An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction

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 M...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mohamed Chaibi, EL Mahjoub Benghoulam, Lhoussaine Tarik, Mohamed Berrada, Abdellah El Hmaidi
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	solar radiation support-vector regression light gradient boosting multilayer perceptron permutation feature importance Shapley additive explanations Technology T
Acceso en línea:	https://doaj.org/article/b747539a9fcd4b4291320360fb351d14
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b747539a9fcd4b4291320360fb351d14
record_format	dspace
spelling	oai:doaj.org-article:b747539a9fcd4b4291320360fb351d142021-11-11T16:04:57ZAn Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction10.3390/en142173671996-1073https://doaj.org/article/b747539a9fcd4b4291320360fb351d142021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/21/7367https://doaj.org/toc/1996-1073Machine 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 (<i>H</i>) 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<sup>2</sup> = 0.9377, RMSE = 0.4827 kWh/m<sup>2</sup>, MAE = 0.3614 kWh/m<sup>2</sup>) 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 (<i>H</i><sub>0</sub>) and sunshine duration fraction (<i>SF</i>) are the two most important parameters that affect <i>H</i> 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 <i>H</i><sub>0</sub>, <i>SF</i>, and <i>RH</i> was better than the model with all features.Mohamed ChaibiEL Mahjoub BenghoulamLhoussaine TarikMohamed BerradaAbdellah El HmaidiMDPI AGarticlesolar radiationsupport-vector regressionlight gradient boostingmultilayer perceptronpermutation feature importanceShapley additive explanationsTechnologyTENEnergies, Vol 14, Iss 7367, p 7367 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	solar radiation support-vector regression light gradient boosting multilayer perceptron permutation feature importance Shapley additive explanations Technology T
spellingShingle	solar radiation support-vector regression light gradient boosting multilayer perceptron permutation feature importance Shapley additive explanations Technology T Mohamed Chaibi EL Mahjoub Benghoulam Lhoussaine Tarik Mohamed Berrada Abdellah El Hmaidi An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction
description	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 (<i>H</i>) 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<sup>2</sup> = 0.9377, RMSE = 0.4827 kWh/m<sup>2</sup>, MAE = 0.3614 kWh/m<sup>2</sup>) 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 (<i>H</i><sub>0</sub>) and sunshine duration fraction (<i>SF</i>) are the two most important parameters that affect <i>H</i> 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 <i>H</i><sub>0</sub>, <i>SF</i>, and <i>RH</i> was better than the model with all features.
format	article
author	Mohamed Chaibi EL Mahjoub Benghoulam Lhoussaine Tarik Mohamed Berrada Abdellah El Hmaidi
author_facet	Mohamed Chaibi EL Mahjoub Benghoulam Lhoussaine Tarik Mohamed Berrada Abdellah El Hmaidi
author_sort	Mohamed Chaibi
title	An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction
title_short	An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction
title_full	An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction
title_fullStr	An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction
title_full_unstemmed	An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction
title_sort	interpretable machine learning model for daily global solar radiation prediction
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b747539a9fcd4b4291320360fb351d14
work_keys_str_mv	AT mohamedchaibi aninterpretablemachinelearningmodelfordailyglobalsolarradiationprediction AT elmahjoubbenghoulam aninterpretablemachinelearningmodelfordailyglobalsolarradiationprediction AT lhoussainetarik aninterpretablemachinelearningmodelfordailyglobalsolarradiationprediction AT mohamedberrada aninterpretablemachinelearningmodelfordailyglobalsolarradiationprediction AT abdellahelhmaidi aninterpretablemachinelearningmodelfordailyglobalsolarradiationprediction AT mohamedchaibi interpretablemachinelearningmodelfordailyglobalsolarradiationprediction AT elmahjoubbenghoulam interpretablemachinelearningmodelfordailyglobalsolarradiationprediction AT lhoussainetarik interpretablemachinelearningmodelfordailyglobalsolarradiationprediction AT mohamedberrada interpretablemachinelearningmodelfordailyglobalsolarradiationprediction AT abdellahelhmaidi interpretablemachinelearningmodelfordailyglobalsolarradiationprediction
_version_	1718432436351664128

An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction

Ejemplares similares