# The MJO index calculated using the same method aligns well with the 'retrieve\_annual\_training\_data', but there are still significant deviations when compared to the 'retrieve\_daily\_MJO\_obs'

**URL:** <https://forum.ecmwf.int/t/the-mjo-index-calculated-using-the-same-method-aligns-well-with-the-retrieve-annual-training-data-but-there-are-still-significant-deviations-when-compared-to-the-retrieve-daily-mjo-obs/15245>\
**Category:** AI Weather Quest\
**Tags:** technical-questions\
**Created:** [11 August 2026 03:34 UTC](https://forum.ecmwf.int/t/the-mjo-index-calculated-using-the-same-method-aligns-well-with-the-retrieve-annual-training-data-but-there-are-still-significant-deviations-when-compared-to-the-retrieve-daily-mjo-obs/15245 "2026-08-11T03:34:14Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Hailin\_Liu](https://forum.ecmwf.int/letter_avatar_proxy/v4/letter/h/5e9695/32.png) [@Hailin\_Liu](https://forum.ecmwf.int/u/Hailin_Liu)\
**Post date:** [11 August 2026 03:34 UTC](https://forum.ecmwf.int/t/the-mjo-index-calculated-using-the-same-method-aligns-well-with-the-retrieve-annual-training-data-but-there-are-still-significant-deviations-when-compared-to-the-retrieve-daily-mjo-obs/15245/1 "2026-08-11T03:34:14Z")

</div>

After revising the MJO index calculation method using the `retrieve_MJO_projection_data` function provided in the updated AI\_WQ\_package, the MJO index calculated from the ERA5 data (U200, U850, and daily mean TTR, 1979–2026) aligns perfectly with the updated `retrieve_annual_training_data` under the “Training Data — AI\_Weather\_Quest 3.9 documentation”.

However, it still does not align with the `retrieve_daily_MJO_obs` data found under the “Forecast Evaluation — AI\_Weather\_Quest 3.9 documentation”.

What could be the cause of this? It is quite puzzling why the results derived from the exact same dataset and (revised) methodology match one set of official data but fail to match the other. Could this discrepancy be due to a specific calculation detail, or might there be an issue with the files provided on the official website?

Could you please look into this and verify? I would be extremely grateful if you could help clarify this or share any missing details.🌹 🌹 🌹

 ![52dc032f5ac59efd4bc8e2f1f8a7d4e4](https://forum.ecmwf.int/uploads/default/original/2X/7/72f846f9794107459c4e00568b4a216f5130252d.png)

 ![d01e1f5adc4f6435283a93aac53c7abf](https://forum.ecmwf.int/uploads/default/original/2X/5/571ccc3161539a58dedde9443621cadd5da3b520.png)

---

<div class="post-metadata">

**Author:** ![Joshua\_Talib](https://forum.ecmwf.int/user_avatar/forum.ecmwf.int/joshua_talib/32/987_2.png) [@Joshua\_Talib](https://forum.ecmwf.int/u/Joshua_Talib)\
**Post date:** [11 August 2026 12:54 UTC](https://forum.ecmwf.int/t/the-mjo-index-calculated-using-the-same-method-aligns-well-with-the-retrieve-annual-training-data-but-there-are-still-significant-deviations-when-compared-to-the-retrieve-daily-mjo-obs/15245/2 "2026-08-11T12:54:03Z")

</div>

Thanks @Hailin_Liu . This is on my to-do list to solve next week.

Josh

---

<div class="post-metadata">

**Author:** ![Hailin\_Liu](https://forum.ecmwf.int/letter_avatar_proxy/v4/letter/h/5e9695/32.png) [@Hailin\_Liu](https://forum.ecmwf.int/u/Hailin_Liu)\
**Post date:** [12 August 2026 10:41 UTC](https://forum.ecmwf.int/t/the-mjo-index-calculated-using-the-same-method-aligns-well-with-the-retrieve-annual-training-data-but-there-are-still-significant-deviations-when-compared-to-the-retrieve-daily-mjo-obs/15245/3 "2026-08-12T10:41:01Z")

</div>

copy,

Thanks a lot, Joshua.