ORIGINAL RESEARCH article
Front. Energy Res.
Sec. Solar Energy
Volume 13 - 2025 | doi: 10.3389/fenrg.2025.1611429
Potential Analysis and Energy Prediction of Photovoltaic Power Plants using Satellite-Based Remote Sensing and Artificial Intelligence Techniques
Provisionally accepted
Hadis Ghaedrahmati1
Saeed Talebi1
Amirmohammad Moradi2Aref Eskandari3Parviz Parvin1
Mohammadreza Aghaei4*- 1Amirkabir University of Technology, Tehran, Tehran, Iran
- 2Concordia University, Montreal, Quebec, Canada
- 3Iran University of Science and Technology, Tehran, Tehran, Iran
- 4Norwegian University of Science and Technology, Trondheim, Norway
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
photovoltaic (PV) systems have seen significant global growth due to their economic and environmental benefits. However, the output of PV systems is subject to uncertainties arising from factors like unpredictable weather conditions. Given the considerable uncertainty in meteorological data, Geographic Information Systems (GIS) have emerged as effective tools for analyzing such data. This study presents a novel method based on satellite-based remote sensing and artificial intelligence techniques to assess the potential of PV power plants and predict energy generation in different locations. We utilize GIS and the Analytic Hierarchy Process (AHP) in ArcGIS software to evaluate suitable sites for PV systems. Satellite data from global sources is used to analyze PV energy production based on specific geographic coordinates. Several machine learning algorithms, including Random Forest (RF), Support Vector Regression (SVR), Decision Tree (DT), and XGBoost, are applied to predict PV energy production from meteorological variables. The evaluation, using various statistical metrics, shows that the XGBoost algorithm outperforms others, achieving up to 91% accuracy in predicting energy production from PV systems.
Keywords: photovoltaic performance prediction, Energy prediction, remote sensing, satellite imagery in solar energy, artificial intelligence
Received: 14 Apr 2025; Accepted: 19 May 2025.
Copyright: © 2025 Ghaedrahmati, Talebi, Moradi, Eskandari, Parvin and Aghaei. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Mohammadreza Aghaei, Norwegian University of Science and Technology, Trondheim, Norway
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.