Model Card: AutoML TimeSeries Predictor for Carbon Dioxide Emission

Model Details

  • Framework: AutoGluon
  • Task: Time Series Regression

Dataset

  • Source: EDGAR GHG
  • Target: target (CO2 emission)
  • Preprocessing Steps:
    • Extracted CO2 only rows.
    • Dropped 'Substance' column.
    • Rearranged the processed dataframe

Training

  • Framework: AutoGluon
  • Preset: prediction_length = 10, freq = "Y"
  • Explored Models: SeasonalNaive, RecursiveTabular, AutoETS, and WeightedEmsemble.

Best Model

  • Model: WeightedAssembly
  • Total Runtime: 42.02 seconds
  • Time to inference: 0.109650 seconds
  • Weighted Quantile Loss (WQL): -0.0665

Notes

Educational use only. Used AutoML for training model, used ChatGPT to debug

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Space using yl0628/co2-emission-time-series 1