Numerical Weather Prediction (NWP) Model Forecasts
This dataset provides granular, multi-model weather forecasts for multiple days, including temperature, wind, precipitation, cloud cover, and severe weather probabilities for specific locations and times. It is ideal for energy load forecasting, storm preparation, and operational planning, offering standardized outputs from leading NWP models such as GFS, NAM, HRRR, and ECMWF.
Sample rows
preview · 8 of 200 rows · all 16 columns| forecast_idstring | model_namestring | cloud_cover_percentinteger | is_operationalboolean | forecast_run_datetimedatetime | forecast_valid_datetimedatetime | location_latitudefloat | location_longitudefloat | location_namestring | temperature_celsiusfloat | wind_speed_mpsfloat | wind_direction_degreesinteger | precipitation_mmfloat | severe_weather_probabilityfloat | forecast_horizon_hoursinteger | data_sourcestring |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| FCAST-00001 | GFS | 60 | true | 2024-06-01T03:00:00Z | 2024-06-01T06:00:00Z | 40.7128 | -74.006 | New York City | 22.4 | 3.2 | 185 | 2.1 | blank | 3 | NOAA |
| FCAST-00002 | NAM | 20 | true | 2024-06-01T06:00:00Z | 2024-06-01T09:00:00Z | 51.5074 | -0.1278 | London | 17.8 | 4.5 | 215 | 0 | blank | 3 | UK Met Office |
| FCAST-00003 | HRRR | 45 | true | 2024-06-01T09:00:00Z | 2024-06-01T15:00:00Z | 48.8566 | 2.3522 | Paris | 19.5 | 2.7 | 145 | 1.2 | blank | 6 | Météo-France |
| FCAST-00004 | ECMWF | 15 | true | 2024-06-01T12:00:00Z | 2024-06-01T15:00:00Z | -33.8688 | 151.2093 | Sydney | 12.6 | 5.5 | 90 | 0 | blank | 3 | BOM |
| FCAST-00005 | GFS | 25 | true | 2024-06-01T15:00:00Z | 2024-06-01T18:00:00Z | 35.6895 | 139.6917 | Tokyo | 25.3 | 2.9 | 30 | 0 | blank | 3 | JMA |
| FCAST-00006 | NAM | 10 | true | 2024-06-01T18:00:00Z | 2024-06-01T21:00:00Z | 41.9028 | 12.4964 | Rome | 28.7 | 1.4 | 60 | 0 | blank | 3 | Italian Met Service |
| FCAST-00007 | HRRR | 60 | true | 2024-06-02T00:00:00Z | 2024-06-02T06:00:00Z | 37.7749 | -122.4194 | San Francisco | 15.1 | 5.9 | 285 | 0.6 | blank | 6 | NOAA |
| FCAST-00008 | ECMWF | 35 | true | 2024-06-02T03:00:00Z | 2024-06-02T27:00:00Z | 52.52 | 13.405 | Berlin | 18.4 | 3.1 | 135 | 0.3 | blank | 24 | DWD |
| FCAST-00009 | GFS | 10 | true | 2024-06-02T06:00:00Z | 2024-06-02T30:00:00Z | 34.0522 | -118.2437 | Los Angeles | 24.8 | 3.3 | 110 | 0 | blank | 24 | NOAA |
| FCAST-00010 | NAM | 75 | true | 2024-06-02T09:00:00Z | 2024-06-02T33:00:00Z | -23.5505 | -46.6333 | São Paulo | 20.2 | 4.9 | 170 | 1.8 | blank | 24 | INMET |
| FCAST-00011 | HRRR | 80 | true | 2024-06-02T12:00:00Z | 2024-06-02T36:00:00Z | 19.4326 | -99.1332 | Mexico City | 21.7 | 2.5 | 210 | 3.6 | blank | 24 | CONAGUA |
| FCAST-00012 | ECMWF | 25 | true | 2024-06-02T15:00:00Z | 2024-06-02T39:00:00Z | -1.2921 | 36.8219 | Nairobi | 26.2 | 3.7 | 65 | 0 | blank | 24 | KMD |
| FCAST-00013 | GFS | 85 | true | 2024-06-02T18:00:00Z | 2024-06-03T00:00:00Z | 55.7558 | 37.6173 | Moscow | 13.9 | 5.1 | 320 | 4.9 | blank | 6 | Roshydromet |
| FCAST-00014 | NAM | 55 | true | 2024-06-03T00:00:00Z | 2024-06-03T03:00:00Z | 28.6139 | 77.209 | Delhi | 33.1 | 7.2 | 110 | 0.7 | 0.13 | 3 | IMD |
| FCAST-00015 | HRRR | 70 | true | 2024-06-03T03:00:00Z | 2024-06-03T09:00:00Z | -34.6037 | -58.3816 | Buenos Aires | 10.4 | 5.6 | 195 | 2.4 | 0.15 | 6 | SMN |
| FCAST-00016 | ECMWF | 35 | true | 2024-06-03T06:00:00Z | 2024-06-03T18:00:00Z | 59.3293 | 18.0686 | Stockholm | 15.2 | 3.8 | 75 | 0.2 | blank | 12 | SMHI |
| FCAST-00017 | GFS | 20 | true | 2024-06-03T09:00:00Z | 2024-06-03T21:00:00Z | 35.6762 | 139.6503 | Tokyo Center | 27.5 | 2.1 | 55 | 0 | blank | 12 | JMA |
| FCAST-00018 | NAM | 45 | true | 2024-06-03T12:00:00Z | 2024-06-03T24:00:00Z | 47.3769 | 8.5417 | Zurich | 19.1 | 3 | 125 | 0.8 | blank | 12 | MeteoSwiss |
| FCAST-00019 | HRRR | 80 | true | 2024-06-03T15:00:00Z | 2024-06-04T03:00:00Z | -22.9068 | -43.1729 | Rio de Janeiro | 27.8 | 7.3 | 95 | 5.9 | 0.21 | 12 | INMET |
| FCAST-00020 | ECMWF | 85 | true | 2024-06-03T18:00:00Z | 2024-06-04T06:00:00Z | 60.1699 | 24.9384 | Helsinki | 9.7 | 6.1 | 320 | 1.1 | blank | 12 | FMI |
What the 200 rows show
from the 200-row sample- 73%is_
operational = true - 65median cloud_
cover_ percent - 21.4median temperature_
celsius - 5.3median wind_
speed_ mps - 145median wind_
direction_ degrees - 1.8median precipitation_
mm
Median 65, from 0 to 100.
- string 4
- integer 3
- float 6
- datetime 2
- boolean 1
Columns
16 columns in four groups| column | type | description | example |
|---|---|---|---|
| Text 4 columns | |||
forecast_id | string | Unique identifier for each forecast recordunique | FCAST-00001 |
model_name | string | Name of the NWP model used for the forecast (e.g., GFS, NAM, HRRR, ECMWF)GFS · NAM · HRRR · ECMWF | GFS |
location_name | string | Human-readable name of the forecast location (e.g., city, region)optional | New York City |
data_source | string | Source of the forecast data (e.g., NOAA, ECMWF, local agency)optional | NOAA |
| Numbers 9 columns | |||
location_latitude | float | Latitude of the forecast location-90 to 90 | 40.7128 |
location_longitude | float | Longitude of the forecast location-180 to 180 | -74.006 |
temperature_celsius | float | Forecasted air temperature in degrees Celsius-100 to 60 | 22.4 |
wind_speed_mps | float | Forecasted wind speed in meters per second0 or more | 3.2 |
wind_direction_degrees | integer | Forecasted wind direction in degrees (0-359, where 0 is North)0 to 359 | 185 |
precipitation_mm | float | Forecasted precipitation amount in millimeters0 or more | 2.1 |
cloud_cover_percent | integer | Forecasted cloud cover as a percentage (0-100)0 to 100 | 60 |
severe_weather_probability | float | Probability of severe weather (e.g., storms, tornadoes) as a decimal between 0 and 10 to 1 · optional | 0.13 |
forecast_horizon_hours | integer | Number of hours ahead from the forecast run time to the valid time0 or more | 3 |
| Dates and times 2 columns | |||
forecast_run_datetime | datetime | Date and time when the forecast model run was initiated | 2024-06-01T03:00:00Z |
forecast_valid_datetime | datetime | Date and time for which the forecast is valid | 2024-06-01T06:00:00Z |
| True or false 1 column | |||
is_operational | boolean | Indicates if the forecast is from an operational run (true) or experimental (false)optional | true |
Use it for
An energy dashboard
The is_
operational rate and cloud_ cover_ percent by model_ name. Excel, Power BI or Tableau. Why do 146 of 200 rows have is_
operational = true? A class exercise
Hand out the rows and one question. Everyone works from the same 200 rows.
- Forecasts200FCAST-0000160GFSFCAST-0000220NAMFCAST-0002190GFS
A software demo
Believable forecasts with model_
name, forecast_ run_ datetime and forecast_ valid_ datetime to fill a screen in front of a buyer.
This dataset200 rows16 columns
Yours1,000 rows16 columnslocation_latitude: UK only
blueprint · numerical-weather-prediction-nwp-model-forecasts
Behind this dataset
Same schema. As many rows as you need.
These 200 rows came out of a blueprint — 16 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.
Rules it was built with
- Forecast model: GFS (global), NAM (North America), HRRR (high-resolution), ECMWF
- Forecast initialization (run) time and valid time
- Forecast horizon: 1-16 days ahead depending on model
- Temperature forecast: high, low, hourly profile
- Wind speed/direction forecast for wind generation
- Precipitation probability and quantitative precipitation forecast (QPF)
- Cloud cover percentage for solar PV output estimation
- Ensemble forecasts for uncertainty quantification
Open the blueprint in Data Factory
1 credit per row. New accounts start with 25 free credits.
- Exports
- CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
- Licence
- yours to use, including commercially
- API slug
- numerical-weather-prediction-nwp-model-forecasts