Assessment of the criteria importance for determining solar panel site potential via machine learning algorithms, a case study Central Anatolia region, Turkey

Fatih Sari and Selmin Ener Rusen

Renewable Energy, 2025, vol. 239, issue C

Abstract: In this study, 16 criteria influencing solar energy potential were identified, and interactions with 1311 existing solar power plants were examined using MaxEnt and Logistic Regression methods. Unlike traditional site suitability studies in the literature, this study determined criterion weights solely based on natural intersections of criteria with locations of existing solar power plants, without artificial weight assignment. Thus, correlations demonstrated by 1311 solar power plants across the 16 criteria were used to create solar energy potential maps for the entire study area. The MaxEnt analysis yielded an AUC value of 0.760, while the LR method calculated an R2 value of 0.7904, indicating high correlation between all points and specific criterion values, with approximately 80 % of the study area's solar energy potential being determined by these criteria. In MaxEnt, criteria such as distance from land use, highways, and power transmission lines were highlighted, while LR showed that temperature-related criteria also significantly influenced potential determination. The study found that 6.21 % of the study area had the highest potential using MaxEnt, and 8.71 % using LR, with Aksaray, Karaman, Ereğli, and Karatay identified as districts with the highest potential. The correlation value between the results of both methods has been calculated as 0.756.

Keywords: MaxEnt; LR; GIS; Solar power plant; Site selection (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960148124022134
Full text for ScienceDirect subscribers only

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:eee:renene:v:239:y:2025:i:c:s0960148124022134

DOI: 10.1016/j.renene.2024.122145

Access Statistics for this article

Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides

More articles in Renewable Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().