YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

🌦️ NOVA Weather

NOVA Weather is a custom weather forecasting neural network trained on historical weather data.

Architecture

Transformer-based time-series model.

Input:

  • Previous 168 hours
  • Multiple weather variables
  • Location embedding
  • Cyclical time features

Output:

  • Next 24 hours
  • Temperature
  • Humidity
  • Dew point
  • Apparent temperature
  • Precipitation
  • Rain
  • Snowfall
  • Pressure
  • Cloud cover
  • Wind speed
  • Wind gusts

V1 Results

Temperature MAE:

0.8590

Temperature RMSE:

1.0353

Training

Historical data: 2018-01-01 through 2025-12-31

Locations: 8

Parameters: 871,584

Data Source

Open-Meteo Historical Weather API.

This is an experimental machine-learning weather forecasting project and is not intended to replace official weather forecasts.

Downloads last month
14
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support