# NASA Airathon

**URL:** https://community.drivendata.org/c/airathon/51.md

[Latest](https://community.drivendata.org/latest.md) · [Categories](https://community.drivendata.org/categories.md)

---

## [About the NASA Airathon category](https://community.drivendata.org/t/about-the-nasa-airathon-category/6975)

<div class="topic-metadata">

**Author:** [@glipstein](https://community.drivendata.org/u/glipstein)\
**Replies:** 0

</div>

This category is for posts about the NASA Airathon: Predict Air Quality competition. Please keep all posts here specific to the competition.

---

## [Retrieving data for real time analysis](https://community.drivendata.org/t/retrieving-data-for-real-time-analysis/7670)

<div class="topic-metadata">

**Author:** [@gziz](https://community.drivendata.org/u/gziz)\
**Replies:** 0\
**Last updated:** [April 27, 2022, 5:04pm UTC](https://community.drivendata.org/t/retrieving-data-for-real-time-analysis/7670 "2022-04-27T17:04:10Z")

</div>

I would like to use the model I built for testing on real time data. Nevertheless, I can only seem to find on Earth Data and other sources that the most recent data for MCD19A2 as of now (April 27) is from April 14. Alm…

---

## [Can this algorithms work for a specific city?](https://community.drivendata.org/t/can-this-algorithms-work-for-a-specific-city/7579)

<div class="topic-metadata">

**Author:** [@gziz](https://community.drivendata.org/u/gziz)\
**Replies:** 1\
**Last updated:** [April 4, 2022, 3:53pm UTC](https://community.drivendata.org/t/can-this-algorithms-work-for-a-specific-city/7579 "2022-04-04T15:53:32Z")

</div>

The granules size is 12,000 km by 12,000 km, I would love to try using what I learned in this competition for a specific city. Wouldn’t the fact that a granule size covers multiples cities even states make the prediction…

---

## [Solution for the challenge](https://community.drivendata.org/t/solution-for-the-challenge/7572)

<div class="topic-metadata">

**Author:** [@air\_hack](https://community.drivendata.org/u/air_hack)\
**Replies:** 1\
**Last updated:** [April 4, 2022, 3:47pm UTC](https://community.drivendata.org/t/solution-for-the-challenge/7572 "2022-04-04T15:47:51Z")

</div>

Just wanted to know if the best solution will be published or not Thanks

---

## [Where to get satellite data](https://community.drivendata.org/t/where-to-get-satellite-data/7551)

<div class="topic-metadata">

**Author:** [@gziz](https://community.drivendata.org/u/gziz)\
**Replies:** 1\
**Last updated:** [March 24, 2022, 5:42pm UTC](https://community.drivendata.org/t/where-to-get-satellite-data/7551 "2022-03-24T17:42:32Z")

</div>

Once the competition has ended, I’d like to know if there’s an API/Platform where I can get the same type of satellite data as the one from the competition. Thanks in advance!

---

## [Is it available to get the test label after the competition?](https://community.drivendata.org/t/is-it-available-to-get-the-test-label-after-the-competition/7545)

<div class="topic-metadata">

**Author:** [@FunnyEngineer](https://community.drivendata.org/u/FunnyEngineer)\
**Replies:** 1\
**Last updated:** [March 24, 2022, 5:38pm UTC](https://community.drivendata.org/t/is-it-available-to-get-the-test-label-after-the-competition/7545 "2022-03-24T17:38:00Z")

</div>

I am a Ph.D. student from UT and would like to keep working on this topic after the competition closed since these topics are quite interesting. Just wondering will the test data will be available for download. Thanks!

---

## [Goddard Earth Observing System unavailable](https://community.drivendata.org/t/goddard-earth-observing-system-unavailable/7531)

<div class="topic-metadata">

**Author:** [@andreaRapuzzi](https://community.drivendata.org/u/andreaRapuzzi)\
**Replies:** 3\
**Last updated:** [March 23, 2022, 6:45am UTC](https://community.drivendata.org/t/goddard-earth-observing-system-unavailable/7531 "2022-03-23T06:45:43Z")

</div>

Hi there, all the links provided for the Goddard Earth Observing System seem unavailable. Is this a transient problem? Thanks in advance!! Andrea

---

## [(Short-term) Forecasting or (Concurrent) Estimation?](https://community.drivendata.org/t/short-term-forecasting-or-concurrent-estimation/7299)

<div class="topic-metadata">

**Author:** [@sukantabasu](https://community.drivendata.org/u/sukantabasu)\
**Replies:** 3\
**Last updated:** [March 20, 2022, 6:38pm UTC](https://community.drivendata.org/t/short-term-forecasting-or-concurrent-estimation/7299 "2022-03-20T18:38:20Z")

</div>

In the problem description, it has been mentioned that: “Remember that for each observation, you may only use input values that are available before this time.” “Remember that you are not allowed to use future data, so…

---

## [Model building (one or multiple)](https://community.drivendata.org/t/model-building-one-or-multiple/7534)

<div class="topic-metadata">

**Author:** [@cm818116](https://community.drivendata.org/u/cm818116)\
**Replies:** 1\
**Last updated:** [March 20, 2022, 6:11pm UTC](https://community.drivendata.org/t/model-building-one-or-multiple/7534 "2022-03-20T18:11:08Z")

</div>

Dear staff: According to the problem description, only using one model to predict the test data from three areas is allowed, and using multiple models(e.g. 3) to separately predict three areas then returning predictions…

---

## [Data Extraction and Processing Times](https://community.drivendata.org/t/data-extraction-and-processing-times/7489)

<div class="topic-metadata">

**Author:** [@kovila](https://community.drivendata.org/u/kovila)\
**Replies:** 3\
**Last updated:** [March 14, 2022, 9:04pm UTC](https://community.drivendata.org/t/data-extraction-and-processing-times/7489 "2022-03-14T21:04:55Z")

</div>

Hello, just for info, i would like to know, on average, how long it’s taking you to download satellite data and processing it into the correct format for it be ready to feed into the model as features. Thank you!

---

## [Request understanding of the data files](https://community.drivendata.org/t/request-understanding-of-the-data-files/7306)

<div class="topic-metadata">

**Author:** [@ankitdid](https://community.drivendata.org/u/ankitdid)\
**Replies:** 1\
**Last updated:** [February 16, 2022, 8:56pm UTC](https://community.drivendata.org/t/request-understanding-of-the-data-files/7306 "2022-02-16T20:56:43Z")

</div>

Hello, The file names of downloaded files from your repository is: tropomi 2019 : 20190107T042626\_tropomi\_tpe\_0.nc 20190107T060756\_tropomi\_tpe\_0.nc 20190107T074926\_tropomi\_dl\_0.nc 20190107T212126\_tropomi\_la\_0.nc B…

---

## [Data files and train labels](https://community.drivendata.org/t/data-files-and-train-labels/7403)

<div class="topic-metadata">

**Author:** [@nayeemmz](https://community.drivendata.org/u/nayeemmz)\
**Replies:** 5\
**Last updated:** [February 25, 2022, 9:28pm UTC](https://community.drivendata.org/t/data-files-and-train-labels/7403 "2022-02-25T21:28:19Z")

</div>

I am looking at the downloaded data files and trying to match the filename with the train labels. For example, in Train\_label.csv the first line is 2018-02-01T08:00:00Z,3S31A,11.4 Then I am looking at the training dat…

---

## [Can we use location, grid\_id as features](https://community.drivendata.org/t/can-we-use-location-grid-id-as-features/7459)

<div class="topic-metadata">

**Author:** [@adityakumarsinha](https://community.drivendata.org/u/adityakumarsinha)\
**Replies:** 4\
**Last updated:** [March 8, 2022, 6:07pm UTC](https://community.drivendata.org/t/can-we-use-location-grid-id-as-features/7459 "2022-03-08T18:07:43Z")

</div>

Hi All To be sure can we use location as feature for training and inference, or create different model location wise? Is it acceptable? Similarly can we use grid\_ids or generic encoding of grid\_id derived from data as …

---

## [Los Angeles time zone](https://community.drivendata.org/t/los-angeles-time-zone/7440)

<div class="topic-metadata">

**Author:** [@jessethegreat](https://community.drivendata.org/u/jessethegreat)\
**Replies:** 4\
**Last updated:** [March 7, 2022, 11:44pm UTC](https://community.drivendata.org/t/los-angeles-time-zone/7440 "2022-03-07T23:44:01Z")

</div>

Isn’t Los Angeles GMT minus 8?

---

## [New Approved Datasets and Blog Post Tutorials](https://community.drivendata.org/t/new-approved-datasets-and-blog-post-tutorials/7433)

<div class="topic-metadata">

**Author:** [@cszc](https://community.drivendata.org/u/cszc)\
**Replies:** 0\
**Last updated:** [March 4, 2022, 1:52am UTC](https://community.drivendata.org/t/new-approved-datasets-and-blog-post-tutorials/7433 "2022-03-04T01:52:20Z")

</div>

Hello Airathon Community! We’ve got just over two weeks left on the Airathon competitions. To help you perfect your models, we’ve added some new resources. Approved Datasets Requests for new datasets are now closed, but…

---

## [Grid ID's that are in submission\_format but not in train\_labels](https://community.drivendata.org/t/grid-ids-that-are-in-submission-format-but-not-in-train-labels/7428)

<div class="topic-metadata">

**Author:** [@bryanyahir03](https://community.drivendata.org/u/bryanyahir03)\
**Replies:** 3\
**Last updated:** [March 3, 2022, 5:32am UTC](https://community.drivendata.org/t/grid-ids-that-are-in-submission-format-but-not-in-train-labels/7428 "2022-03-03T05:32:43Z")

</div>

I was making some simple analysis on both files and I notice that there are 68 unique grids\_id in submission\_format but only 66 unique grids\_id in train\_labels. The two missing grid\_ids in train\_files corresponds to 7F1D…

---

## [Relevant papers or blogs](https://community.drivendata.org/t/relevant-papers-or-blogs/7319)

<div class="topic-metadata">

**Author:** [@divyad](https://community.drivendata.org/u/divyad)\
**Replies:** 3\
**Last updated:** [February 25, 2022, 8:18pm UTC](https://community.drivendata.org/t/relevant-papers-or-blogs/7319 "2022-02-25T20:18:10Z")

</div>

Hello, Can anyone suggest me any relevant papers or blogs useful for this competition as working with satellite images is a challenging domain for me. Thanks.

---

## [Global Forecast System (GFS) data](https://community.drivendata.org/t/global-forecast-system-gfs-data/7231)

<div class="topic-metadata">

**Author:** [@sukantabasu](https://community.drivendata.org/u/sukantabasu)\
**Replies:** 9\
**Last updated:** [February 24, 2022, 11:18pm UTC](https://community.drivendata.org/t/global-forecast-system-gfs-data/7231 "2022-02-24T23:18:27Z")

</div>

Hi, The data for 2017-2019 are not available on TDDS server: https://www.ncei.noaa.gov/thredds/catalog/model-gfs-g3-anl-files/catalog.html The https server does not work: https://www.ncei.noaa.gov/data/global-forecas…

---

## [Looking for teammates for NASA Airathon](https://community.drivendata.org/t/looking-for-teammates-for-nasa-airathon/7309)

<div class="topic-metadata">

**Author:** [@sukyong](https://community.drivendata.org/u/sukyong)\
**Replies:** 1\
**Last updated:** [February 23, 2022, 4:22pm UTC](https://community.drivendata.org/t/looking-for-teammates-for-nasa-airathon/7309 "2022-02-23T16:22:02Z")

</div>

Hello everyone, There are only one month left for this competition, and I am looking for teammates who can work together. I have strong background in data analysis and environmental science (especially air quality and w…

---

## [Dowloading Data](https://community.drivendata.org/t/dowloading-data/7188)

<div class="topic-metadata">

**Author:** [@smcoder5](https://community.drivendata.org/u/smcoder5)\
**Replies:** 13\
**Last updated:** [February 22, 2022, 8:51pm UTC](https://community.drivendata.org/t/dowloading-data/7188 "2022-02-22T20:51:41Z")

</div>

I am trying to download using boto3 and cloudpathlib in python, but I am getting error “Unable to locate Credentials”, I don’t know why I am getting this error but someone can tell me what is the name of bucket of amazon…

---

## [Satellite data not available for some train/test samples](https://community.drivendata.org/t/satellite-data-not-available-for-some-train-test-samples/7275)

<div class="topic-metadata">

**Author:** [@pereza](https://community.drivendata.org/u/pereza)\
**Replies:** 1\
**Last updated:** [February 17, 2022, 8:28pm UTC](https://community.drivendata.org/t/satellite-data-not-available-for-some-train-test-samples/7275 "2022-02-17T20:28:37Z")

</div>

Hi there! I opened this issue because there are data samples for which there is no satellite (MAIAC or MISR data available). For instance: If you check the submission\_format.csv, there are samples ranging from 2017-01-…

---

## [Clarification on features' dates used for prediction](https://community.drivendata.org/t/clarification-on-features-dates-used-for-prediction/7215)

<div class="topic-metadata">

**Author:** [@lzvam](https://community.drivendata.org/u/lzvam)\
**Replies:** 9\
**Last updated:** [February 4, 2022, 9:41pm UTC](https://community.drivendata.org/t/clarification-on-features-dates-used-for-prediction/7215 "2022-02-04T21:41:57Z")

</div>

it is unclear to me reading the problem description whether we are allowed to use satellite data on the same day of the label value or only from previous dates? for example, for label’s datetime 31st Jan 2019, are we all…

---

## [Final results submission](https://community.drivendata.org/t/final-results-submission/7164)

<div class="topic-metadata">

**Author:** [@air\_hack](https://community.drivendata.org/u/air_hack)\
**Replies:** 3\
**Last updated:** [February 4, 2022, 4:27pm UTC](https://community.drivendata.org/t/final-results-submission/7164 "2022-02-04T16:27:43Z")

</div>

As we are only submitting CSV files with model predictions over testing datasets, this is more like a validation dataset right? During the last days of the competition, the model will be tested against unseen data, right…

---

## [Missing TROPOMI 2020 data](https://community.drivendata.org/t/missing-tropomi-2020-data/7149)

<div class="topic-metadata">

**Author:** [@zxdawn](https://community.drivendata.org/u/zxdawn)\
**Replies:** 3\
**Last updated:** [February 3, 2022, 8:58pm UTC](https://community.drivendata.org/t/missing-tropomi-2020-data/7149 "2022-02-03T20:58:44Z")

</div>

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-airath…

---

## [Finding teammates!](https://community.drivendata.org/t/finding-teammates/7108)

<div class="topic-metadata">

**Author:** [@SwetaX](https://community.drivendata.org/u/SwetaX)\
**Replies:** 8\
**Last updated:** [February 3, 2022, 2:53pm UTC](https://community.drivendata.org/t/finding-teammates/7108 "2022-02-03T14:53:47Z")

</div>

Let’s look for teammates here in this thread!

---

## [Understanding train\_labels time distribution](https://community.drivendata.org/t/understanding-train-labels-time-distribution/7212)

<div class="topic-metadata">

**Author:** [@eyastaifour](https://community.drivendata.org/u/eyastaifour)\
**Replies:** 10\
**Last updated:** [February 2, 2022, 10:27pm UTC](https://community.drivendata.org/t/understanding-train-labels-time-distribution/7212 "2022-02-02T22:27:53Z")

</div>

Hi ! train\_labels’ datetime object Hour varies for different grids - but the competition’s page states: " datetime (string): The UTC datetime of the measurement in the format YYYY-MM-DDTHH:mm:ssZ . A value represents the…

---

## [Strategy to impute missing data?](https://community.drivendata.org/t/strategy-to-impute-missing-data/7226)

<div class="topic-metadata">

**Author:** [@eyastaifour](https://community.drivendata.org/u/eyastaifour)\
**Replies:** 1\
**Last updated:** [February 2, 2022, 2:35pm UTC](https://community.drivendata.org/t/strategy-to-impute-missing-data/7226 "2022-02-02T14:35:59Z")

</div>

Hi all ! I was wondering what your strategies were with regards to the missing data in satellites file. I imagine it is at the very core of the problem statement. I am approaching this challenge as an opportunity to lear…

---

## [What data to access from nasadem planetary computer?](https://community.drivendata.org/t/what-data-to-access-from-nasadem-planetary-computer/7197)

<div class="topic-metadata">

**Author:** [@kar95ar](https://community.drivendata.org/u/kar95ar)\
**Replies:** 4\
**Last updated:** [February 1, 2022, 11:39pm UTC](https://community.drivendata.org/t/what-data-to-access-from-nasadem-planetary-computer/7197 "2022-02-01T23:39:12Z")

</div>

Hello! I was able to understand the overall code to access the data. But I am not sure which areas of interest to access. Are these areas of interests for Los Angeles, Delhi, Taipei? How to get the right co-ordinates?

---

## [Converting Lat/Long to Meters](https://community.drivendata.org/t/converting-lat-long-to-meters/7214)

<div class="topic-metadata">

**Author:** [@eyastaifour](https://community.drivendata.org/u/eyastaifour)\
**Replies:** 1\
**Last updated:** [February 1, 2022, 11:30pm UTC](https://community.drivendata.org/t/converting-lat-long-to-meters/7214 "2022-02-01T23:30:23Z")

</div>

Hi all - I am wondering how to convert Lat/Long from the WKT definitions of a grid (in grid\_metadata) to the format used in the MODIS dataset. I am not familiar with CRS, projections, and i’d apprecaite a pointer. Thanks…

---

## [Understanding MAIAC geolocation](https://community.drivendata.org/t/understanding-maiac-geolocation/7186)

<div class="topic-metadata">

**Author:** [@eyastaifour](https://community.drivendata.org/u/eyastaifour)\
**Replies:** 6\
**Last updated:** [January 31, 2022, 4:26pm UTC](https://community.drivendata.org/t/understanding-maiac-geolocation/7186 "2022-01-31T16:26:10Z")

</div>

I am trying to wrap my head around the available data for this competition, and I have decided to do a bit of exploration. One thing that I’ve done is visualize the values in train\_label.csv on a map - this helps me unde…

[Next page](https://community.drivendata.org/c/airathon/51.md?page=1)
