimating surface O
<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub>
on a daily scale. Validated against
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in situ</i>
sites in Chongqing, averaged
<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula>
of cross validations reached 0.9, while the root-mean-squared error (RMSE) and mean bias error (MBE) were 13.57 and
<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$0.37~\mu \text {g}/\text {m}^{3}$ </tex-math></inline-formula>
, respectively. We found out that the model performance is associated with the relative height difference between training sites and the test site. The model performed stably when the height difference was lower than 200 m, but obvious performance degradation was seen when the height difference is exceeding 400 m. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1109/LGRS.2021.3119699 | IEEE Geoscience and Remote Sensing Letters |
Keywords | DocType | Volume |
Deep forest,machine learning,mountainous areas,O₃ pollution,Sentinel-5p,TROPOspheric Monitoring Instrument (TROPOMI) | Journal | 19 |
ISSN | Citations | PageRank |
1545-598X | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Songyan Zhu | 1 | 0 | 2.37 |
| Hao Zhu | 2 | 0 | 0.34 |
| Jian Xu | 3 | 21 | 10.93 |
| Qiaolin Zeng | 4 | 0 | 2.70 |
| Dejun Zhang | 5 | 0 | 0.34 |
| Xiaoran Liu | 6 | 0 | 0.34 |