Solar Irradiance and Cloud Cover for PV Forecasting
This dataset provides high-resolution solar irradiance measurements (GHI, DNI, DHI) from ground-based sensors alongside satellite-derived cloud cover and motion vectors, enabling accurate short-term and day-ahead photovoltaic (PV) power forecasting. Each record is geo-tagged and time-stamped, supporting advanced analytics, model training, and grid integration studies for renewable energy systems.
Sample rows
preview · 8 of 180 rows · all 16 columns| measurement_idstring | cloud_cover_percentfloat | quality_flagboolean | satellite_sourcestring | site_idstring | site_namestring | latitudefloat | longitudefloat | elevation_mfloat | timestampdatetime | ghi_w_m2float | dni_w_m2float | dhi_w_m2float | cloud_motion_vector_ufloat | cloud_motion_vector_vfloat | forecast_horizon_minutesinteger |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| M0001 | 2.3 | true | GOES-16 | S001 | Phoenix Solar Array | 33.4484 | -112.074 | 331 | 2024-06-10T15:00:00Z | 1157.2 | 1083.4 | 66.1 | 2.1 | 3.2 | 90 |
| M0002 | 5.7 | true | GOES-16 | S002 | Denver High Plateau | 39.7392 | -104.9903 | 1609 | 2024-06-10T15:15:00Z | 1078.5 | 1001.2 | 78.4 | 3.8 | 1.6 | 60 |
| M0003 | 8.2 | true | GOES-17 | S003 | Mauna Loa Observatory | 19.5396 | -155.5781 | 3397 | 2024-06-10T15:30:00Z | 1120.7 | 1048.9 | 59.7 | 5.5 | 4.3 | 45 |
| M0004 | 100 | false | blank | S004 | Null Island Outpost | 0 | 0 | blank | 2024-06-10T15:45:00Z | 0 | 0 | 0 | 0 | 0 | 240 |
| M0005 | 0.4 | true | Meteosat-11 | S005 | Sahara Desert East | 23.4162 | 25.6628 | 112 | 2024-06-10T16:00:00Z | 1189.6 | 1132.4 | 53.7 | 6.3 | 1.2 | 30 |
| M0006 | 26.4 | true | Meteosat-9 | S006 | Berlin City Solar | 52.52 | 13.405 | 34 | 2024-06-10T16:15:00Z | 832.2 | 650.7 | 131.4 | 1.4 | -1.7 | 120 |
| M0007 | 9.1 | true | Himawari-8 | S007 | Tokyo Rooftop Array | 35.6895 | 139.6917 | 40 | 2024-06-10T16:30:00Z | 912.8 | 870 | 78.9 | 7.1 | 2.8 | 15 |
| M0008 | 100 | false | Meteor-M | S008 | Arctic Boundary Station | 78.2232 | 15.6469 | blank | 2024-06-10T17:00:00Z | 0 | 0 | 0 | -5.1 | 7.2 | 1440 |
| M0009 | 3.9 | true | Meteosat-9 | S009 | Cape Town Solar Field | -33.9249 | 18.4241 | 58 | 2024-06-10T17:15:00Z | 1059.4 | 1016.1 | 70.2 | 4.9 | 0.4 | 60 |
| M0010 | 2.7 | true | GOES-16 | S010 | Los Angeles Civic Array | 34.0522 | -118.2437 | 71 | 2024-06-10T17:30:00Z | 1045.3 | 976.5 | 57.3 | 2.4 | -2.1 | 90 |
| M0011 | 6.6 | true | Himawari-8 | S011 | Sydney Opera Solar | -33.8688 | 151.2093 | 24 | 2024-06-10T17:45:00Z | 1012.7 | 960.8 | 63.9 | 3.1 | 1.5 | 30 |
| M0012 | 55.2 | true | EUMETSAT | S012 | London Green Hub | 51.5074 | -0.1278 | 11 | 2024-06-10T18:00:00Z | 621.1 | 430.5 | 168.7 | -1.8 | 0.6 | 75 |
| M0013 | 67.4 | true | Meteor-M | S013 | Moscow Urban Array | 55.7558 | 37.6173 | 156 | 2024-06-10T18:15:00Z | 487.2 | 412.8 | 92.1 | -3.5 | 1.3 | 180 |
| M0014 | 3 | true | GOES-18 | S014 | Rio de Janeiro Array | -22.9068 | -43.1729 | 2 | 2024-06-10T18:30:00Z | 1162 | 1125.7 | 61.4 | 4.5 | 2.9 | 30 |
| M0015 | 19 | true | Meteosat-11 | S015 | New Delhi Solar Testbed | 28.6139 | 77.209 | 216 | 2024-06-10T18:45:00Z | 818.3 | 734.7 | 101.5 | 5.2 | -1.1 | 45 |
| M0016 | 74.1 | true | GOES-18 | S016 | Lima Coastal Station | -12.0464 | -77.0428 | 154 | 2024-06-10T19:00:00Z | 363.4 | 224.1 | 106.6 | -2.6 | 1.7 | 120 |
| M0017 | 100 | false | Meteor-M | S017 | Stationary Platform-01 | -66 | 140 | blank | 2024-06-10T19:15:00Z | 0 | 0 | 0 | 2.6 | -6.7 | 1440 |
| M0018 | 15.7 | true | GOES-16 | S018 | Quito Solar Observatory | -0.1807 | -78.4678 | 2850 | 2024-06-10T19:30:00Z | 1025.5 | 920.2 | 72.3 | 3.7 | 0.2 | 60 |
| M0019 | 100 | false | NOAA-20 | S019 | Siberian Outpost | 66 | 100 | blank | 2024-06-10T19:45:00Z | 0 | 0 | 0 | -7 | 6.1 | 1440 |
| M0020 | 22.1 | true | EUMETSAT | S020 | Madrid Urban Solar | 40.4168 | -3.7038 | 667 | 2024-06-10T20:00:00Z | 871.4 | 779.8 | 112.7 | 2.7 | -0.8 | 45 |
What the 180 rows show
from the 180-row sample- 82%quality_
flag = true - 13.8median cloud_
cover_ percent - 70.5median elevation_
m - 883.9median ghi_
w_ m2 - 814.6median dni_
w_ m2 - 66.2median dhi_
w_ m2
Median 13.8, from 0.0 to 100.0.
- string 4
- integer 1
- float 9
- datetime 1
- boolean 1
Columns
16 columns in four groups| column | type | description | example |
|---|---|---|---|
| Text 4 columns | |||
measurement_id | string | Unique identifier for each measurement recordunique | M0001 |
site_id | string | Unique identifier for the measurement site or station | S001 |
site_name | string | Descriptive name of the measurement site or stationoptional | Phoenix Solar Array |
satellite_source | string | Name or code of the satellite data source used for cloud motion vectors9 sources · optional | GOES-16 |
| Numbers 10 columns | |||
latitude | float | Latitude coordinate of the measurement site-90 to 90 | 33.4484 |
longitude | float | Longitude coordinate of the measurement site-180 to 180 | -112.074 |
elevation_m | float | Elevation of the site in meters above sea leveloptional | 331 |
ghi_w_m2 | float | Global Horizontal Irradiance measured in watts per square meter (W/m^2)0 or more | 1157.2 |
dni_w_m2 | float | Direct Normal Irradiance measured in watts per square meter (W/m^2)0 or more | 1083.4 |
dhi_w_m2 | float | Diffuse Horizontal Irradiance measured in watts per square meter (W/m^2)0 or more | 66.1 |
cloud_cover_percent | float | Estimated cloud cover percentage at the site (0-100%)0 to 100 | 2.3 |
cloud_motion_vector_u | float | East-west (u) component of the cloud motion vector in meters per second (m/s) | 2.1 |
cloud_motion_vector_v | float | North-south (v) component of the cloud motion vector in meters per second (m/s) | 3.2 |
forecast_horizon_minutes | integer | Forecast horizon in minutes (e.g., 0 for nowcast, up to 1440 for day-ahead)0 to 1,440 | 90 |
| Dates and times 1 column | |||
timestamp | datetime | Date and time of the measurement in UTC | 2024-06-10T15:00:00Z |
| True or false 1 column | |||
quality_flag | boolean | Indicates if the measurement passed quality control checks (true = passed, false = failed)optional | true |
Use it for
An energy dashboard
The quality_
flag rate, cloud_ cover_ percent and a breakdown of satellite_ source. Excel, Power BI or Tableau. Why do 147 of 180 rows have quality_
flag = true? A class exercise
Hand out the rows and one question. Everyone works from the same 180 rows.
- Measurements180M00012.3trueM00025.7trueM0004100false
A software demo
Believable measurements with site_
id, site_ name and latitude to fill a screen in front of a buyer.
This dataset180 rows16 columns
Yours1,000 rows16 columnssite_id: UK only
blueprint · solar-irradiance-and-cloud-cover-for-pv-forecasting
Behind this dataset
Same schema. As many rows as you need.
These 180 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
- Timestamp at 1-minute or 15-minute intervals
- GHI (Global Horizontal Irradiance) in W/m², 0-1000 typical
- DNI (Direct Normal Irradiance) for concentrating solar
- DHI (Diffuse Horizontal Irradiance) for cloudy sky conditions
- Cloud cover fraction (0-1) or percentage
- Satellite cloud motion vectors for nowcasting (0-6 hours)
- Clearness index = GHI / extraterrestrial radiation
- PV system DC output forecast (MW) from irradiance
Open the blueprint in Data Factory
1 credit per row. Preview 20 rows free. Buy rows for the full run.
- Exports
- CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
- Licence
- yours to use, including commercially
- API slug
- solar-irradiance-and-cloud-cover-for-pv-forecasting