# Machine Learning + Ladybug

**URL:** <https://discourse.mcneel.com/t/machine-learning-ladybug/169161>\
**Category:** Grasshopper\
**Tags:** windows, ladybug, grasshopperrhino, machine-learning\
**Created:** [November 14, 2023, 1:08pm UTC](https://discourse.mcneel.com/t/machine-learning-ladybug/169161 "2023-11-14T13:08:29Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Gregor\_Ruta](https://sea3.discourse-cdn.com/mcneel/user_avatar/discourse.mcneel.com/gregor_ruta/32/484857_2.png) [@Gregor\_Ruta](https://discourse.mcneel.com/u/Gregor_Ruta)\
**Post date:** [November 14, 2023, 1:08pm UTC](https://discourse.mcneel.com/t/machine-learning-ladybug/169161/1 "2023-11-14T13:08:30Z")

</div>

Hello World!

I want to train a model from the humongous results from Ladybug to apply it to a larger scale set of inputs.

Does anyone have any tips on how to go about it? I am looking for books, articles and tutorials for similar tasks.

I have seen a general discussion about Neural Networks in GH and will follow up in that topic.

[Recommendations on how to get started with Neural Networks in Grasshopper? - Grasshopper - McNeel Forum](https://discourse.mcneel.com/t/recommendations-on-how-to-get-started-with-neural-networks-in-grasshopper/52989/2)

I am aware about LunchBox, Pug and Owl. I will start by reading the documentation and read tutorials - yet it will be extremely helpful to see a solution to a problem similar to mine.

I have also posted this on Grasshopper forum. Thanks in advance!

Cheers,

Gregor

---

<div class="post-metadata">

**Author:** ![fad095760](https://sea3.discourse-cdn.com/mcneel/user_avatar/discourse.mcneel.com/fad095760/32/628507_2.png) [@fad095760](https://discourse.mcneel.com/u/fad095760)\
**Post date:** [August 16, 2026, 7:39pm UTC](https://discourse.mcneel.com/t/machine-learning-ladybug/169161/3 "2026-08-16T19:39:05Z")

</div>

I have worked on a similar workflow using Ladybug/Honeybee simulation outputs to create a multi-objective dataset. After collecting simulation results and design parameters, I used Python-based ML/data analysis workflows to investigate relationships between inputs and performance indicators. For your case, I would suggest treating Ladybug outputs as your training data and developing a surrogate model to replace expensive simulations.  
I can send my LinkedIn link and see my work , if you would like.
