Integration of satellite imagery and meteorological data to estimate solar radiation using machine learning models

被引:0
作者
Palacios, Luis Eduardo Ordonez [1 ]
Guerrero, Victor Bucheli [1 ]
Ordonez, Hugo [2 ]
机构
[1] Univ Valle, Santiago De Cali, Colombia
[2] Univ Cauca, Popayan, Colombia
关键词
GOES-13; Meteorological stations; Solar Radiation; Sunshine; Predictive model; NETWORK ENSEMBLE MODEL; PREDICTION; HELIOSAT-2; REGIONS;
D O I
10.3897/jucs.98648
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Knowing the behavior of solar energy is imperative for its use in photovoltaic systems; moreover, the number of weather stations is insufficient. This study presents a method for the integration of solar resource data: images and datasets. For this purpose, variables are extracted from images obtained from the GOES-13 satellite and integrated with variables obtained from meteorological stations. Subsequently, this data integration was used to train solar radiation prediction models in three different scenarios with data from 2012 and 2017. The predictive ability of five regression methods was evaluated, of which, neural networks had the highest performance in the scenario that integrates the meteorological variables and features obtained from the images. The analysis was performed using four evaluation metrics in each year. In the 2012 dataset, an R2 of 0.88 and an RMSE of 90.99 were obtained. On the other hand, in the 2017 dataset, an R2 of 0.92 and an RMSE of 40.97 were achieved. The model integrating data improves performance by up to 4% in R2 and up to 10 points less in the level of dispersion according to RMSE, with respect to models using separate data.
引用
收藏
页码:738 / 758
页数:21
相关论文
共 54 条
  • [1] Acciona, 2021, QUE BEN TIEN EN SOL
  • [2] Prediction of daily global solar radiation using different machine learning algorithms: Evaluation and comparison
    Agbulut, Umit
    Gurel, Ali Etem
    Bicen, Yunus
    [J]. RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2021, 135
  • [3] Agroclima, 2021, SERV MET FED NAC CAF
  • [4] Optimizing the Heliosat-II Method for Surface Solar Irradiation Estimation with GOES Images
    Albarelo, Tommy
    Marie-Joseph, Isabelle
    Primerose, Antoine
    Seyler, Frederique
    Wald, Lucien
    Linguet, Laurent
    [J]. CANADIAN JOURNAL OF REMOTE SENSING, 2015, 41 (02) : 86 - 100
  • [5] Alcaldia de Santiago de Cali, 2021, ABOUT US
  • [6] Solar Irradiance Forecasting Using Deep Neural Networks
    Alzahrani, Ahmad
    Shamsi, Pourya
    Dagli, Cihan
    Ferdowsi, Mehdi
    [J]. COMPLEX ADAPTIVE SYSTEMS CONFERENCE WITH THEME: ENGINEERING CYBER PHYSICAL SYSTEMS, CAS, 2017, 114 : 304 - 313
  • [7] Electricity production based forecasting of greenhouse gas emissions in Turkey with deep learning, support vector machine and artificial neural network algorithms
    Bakay, Melahat Sevgul
    Agbulut, Umit
    [J]. JOURNAL OF CLEANER PRODUCTION, 2021, 285
  • [8] Ballen Doncel, 2018, ESTIMACION IRRADIANC
  • [9] Multi-step ahead forecasting of global solar radiation for arid zones using deep learning
    Chandola, Deeksha
    Gupta, Harsh
    Tikkiwal, Vinay Anand
    Bohra, Manoj Kumar
    [J]. INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND DATA SCIENCE, 2020, 167 : 626 - 635
  • [10] Artificial neural network based model for retrieval of the direct normal, diffuse horizontal and global horizontal irradiances using SEVIRI images
    Eissa, Yehia
    Marpu, Prashanth R.
    Gherboudj, Imen
    Ghedira, Hosni
    Ouarda, Taha B. M. J.
    Chiesa, Matteo
    [J]. SOLAR ENERGY, 2013, 89 : 1 - 16