Skip to content

Dataset · solarbench

SKIPP'D sky images and solar power generation

solarbench/SKIPPD

Over a million records with sky images and tabular data on solar energy generation for short-term forecasting.

What's inside

The dataset contains 1 to 10 million records combining sky images (image modality) and tabular photovoltaic power generation metrics (tabular). Prepared by a research group (Nie et al., 2023) and published in Solar Energy specifically for short-term solar generation forecasting tasks.

What you can do with it

  • Training multimodal models for short-term solar power plant generation forecasting
  • Cloud cover and cloud motion recognition from sky images
  • Benchmarking time series forecasting algorithms with visual features
Size
1M–10M rows
Downloads this month
1.4K
Likes
22

How to load it

from datasets import load_dataset

ds = load_dataset("solarbench/SKIPPD")