Contact
Contact
Featured products
Menu item
Prospect
Quick estimate of PV site's solar potential
Menu item
Evaluate
Data, design & PV simulation in one solution
Menu item
Monitor
Real-time PV output assessment
Menu item
Forecast
Solar power output forecast for up to 14 days
More about products
Other solutions
Menu item
Analyst
Simplified & unified solar data management
Menu item
Integrations
Automate delivery of Solargis data
Menu item
Solarmaps
Assess weather impact on PV performance
Menu item
PV Components Catalog
Technical specifications of PV components
Menu item
Use cases
How we support entire PV plant lifecycle
Solar Resource & Meteo Assessment
Detailed solar resource validation and assessment
Site Adaptation of Solargis Models
Combining satellite data with on-site measurements
Quality Control of Solar & Meteo Measurements
Correction of errors in ground-measured data
Customized GIS Data
Customized Solargis GIS data for your applications
PV Energy Yield Assessment
Estimated energy uncertainties and related data inputs
PV Performance Assessment
Energy estimate for refinancing or asset acquisition
PV Variability & Storage Optimization Study
Understand output variability across wide geo regions
Regional Solar Energy Potential Study
Identification of locations for solar power plants
More about services
Menu item
Prospect
Quick estimate of PV site's solar potential
Menu item
Evaluate
Data, design & PV simulation in one solution
Menu item
Monitor
Real-time PV output assessment
Menu item
Forecast
Solar power output forecast for up to 14 days
Menu item
Integrations
Automate delivery of Solargis data
Our expertise
How our technology works
Historical data: validation and accuracy
How we validate our datasets and models
Forecast data: validation and accuracy
Validation of GHI and PVOUT forecasts
Methodology
How we transform science into technology
Knowledge base
Release notes
Success stories
Blog
Ebooks & Whitepapers
Webinars
Solargis in media
Publications
Free Maps & GIS Data
Collaterals
About Solargis
Partners
Events
ISO Certification
Careers
Solargis Platform
Solargis Platform
Prospect
Prospect
Evaluate
Evaluate
English
Español
简体中文
Slovensky
HomeTechnology
Validation study detailsGHI validation statisticsPVOUT validation statistics

As PV power grows in the global energy mix, forecast accuracy has never mattered more. Reliable GHI and PVOUT predictions help grid operators maintain stability, asset owners avoid penalties, and traders optimize their strategies.

Validation study details#

This validation study evaluates the accuracy of solar and PVOUT forecasts by comparing forecasted values with satellite-based data.

  • Locations: 153 global sites across all continents
  • Horizons: Hour-ahead (nowcasting) and day-ahead
  • Results are grouped by major climate zones: Temperate, cold, arid, tropical, and polar
  • Metrics: Bias, Mean Absolute Deviation (MAD), and Root Mean Square Deviation (RMSD)

PVOUT accuracy statistics in this validation study are based on the following configuration:

  • Geometry: Fixed (one angle)
  • Azimuth (orientation): 0° or 180° depending on hemisphere
  • Tilt: Optimal for given location
  • Installed capacity: 10,000 kW
  • PV module technology: CSI

Detailed PV configuration parameters can be found here ->

GHI represents the total solar irradiance incident on a horizontal surface and is the primary meteorological driver of PV power output. Validating GHI forecast accuracy is therefore a critical first step in assessing the overall quality of the forecasting system.

See the numbers behind Solargis GHI forecasts. Hour-ahead and day-ahead accuracy validated across 153 global sites in all major climate zones.

GHI validation statistics

Hour-ahead (nowcast) accuracy

What we did

  • Generated hour-ahead GHI forecasts using Solargis's internal Cloud Motion Vector (CMV) model, which tracks cloud movement from satellite imagery.
  • Validated forecasts against satellite-based reference GHI for 153 globally distributed sites, covering all major climate zones.
  • Compared accuracy at hourly and 15-minute temporal resolutions using data from 2025.
  • Calculated Bias, MAD, and RMSD as standard accuracy indicators, both globally and per climate zone.

Results we obtained

GHI Hourly 15-min
Average Bias -0.18% -0.18%
Average MAD 4.87% 5.39%
Average RMSD 8.58% 9.58%

Full results by climate zone ->

Conclusions

  • Forecast accuracy is better for hourly than for 15-minute data, primarily due to temporal aggregation effects that smooth short-term variability.
  • Arid regions achieve the best performance due to stable, clear-sky conditions.
  • Temperate and cold climates show moderate errors driven by variable cloud cover and frontal systems.
  • Tropical and polar regions exhibit the highest errors, caused by convective activity, rapid cloud formation, low sun angles, and seasonal extremes.

Day-ahead accuracy

What we did

  • Generated day-ahead GHI forecasts (approximately 24–48 hours ahead) using Numerical Weather Prediction (NWP) models.
  • Validated the same 153 global sites at hourly and 15-minute resolutions using 2025 data.
  • Compared results with hour-ahead accuracy to quantify the effect of extended forecast horizon on accuracy.

Results we obtained

GHI Hourly 15-min
Average Bias 0.56% 0.57%
Average MAD 6.15% 6.61%
Average RMSD 10.11% 10.89%

Full results by climate zone ->

Conclusions

  • Accuracy is lower compared to hour-ahead forecasts due to the longer prediction horizon.
  • Arid regions achieve the best performance due to stable conditions.
  • Tropical regions perform worst due to convective cloud formation.
  • Polar regions show lower accuracy, partly influenced by limited sample size.
  • Temperate and cold climates show moderate errors.

PVOUT is the electrical power produced by a PV system when sunlight is converted into electricity by PV modules. GHI is the primary input for PVOUT, but accuracy also depends on PV system configuration parameters such as module tilt and orientation, installed capacity, shading conditions, and system losses.

See the numbers behind Solargis PVOUT forecasts. Hour-ahead and day-ahead accuracy validated across 153 global sites in all major climate zones.

PVOUT validation statistics

Hour-ahead (nowcast) accuracy

What we did

  • Transformed hour-ahead GHI forecasts into PVOUT forecasts using the same fixed PV system configuration.
  • Validated accuracy for all 153 sites, comparing with hour-ahead results to quantify the horizon effect.
  • Calculated Bias, MAD, and RMSD both globally and per climate zone, at hourly and 15-minute resolution.
  • Additionally analyzed minimum and maximum MAD across sites to quantify variability in forecast performance.

Results we obtained

PVOUT Hourly 15-min
Average Bias -0.15% -0.15%
Average MAD 4.89% 5.40%
Average RMSD 8.66% 9.68%

Full results by climate zone ->

Conclusions

  • Overall PVOUT and GHI accuracy patterns are very similar, as GHI is the primary input to PVOUT.
  • Bias is close to zero across all climate zones, but average bias alone does not reflect full forecast quality — MAD is the most important indicator as it captures the typical magnitude of deviations regardless of direction.
  • Best hour-ahead PVOUT accuracy is achieved in arid zones and worst in polar and tropical zones.

Day-ahead accuracy

What we did

  • Transformed day-ahead GHI forecasts into PVOUT forecasts using the same fixed PV system configuration.
  • Validated accuracy for all 153 sites, comparing with hour-ahead results to quantify the horizon effect.
  • Analyzed MAD min/max variability across sites to support realistic accuracy expectations for operational use.

Results we obtained

PVOUT Hourly 15-min
Average Bias 1.08% 1.08%
Average MAD 6.27% 6.70%
Average RMSD 10.49% 11.24%

Full results by climate zone ->

Conclusions

  • Day-ahead PVOUT accuracy is slightly worse than hour-ahead.
  • The day-ahead horizon is the most critical for electricity market participation, grid planning, and battery storage optimization.
  • Forecast accuracy can differ significantly by site — both the average MAD and the variability expressed by minimum and maximum values should be considered when evaluating expected performance.

Read the full validation study