datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
lk-dmc-weather-forecasts-chunkslk-dmc-weather-forecasts-docsweather_forecast_japan
Overview
This dataset contains daily-collected weather forecasts for up to seven days ahead for all the meteorological observatories in Japan, published by the Japan Meteorological Agency (JMA) at https://www.jma.go.jp/bosai/forecast/.
We collect, structurize, and accumulate the prediction since the page is overridden whenever the information is updated.
The data is automatically updated daily using GitHub Actions. Since the actual forecasts are published multiple times a day… See the full description on the dataset page: https://huggingface.co/datasets/jniimi/weather_forecast_japan.sevir_lrweather-forecasts
OpenThomas weather forecasts
Every forecast the OpenThomas weather desk read or
produced, as-of. Pushed daily from the trading box, so each commit is a
timestamped record of what was known when — the leak-free substrate behind
the paper's replay experiments (docs/EXPERIMENTS.md in the
harness repository).
file
what
lines / bytes
data/nwp-guidance-and-settlements.jsonl
as-of daily extremes from seven public NWP models (Open-Meteo previous-runs API) at leads 0-5, plus… See the full description on the dataset page: https://huggingface.co/datasets/openthomas/weather-forecasts.severe-weather-env-gfs-forecast-v1
Severe Weather Environment GFS Forecast v1
This dataset contains compact GFS point-feature rows from severe-weather forecast-map experiments. It is meant for lead-time testing, forecast calibration, and medium-range SPC-style probability research.
This is a research dataset, not operational guidance. It is not an official NOAA, NWS, SPC, or GFS product, and it should not be used as a stand-alone warning or forecast system.
Files
data/gfs_point_forecast.parquet: primary… See the full description on the dataset page: https://huggingface.co/datasets/deepguess/severe-weather-env-gfs-forecast-v1.wids2023_competition_weather_forecasting
WiDS 2023 Weather Forecasting (TsFile format)
Apache TsFile conversion of mirai-ml/wids2023_competition_weather_forecasting. The repository contains both source splits from the same Hugging Face dataset.
Modalities: Time-series.
Overview
The WiDS Datathon 2023 task forecasts the arithmetic mean of the maximum and minimum temperature over the following 14 days for each US location and start date. The source combines weather, climate, forecast-model, and oscillation… See the full description on the dataset page: https://huggingface.co/datasets/THULab/wids2023_competition_weather_forecasting.Pangu-Weather_Forecasts
Pangu-Weather Forecasts for Spectral-Fusion Precipitation Nowcasting
This repository hosts the Pangu-Weather forecast data used in our paper
"Extending Precipitation Nowcasting Horizons via Spectral Fusion of Radar
Observations and Foundation Model Priors" (IJCNN 2026).
Array format
Each forecast step is stored as two NumPy arrays, following Pangu-Weather's native
variable ordering:
*_surface.npy — shape (4, H, W). The 4 surface variables.
*_upper.npy — shape… See the full description on the dataset page: https://huggingface.co/datasets/Onemiss/Pangu-Weather_Forecasts.historical-us-station-weather-forecasts
Historical US station weather forecasts and observations
December 4, 2025–July 12, 2026 · 7,514,981 forecast records · 882,212 observation records · 14 stations · 19 forecast models
Historical weather data, packaged as one complete SQLite database per station. Each file contains the stored forecast runs, full observation history, daily highs and lows, reported high/low evidence, collection coverage and field descriptions. Weather fields are stored in ordinary columns, without… See the full description on the dataset page: https://huggingface.co/datasets/whodisidk/historical-us-station-weather-forecasts.weather-forecasting-challenge
Dataset Description
Data Overview
The WiDS Datathon 2023 focuses on a prediction task involving forecasting sub-seasonal temperatures (temperatures over a two-week period, in our case) within the United States. We are using a pre-prepared dataset consisting of weather and climate information for a number of US locations, for a number of start dates for the two-week observation, as well as the forecasted temperature and precipitation from a number of weather… See the full description on the dataset page: https://huggingface.co/datasets/serenia-science/weather-forecasting-challenge.Weather-Time-Series-ForecastingWeather_Forecast_Dataset
Weather Forecast Dataset
This dataset is ideal for beginners looking to practice machine learning, specifically using classification techniques.
With 2,500 weather observations, it’s a simple yet practical dataset for learning how to predict rainfall based on various weather conditions.
Perfect for use with Python libraries like scikit-learn, this dataset enables experimentation with algorithms such as logistic regression , decision trees , and random forests .
The dataset's… See the full description on the dataset page: https://huggingface.co/datasets/zeeshier/Weather_Forecast_Dataset.weather_forecast
Dataset Card for Dataset Name
This dataset card aims to be a base template for new datasets. It has been generated using this raw template.
Dataset Details
Dataset Description
Curated by: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: [More Information Needed]
Dataset Sources [optional]
Repository: [More… See the full description on the dataset page: https://huggingface.co/datasets/Nursultan2003ch/weather_forecast.weather_forecast_dataNhaBe