Hi, the OMI data is from 2019 to 2020, but the TROPOMI data not.
$ aws s3 ls s3://drivendata-competition-airathon-public-eu/no2/train/tropomi/ --no-sign-request
PRE 2019/
$ aws s3 ls s3://drivendata-competition-airathon-public-eu/no2/train/omi/ --no-sign-request
PRE 2019/
PRE 2020/
BTW, it is better to use the S5P-PAL data. Could you help us update the data? Thanks.
Thanks for bringing this up @zxdawn ! Will look into this and update on any actions we take later this week.
You’re welcome @cszc
In case you want to know what’s the difference between the S5P-PAL (V2.2) and older version, you can check this new paper.
As mentioned in that paper, “a general increase of the tropospheric NO2 columns over polluted scenes of order 15 %”
And, KNMI colleges are encouraging scientists to use the reprocessed data (V2.2), because that can give a better view of COVID without the differences caused by different versions.
That may be why the developers of this competition only include the old version of TROPOMI data.
Anyway, hope the new data will be useful for the competition 
Hi again @zxdawn . Just to give you an update, we’ve updated the s3 buckets with the Hi-Res TROPOMI data, which should cover the missing period. Thanks again for bringing that to our attention.
The S5P-PAL dataset also looks like it could be valuable, but we have a few concerns. Namely, will it be available on an ongoing-basis/for the validation period? If you’d like to see it approved, please fill out the official data request form: NASA Airathon: Data Approval Request Form. It’d be great if you could address the question about availability there.
Thanks again!