Weather forecasting with AI, Kaggle tips and tricks, dealing with missing data, deep learning with Jesper Dramsch, The Data Scientist Show #040
The Data Scientist Show - Daliana Liu
00:00
The Challenges of Validation in Weather Data
A validation, for sure. It's one of my favourite topics. Every time you have this spetial dimension in your data, you have to be super careful how you separate your data. So whether with a gap between for validation, which makes it less accurate in the spatial dimension, you definitely can have some over fitting there. But then you can at least do it on a different year where you have a bit of a different climate and a bit of different weather, even in the different locations.
Transcript
Play full episode
