Development of machine learning models for the estimation of diffuse solar radiation in the humid-subtropical climatic region of India

Abstract In this research paper, the investigation focused on developing machine learning models and comparing them with the best empirical models for estimating monthly average diffuse solar radiation. This document shares findings and information gathered from a 3-year study from August 2020 to Ju...

Full description

Saved in:
Bibliographic Details
Main Authors: Farooque Azam, Naiem Akhtar, Shahid Husain
Format: Article
Language:English
Published: Springer 2025-04-01
Series:Discover Atmosphere
Subjects:
Online Access:https://doi.org/10.1007/s44292-025-00030-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850145477312380928
author Farooque Azam
Naiem Akhtar
Shahid Husain
author_facet Farooque Azam
Naiem Akhtar
Shahid Husain
author_sort Farooque Azam
collection DOAJ
description Abstract In this research paper, the investigation focused on developing machine learning models and comparing them with the best empirical models for estimating monthly average diffuse solar radiation. This document shares findings and information gathered from a 3-year study from August 2020 to July 2023, where measurements were taken and analyzed. Two pyranometers, one with a shading ring, were used to measure global and diffuse solar radiation. The study found that the mean values of global, beam, and diffuse solar radiation were 22.39 MJ/m2 day, 14.51 MJ/m2 day, and 7.80 MJ/m2 day, respectively. The average values for the sky-clearness index, diffuse fraction, and diffusion coefficient were also determined as 0.71, 0.36, and 0.25, respectively. To assess the suitability of different models for estimating diffuse solar radiation using only global solar radiation as input, six machine learning models, namely KNN, SVM, RF, GPR, MLP, and XGBoost, and four best empirical models for the region have been evaluated. Various well-established statistical indicators were utilized for a comprehensive evaluation of the models. These statistical metrics were then converted into scaled values to calculate each model’s Global Performance Indicator (GPI). XGBoost model outperformed the others, achieving a GPI value of 6.073.
format Article
id doaj-art-e03dce8ee3dd4029bd45fcadba168e25
institution OA Journals
issn 2948-1554
language English
publishDate 2025-04-01
publisher Springer
record_format Article
series Discover Atmosphere
spelling doaj-art-e03dce8ee3dd4029bd45fcadba168e252025-08-20T02:28:05ZengSpringerDiscover Atmosphere2948-15542025-04-013111710.1007/s44292-025-00030-0Development of machine learning models for the estimation of diffuse solar radiation in the humid-subtropical climatic region of IndiaFarooque Azam0Naiem Akhtar1Shahid Husain2Solar Energy Laboratory, Department of Mechanical Engineering, Zakir Husain College of Engineering and Technology, Aligarh Muslim UniversitySolar Energy Laboratory, Department of Mechanical Engineering, Zakir Husain College of Engineering and Technology, Aligarh Muslim UniversitySolar Energy Laboratory, Department of Mechanical Engineering, Zakir Husain College of Engineering and Technology, Aligarh Muslim UniversityAbstract In this research paper, the investigation focused on developing machine learning models and comparing them with the best empirical models for estimating monthly average diffuse solar radiation. This document shares findings and information gathered from a 3-year study from August 2020 to July 2023, where measurements were taken and analyzed. Two pyranometers, one with a shading ring, were used to measure global and diffuse solar radiation. The study found that the mean values of global, beam, and diffuse solar radiation were 22.39 MJ/m2 day, 14.51 MJ/m2 day, and 7.80 MJ/m2 day, respectively. The average values for the sky-clearness index, diffuse fraction, and diffusion coefficient were also determined as 0.71, 0.36, and 0.25, respectively. To assess the suitability of different models for estimating diffuse solar radiation using only global solar radiation as input, six machine learning models, namely KNN, SVM, RF, GPR, MLP, and XGBoost, and four best empirical models for the region have been evaluated. Various well-established statistical indicators were utilized for a comprehensive evaluation of the models. These statistical metrics were then converted into scaled values to calculate each model’s Global Performance Indicator (GPI). XGBoost model outperformed the others, achieving a GPI value of 6.073.https://doi.org/10.1007/s44292-025-00030-0Diffuse solar radiationHumid-subtropical climateGlobal solar radiationDiffuse fractionMachine learningSky-clearness index
spellingShingle Farooque Azam
Naiem Akhtar
Shahid Husain
Development of machine learning models for the estimation of diffuse solar radiation in the humid-subtropical climatic region of India
Discover Atmosphere
Diffuse solar radiation
Humid-subtropical climate
Global solar radiation
Diffuse fraction
Machine learning
Sky-clearness index
title Development of machine learning models for the estimation of diffuse solar radiation in the humid-subtropical climatic region of India
title_full Development of machine learning models for the estimation of diffuse solar radiation in the humid-subtropical climatic region of India
title_fullStr Development of machine learning models for the estimation of diffuse solar radiation in the humid-subtropical climatic region of India
title_full_unstemmed Development of machine learning models for the estimation of diffuse solar radiation in the humid-subtropical climatic region of India
title_short Development of machine learning models for the estimation of diffuse solar radiation in the humid-subtropical climatic region of India
title_sort development of machine learning models for the estimation of diffuse solar radiation in the humid subtropical climatic region of india
topic Diffuse solar radiation
Humid-subtropical climate
Global solar radiation
Diffuse fraction
Machine learning
Sky-clearness index
url https://doi.org/10.1007/s44292-025-00030-0
work_keys_str_mv AT farooqueazam developmentofmachinelearningmodelsfortheestimationofdiffusesolarradiationinthehumidsubtropicalclimaticregionofindia
AT naiemakhtar developmentofmachinelearningmodelsfortheestimationofdiffusesolarradiationinthehumidsubtropicalclimaticregionofindia
AT shahidhusain developmentofmachinelearningmodelsfortheestimationofdiffusesolarradiationinthehumidsubtropicalclimaticregionofindia