Examining the Potential of a Random Forest Derived Cloud Mask from GOES-R Satellites to Improve Solar Irradiance Forecasting
In order for numerical weather prediction (NWP) models to correctly predict solar irradiance reaching the earth’s surface for more accurate solar power forecasting, it is important to initialize the NWP model with accurate cloud information. Knowing where the clouds are located is the first step. Us...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/7/1671 |
| _version_ | 1797571629292716032 |
|---|---|
| author | Tyler McCandless Pedro Angel Jiménez |
| author_facet | Tyler McCandless Pedro Angel Jiménez |
| author_sort | Tyler McCandless |
| collection | DOAJ |
| description | In order for numerical weather prediction (NWP) models to correctly predict solar irradiance reaching the earth’s surface for more accurate solar power forecasting, it is important to initialize the NWP model with accurate cloud information. Knowing where the clouds are located is the first step. Using data from geostationary satellites is an attractive possibility given the low latencies and high spatio-temporal resolution provided nowadays. Here, we explore the potential of utilizing the random forest machine learning method to generate the cloud mask from GOES-16 radiances. We first perform a predictor selection process to determine the optimal predictor set for the random forest predictions of the horizontal cloud fraction and then determine the appropriate threshold to generate the cloud mask prediction. The results show that the random forest method performs as well as the GOES-16 level 2 clear sky mask product with the ability to customize the threshold for under or over predicting cloud cover. Further developments to enhance the cloud mask estimations for improved short-term solar irradiance and power forecasting with the MAD-WRF NWP model are discussed. |
| first_indexed | 2024-03-10T20:43:23Z |
| format | Article |
| id | doaj.art-ddad83e8271145639bfc4229d5454084 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T20:43:23Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-ddad83e8271145639bfc4229d54540842023-11-19T20:34:21ZengMDPI AGEnergies1996-10732020-04-01137167110.3390/en13071671Examining the Potential of a Random Forest Derived Cloud Mask from GOES-R Satellites to Improve Solar Irradiance ForecastingTyler McCandless0Pedro Angel Jiménez1National Center for Atmospheric Research (NCAR), Boulder, CO 80305, USANational Center for Atmospheric Research (NCAR), Boulder, CO 80305, USAIn order for numerical weather prediction (NWP) models to correctly predict solar irradiance reaching the earth’s surface for more accurate solar power forecasting, it is important to initialize the NWP model with accurate cloud information. Knowing where the clouds are located is the first step. Using data from geostationary satellites is an attractive possibility given the low latencies and high spatio-temporal resolution provided nowadays. Here, we explore the potential of utilizing the random forest machine learning method to generate the cloud mask from GOES-16 radiances. We first perform a predictor selection process to determine the optimal predictor set for the random forest predictions of the horizontal cloud fraction and then determine the appropriate threshold to generate the cloud mask prediction. The results show that the random forest method performs as well as the GOES-16 level 2 clear sky mask product with the ability to customize the threshold for under or over predicting cloud cover. Further developments to enhance the cloud mask estimations for improved short-term solar irradiance and power forecasting with the MAD-WRF NWP model are discussed.https://www.mdpi.com/1996-1073/13/7/1671solar power forecastingmachine learningartificial intelligencerandom forestssupervised learningremote sensing |
| spellingShingle | Tyler McCandless Pedro Angel Jiménez Examining the Potential of a Random Forest Derived Cloud Mask from GOES-R Satellites to Improve Solar Irradiance Forecasting Energies solar power forecasting machine learning artificial intelligence random forests supervised learning remote sensing |
| title | Examining the Potential of a Random Forest Derived Cloud Mask from GOES-R Satellites to Improve Solar Irradiance Forecasting |
| title_full | Examining the Potential of a Random Forest Derived Cloud Mask from GOES-R Satellites to Improve Solar Irradiance Forecasting |
| title_fullStr | Examining the Potential of a Random Forest Derived Cloud Mask from GOES-R Satellites to Improve Solar Irradiance Forecasting |
| title_full_unstemmed | Examining the Potential of a Random Forest Derived Cloud Mask from GOES-R Satellites to Improve Solar Irradiance Forecasting |
| title_short | Examining the Potential of a Random Forest Derived Cloud Mask from GOES-R Satellites to Improve Solar Irradiance Forecasting |
| title_sort | examining the potential of a random forest derived cloud mask from goes r satellites to improve solar irradiance forecasting |
| topic | solar power forecasting machine learning artificial intelligence random forests supervised learning remote sensing |
| url | https://www.mdpi.com/1996-1073/13/7/1671 |
| work_keys_str_mv | AT tylermccandless examiningthepotentialofarandomforestderivedcloudmaskfromgoesrsatellitestoimprovesolarirradianceforecasting AT pedroangeljimenez examiningthepotentialofarandomforestderivedcloudmaskfromgoesrsatellitestoimprovesolarirradianceforecasting |