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
Weather Forecasting
Longer the time scale, you virtually have less training data to train your model on. And that obviously is really problematic, because we're basically starting right in when anthropogenic a climate change is already for gear. But sm w has done some work where they go back to the measured weather predictions and pretend that they predicted on those conditions to the ni tis avertisting gono. This is what we call hind casting in this case. It means you can take one of the variables out of the equation, essentially, and keep it constant. The prediction becomes better over time, but that also means our system completely chan es.
Transcript
Play full episode
