USING LEARNING MACHINES TO CREATE SOLAR RADIATION MAPS FROM NUMERICAL WEATHER PREDICTION MODELS, GROUND MEASUREMENTS AND SATELLITE IMAGES
Domain:
environment and energygeospatialRecord type:
paper
Creator:
GasPagFerBla
Editor:
Dep
Publisher:
CCSD
Host:
International audience
This paper describes the first steps given in order to develop a methodology to generate solar radiation maps using information from different sources. First, it is based on a meteorological simulation over the area of interest by means of a Numerical Weather Prediction Model. After that, a cluster method is applied to identify zones with similar features; this classification helps the final correction of the map based on a set of historical data from 40 sites. The first section contains an introduction of the work, and the second one collects the description of the methodology and data used. The third section presents the obtained results and validations to finish with conclusions and next works in the last section.
Similar
Transport and Deposition of Saharan Dust Observed from Satellite Images and Ground MeasurementsSelecting a clear-sky model to accurately map solar radiation from satellite imagesQuantifying post logging biomass loss using satellite images and ground measurements in Southeast CameroonAn AI-Driven Machine Learning Framework For Accurate Global Solar Radiation Prediction Using Satellite ImageryDo Low Cost Weather Stations Complement Large Scale Numerical Weather Prediction Models?Poverty Prediction by Using Deep Learning on Satellite Images