An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction

Mohamed Chaibi, Mahjoub Benghoulam El, Lhoussaine Tarik, Mohamed Berrada and Abdellah El Hmaidi
Additional contact information
Mohamed Chaibi: Team of Renewable Energy and Energy Efficiency, Department of Physics, Faculty of Science, University of Moulay Ismail, Zitoune, Meknes BP 11201, Morocco
Mahjoub Benghoulam El: Team of Renewable Energy and Energy Efficiency, Department of Physics, Faculty of Science, University of Moulay Ismail, Zitoune, Meknes BP 11201, Morocco
Lhoussaine Tarik: Water and Environmental Engineering Laboratory, Faculty of Science and Technique, Mining, University of Moulay Ismail, Boutalamine, Errachidia BP 509, Morocco
Mohamed Berrada: Laboratory of Mathematical and Computational Modeling, ENSAM, University of Moulay Ismail, Marjane II, Al Mansour, 50000, Meknes BP 15290, Morocco
Abdellah El Hmaidi: Laboratory of Water Sciences and Environmental Engineering, Department of Geology, Faculty of Science, University of Moulay Ismail, Zitoune, Meknes BP 11201, Morocco

Energies, 2021, vol. 14, issue 21, 1-19

Abstract: Machine learning (ML) models are commonly used in solar modeling due to their high predictive accuracy. However, the predictions of these models are difficult to explain and trust. This paper aims to demonstrate the utility of two interpretation techniques to explain and improve the predictions of ML models. We compared first the predictive performance of Light Gradient Boosting (LightGBM) with three benchmark models, including multilayer perceptron (MLP), multiple linear regression (MLR), and support-vector regression (SVR), for estimating the global solar radiation ( H ) in the city of Fez, Morocco. Then, the predictions of the most accurate model were explained by two model-agnostic explanation techniques: permutation feature importance (PFI) and Shapley additive explanations (SHAP). The results indicated that LightGBM (R 2 = 0.9377, RMSE = 0.4827 kWh/m 2 , MAE = 0.3614 kWh/m 2 ) provides similar predictive accuracy as SVR, and outperformed MLP and MLR in the testing stage. Both PFI and SHAP methods showed that extraterrestrial solar radiation ( H 0 ) and sunshine duration fraction ( SF ) are the two most important parameters that affect H estimation. Moreover, the SHAP method established how each feature influences the LightGBM estimations. The predictive accuracy of the LightGBM model was further improved slightly after re-examination of features, where the model combining H 0 , SF , and RH was better than the model with all features.

Keywords: solar radiation; support-vector regression; light gradient boosting; multilayer perceptron; permutation feature importance; Shapley additive explanations (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
https://www.mdpi.com/1996-1073/14/21/7367/pdf (application/pdf)
https://www.mdpi.com/1996-1073/14/21/7367/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:14:y:2021:i:21:p:7367-:d:672782

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().