Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A Machine Learning Approach and Methodology for Solar Radiation Assessment Using Multispectral Satellite Images

A Machine Learning Approach and Methodology for Solar Radiation Assessment Using Multispectral... In this paper, machine learning based method for the estimation of solar radiation in earth surface is presented. To design the machine learning model, multispectral (visible and infrared) satellite images of the very high-resolution from multiple locations are considered as primary data. The satellite images in visible and infrared bands, altitude, latitude, longitude, month, day, time, solar zenith angle, solar azimuth angle, viewing zenith angle, and viewing azimuth angle are used as input to the machine learning, while the solar radiation is taken as output variable. The paper specifics the entire procedure, including data collection, pre-processing, and feature selection, as well as the selection of the best machine learning algorithm, measurements, and validation. The impact of each input feature in estimating the solar radiation is also analyzed using correlation methods. SOLCAST datasets are used for Carcassonne city in the France. The analysis of correlations provides how variables are connected or linked. The Pearson correlation, Kendall rank correlation, Spearman correlation, and Phi K correlations are used in the present study and useful correlations exist because they allow us to anticipate future behaviour by relating the relevant parameters (such as azimuth angle, cloud capacity, dew point temp, air temp, DHI, DNI, horizontal component of beam radiation (Ebh), GHI, precipitable water, relative humidity, surface pressure, wind direction, wind speed, zenith, albedo daily). From the correlation results, neural network algorithm has been adopted using most relevant parameters to validate the results. Researchers and scientists may use the method to build high-efficiency solar devices like solar power plants and photovoltaic cells. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Annals of Data Science Springer Journals

A Machine Learning Approach and Methodology for Solar Radiation Assessment Using Multispectral Satellite Images

Verma, Preeti; Patil, Sunil
Annals of Data Science , Volume 10 (4): 26 – Aug 1, 2023
Download PDF
26 pages

Loading next page...
 
/lp/springer-journals/a-machine-learning-approach-and-methodology-for-solar-radiation-yXkJNlltW1
Publisher
Springer Journals
Copyright
Copyright © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2021
ISSN
2198-5804
eISSN
2198-5812
DOI
10.1007/s40745-021-00352-x
Publisher site
See Article on Publisher Site

Abstract

In this paper, machine learning based method for the estimation of solar radiation in earth surface is presented. To design the machine learning model, multispectral (visible and infrared) satellite images of the very high-resolution from multiple locations are considered as primary data. The satellite images in visible and infrared bands, altitude, latitude, longitude, month, day, time, solar zenith angle, solar azimuth angle, viewing zenith angle, and viewing azimuth angle are used as input to the machine learning, while the solar radiation is taken as output variable. The paper specifics the entire procedure, including data collection, pre-processing, and feature selection, as well as the selection of the best machine learning algorithm, measurements, and validation. The impact of each input feature in estimating the solar radiation is also analyzed using correlation methods. SOLCAST datasets are used for Carcassonne city in the France. The analysis of correlations provides how variables are connected or linked. The Pearson correlation, Kendall rank correlation, Spearman correlation, and Phi K correlations are used in the present study and useful correlations exist because they allow us to anticipate future behaviour by relating the relevant parameters (such as azimuth angle, cloud capacity, dew point temp, air temp, DHI, DNI, horizontal component of beam radiation (Ebh), GHI, precipitable water, relative humidity, surface pressure, wind direction, wind speed, zenith, albedo daily). From the correlation results, neural network algorithm has been adopted using most relevant parameters to validate the results. Researchers and scientists may use the method to build high-efficiency solar devices like solar power plants and photovoltaic cells.

Journal

Annals of Data Science – Springer Journals

Published: Aug 1, 2023

Keywords: Solar radiation; Solar power plant; Machine learning algorithm; Multispectral satellite images

References

  • Estimation of solar radiation using artificial neural networks with different input parameters for Mediterranean region of Anatolia in Turkey
    Koca, A; Oztop, HF; Varol, Y; Koca, GO
  • Simulation of global solar radiation based on cloud observations
    Ehnberg, JS; Bollen, MH
  • Construction of a quadratic model using modified Ångstrom coefficients to estimate global solar radiation
    Akinoǧlu, BG; Ecevit, A
  • Use of artificial neural networks for mapping of solar potential in Turkey
    Sözen, A; Arcaklioǧlu, E; Özalp, M; Kanit, EG
  • Artificial Intelligence technique for modelling and forecasting of solar radiation data: a review
    Mellit, A
  • Fog detection using geostationary satellite data: Temporally continuous algorithm
    Lee, JR; Chung, CY; Ou, ML
  • An assessment of GOES-8 imager data quality
    Ellrod, GP; Achutuni, RV; Daniels, JM; Prins, EM; Nelson, JP
  • An overview of GOES-8 diurnal fire and smoke results for SCAR-B and 1995 fire season in South America
    Prins, EM; Feltz, JM; Menzel, WP; Ward, DE
  • Effective accuracy of satellite-derived hourly irradiances
    Zelenka, A; Perez, R; Seals, R; Renné, D
  • Neural network determination of cloud attenuation to estimate insolation using MTSAT-1R data
    Yeom, JM; Han, KS; Kim, YS; Jang, JD
  • Improvement in surface solar irradiance estimation using HRV/MSG data
    Romano, F; Cimini, D; Cersosimo, A; Di Paola, F; Gallucci, D; Gentile, S; Viggiano, M
  • Predicting the unpredictable: an application of machine learning algorithms in indian stock market
    Saini, A; Sharma, A
  • Internet of things, real-time decision making, and artificial intelligence
    Tien, JM
  • Drought assessment and monitoring through blending of multi-sensor indices using machine learning approaches for different climate regions
    Park, S; Im, J; Jang, E; Rhee, J
  • Estimating global solar radiation using artificial neural network and climate data in the south-western region of Algeria
    Hasni, A; Sehli, A; Draoui, B; Bassou, A; Amieur, B
  • Deep learning: hope or hype
    Ahmed, M; Najmul Islam, AKM
  • Wind speed prediction of central region of Chhattisgarh (India) using artificial neural network and multiple linear regression technique: a comparative study
    Verma, M; Ghritlahre, HK; Chandrakar, G
  • Deep learning and implementations in banking
    Hassani, H; Huang, X; Silva, E; Ghodsi, M
  • Machine learning methods for solar radiation forecasting: a review
    Voyant, C; Notton, G; Kalogirou, S; Nivet, ML; Paoli, C; Motte, F; Fouilloy, A
  • Estimating heat storage in urban areas using multispectral satellite data and machine learning
    Hrisko, J; Ramamurthy, P; Gonzalez, JE
  • Comparison of machine learning methods for mapping the stand characteristics of temperate forests using multi-spectral sentinel-2 data
    Ahmadi, K; Kalantar, B; Saeidi, V; Harandi, EK; Janizadeh, S; Ueda, N
  • Using artificial neural networks to estimate solar radiation in Kuwait
    Bou-Rabee, M; Sulaiman, SA; Saleh, MS; Marafi, S
  • Wind source potential assessment using Sentinel 1 satellite and a new forecasting model based on machine learning: a case study Sardinia islands
    Nezhad, MM; Heydari, A; Groppi, D; Cumo, F; Garcia, DA
  • Universally deployable extreme learning machines integrated with remotely sensed MODIS satellite predictors over Australia to forecast global solar radiation: A new approach
    Deo, RC; Şahin, M; Adamowski, JF; Mi, J
  • A novel hybrid model for hourly global solar radiation prediction using random forests technique and firefly algorithm
    Ibrahim, IA; Khatib, T
  • A machine learning approach for estimation of shallow water depths from optical satellite images and sonar measurements
    Vojinovic, Z; Abebe, YA; Ranasinghe, R; Vacher, A; Martens, P; Mandl, DJ; De Zeeuw, R
  • Landslide detection using multi-scale image segmentation and different machine learning models in the higher himalayas
    Tavakkoli Piralilou, S; Shahabi, H; Jarihani, B; Ghorbanzadeh, O; Blaschke, T; Gholamnia, K; Aryal, J
  • Estimation of solar radiation over Turkey using artificial neural network and satellite data
    Şenkal, O; Kuleli, T
  • Satellite derived bathymetry using machine learning and multi-temporal satellite images
    Sagawa, T; Yamashita, Y; Okumura, T; Yamanokuchi, T
  • An artificial neural network ensemble model for estimating global solar radiation from Meteosat satellite images
    Linares-Rodriguez, A; Ruiz-Arias, JA; Pozo-Vazquez, D; Tovar-Pescador, J
  • A machine learning approach to estimation of downward solar radiation from satellite-derived data products: an application over a semi-arid ecosystem in the US
    Zhou, Q; Flores, A; Glenn, NF; Walters, R; Han, B
  • Spatial assessment of solar radiation by machine learning and deep neural network models using data provided by the COMS MI geostationary satellite: a case study in South Korea
    Yeom, JM; Park, S; Chae, T; Kim, JY; Lee, CS
  • Solcast: Validation of a satellite-derived solar irradiance dataset
    Bright, JM
  • A cloud detection algorithm for satellite imagery based on deep learning
    Jeppesen, JH; Jacobsen, RH; Inceoglu, F; Toftegaard, TS
  • Cloud detection algorithm comparison and validation for operational Landsat data products
    Foga, S; Scaramuzza, PL; Guo, S; Zhu, Z; Dilley, RD; Beckmann, T; Laue, B
  • The influence of cloud cover index on the accuracy of solar irradiance model estimates
    Martins, FR; Silva, SAB; Pereira, EB; Abreu, SL
  • A method for the determination of the global solar radiation from meteorological satellite data
    Cano, D; Monget, JM; Albuisson, M; Guillard, H; Regas, N; Wald, L
  • Estimating incident solar radiation at the surface from images of the Earth transmitted by geostationary satellites: the Heliosat Project
    Diabaté, L; Demarcq, H; Michaud-Regas, N; Wald, L
  • The method Heliosat-2 for deriving shortwave solar radiation from satellite images
    Rigollier, C; Lefèvre, M; Wald, L
  • Solar energy assessment using remote sensing technologies
    Hammer, A; Heinemann, D; Hoyer, C; Kuhlemann, R; Lorenz, E; Müller, R; Beyer, HG
  • On the clear sky model of the ESRA—European Solar Radiation Atlas—with respect to the Heliosat method
    Rigollier, C; Bauer, O; Wald, L
  • Time specific irradiances derived from geostationary satellite images
    Perez, R
  • Mapping of global radiation and cloudiness from Meteosat image data-Theory and ground truth comparisons
    Möser, W; Raschke, E
  • Effects of burning of biomass on satellite estimations of solar irradiation in Brazil
    Pereira, EB; Martins, FR; Abreu, SL; Couto, P; Stuhlmann, R; Colle, S
  • Satellite-derived solar resource maps for Brazil under SWERA project
    Martins, FR; Pereira, EB; Abreu, SL
  • An introduction to Meteosat second generation (MSG)
    Schmetz, J; Pili, P; Tjemkes, S; Just, D; Kerkmann, J; Rota, S; Ratier, A
  • Forecasting of wind speed by using three different techniques of prediction models
    Verma, M; Ghritlahre, HK
  • Solar radiation estimations over India using Meteosat satellite images
    Polo, J; Zarzalejo, LF; Cony, M; Navarro, AA; Marchante, R; Martin, L; Romero, M
  • Conversion function between the Linke turbidity and the atmospheric water vapor and aerosol content
    Ineichen, P
  • Global solar radiation prediction using hybrid online sequential extreme learning machine model
    Hou, M; Zhang, T; Weng, F; Ali, M; Al-Ansari, N; Yaseen, ZM
  • Assessment of SVM, empirical and ANN based solar radiation prediction models with most influencing input parameters
    Meenal, R; Selvakumar, AI
  • Global solar radiation prediction using hybrid online sequential extreme learning machine model
    M Hou, T Zhang, F Weng, M Ali, N Al-Ansari, ZM Yaseen
  • Assessment of SVM, empirical and ANN based solar radiation prediction models with most influencing input parameters
    R Meenal, AI Selvakumar
  • Integration of distributed energy resources in power systems: implementation, operation and control
    citation_title=Integration of distributed energy resources in power systems