# Google hurricane forecasting evaluation

**URL:** <https://community.epinowcast.org/t/google-hurricane-forecasting-evaluation/372>\
**Category:** Uncategorized\
**Created:** [5 January 2026 16:28 UTC](https://community.epinowcast.org/t/google-hurricane-forecasting-evaluation/372 "2026-01-05T16:28:27Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![samabbott](https://dub1.discourse-cdn.com/flex005/user_avatar/community.epinowcast.org/samabbott/32/5_2.png) [@samabbott](https://community.epinowcast.org/u/samabbott)\
**Post date:** [5 January 2026 16:28 UTC](https://community.epinowcast.org/t/google-hurricane-forecasting-evaluation/372/1 "2026-01-05T16:28:27Z")

</div>

I really enjoyed this recent preprint on hurricane forecasting from Google folks: [https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/how-we-re-supporting-better-tropical-cyclone-prediction-with-ai/skillful-joint-probabilistic-weather-forecasting-from-marginals.pdf](https://storage.googleapis.com/deepmind-media/DeepMind.com/Blog/how-we-re-supporting-better-tropical-cyclone-prediction-with-ai/skillful-joint-probabilistic-weather-forecasting-from-marginals.pdf)

aside from the interesting modelling etc what really struck me was the similar but different probablistic forecasting metrics that they are using to evaluate their model. This relates to [Do your evaluations have enough power? - #4 by samabbott](https://community.epinowcast.org/t/do-your-evaluations-have-enough-power/366/4) in that it is clear other fields have different standards of practice.

In particular I liked their different approaches for pooling CRPS and their calibration measure (centred on 1).

 ![Screenshot 2026-01-05 at 16.26.31](https://europe1.discourse-cdn.com/flex005/uploads/epinowcast/original/1X/c914e905cadafc8c4a49af1add3c7e56b0be7b7d.png)

They also talk about a “scorecard” which is very ML and reminded me of this: [Baseball Stats, Model Cards, and Forecasting Performance](https://community.epinowcast.org/t/baseball-stats-model-cards-and-forecasting-performance/322)

I was wondering about seeing if they might like to speak somewhere about this - epinowcast might not be a goer but perhaps we could get them to come and give a talk at LSHTM if they are up the road at Kings cross?