Dear Dr Zhan,
Although one reviewer recommended rejecting your manuscript, that reviewer did not identify any concerns that could not be addressed but just noted that “Revisions would be likely to involve considerable additional effort “. Based on your comprehensive responses to all of the reviewer comments/concerns, the manuscript has been substantially improved. I have just a few minor comments regarding your responses (see below) that I would like you to address before the manuscript can be accepted for publication in ACP.

1) Page 9, Lines 37-38; Page 10, Lines 1-6.
“It is noteworthy that the RF-STK model with MOPITT-CO was superior to the model without MOPITT-CO (R2=0.49, RMSE=0.58 mg m-3, and slope=0.60) and the model with the a priori information (R2=0.49, RMSE=0.57 mg m-3, and slope=0.60) based on the site-based cross-validation results (Tables 2 and S4). The performance difference became more apparent in the region-based cross-validation, where the model with MOPITT-CO (R2=0.45, RMSE=0.61 mg m-3, and slope=0.52) clearly outperformed the model without MOPITT (R2=0.32, RMSE=0.69 mg m-3, and slope=0.46). We therefore reasoned that the MOPITT-CO data were essential for the RF-STK model to achieve better predictive performance, especially for the areas without monitoring sites nearby.”
Note that the numbers in that first sentence appear to be incorrect (they differ from what is in Table 2) but even with the correct numbers I don’t see how it is justified to say that the model with MOPITT-CO is “superior” unless you can show this is a significant difference. The region-based difference does show more improvement and the description of this in the second and third sentences is justified.

2) Page 11, Lines 37-38; Page 12, Lines 1-3.
“The trend underestimation by MOPITT-CO might be largely due to the setting that the a priori information was the same across the years”
This sentence is confusing and should be reworded.
3) Page 12, Line 14-18.
“We chose the period of 2013-2016 for this study due to the data availability”.
While I realize that you don’t have data to go earlier than 2013, why not include 2017?
4) Page 12, Line 24.
“Since July of 2018, the TROPOspheric Monitoring Instrument onboard the Sentinel-5P satellite has been providing the CO product at a higher resolution of 7 km × 3.5 km (Borsdorff et al., 2018), which may replace MOPITT-CO in the RF-STK model in order to make predictions at a higher resolution.”

Revise the last part of this sentence to: “which could replace MOPITT-CO in the RF-STK model in order to make predictions for years after 2018 at a higher resolution.”