EUVIMEDEUVIMED entdecken
Crossref

Sustainable solar energy site suitability using explainable Generative Artificial Intelligence (GenXAI) enhanced MCDM

Mallikarjuna Paramesha, Nitin Liladhar Rane

International Journal of Applied Resilience and Sustainability · 2025

DOI: 10.70593/deepsci.0101008 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Applied Resilience and Sustainability, 2025. Verfasst von Mallikarjuna Paramesha und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sustainable suitability analysis of a site is vital for the sustainable development of solar energy, and it should take into account several environmental and infrastructural factors. Classical GIS-based Multi-Criteria Decision-Making (MCDM) methods, like the MIF method combined with TOPSIS, usually require subjective weights manually set by decision-makers on each criterion that may turn out to be highly biased when intuitively given. In this study, a novel method for the solar farm siting based on explainable Generative Artificial Intelligence (GenXAI) model has been adopted to get the objective optimal weights of MIF criteria. A GIS-based approach along with TOPSIS is utilized in combining 12 climatic, geophysical, and accessibility indicating factors to produce a holistic map of sustainable solar suitability. The interpretability layer of GenXAI increases transparency to the decision process and approximates factors contributions more accurately. Validation of the suitability map with known suitable sites using the Area Under the ROC Curve (AUC) shows that GenXAI -based weighting outperforms manual weighing, even when allowing expert feedback on optimal combination. The AUC of the model, based on traditional MIF weights in, improved from 0.839 to 0.847 and became an even better predictor with weights determined by GenXAI. The results indicate that the interpretability of the generative AI could be applied to MCDM, enhancing the objectivity and accuracy of solar site suitability evaluation, thereby providing a more reliable tool for sustainable energy planning.

Zitieren

APA

Paramesha, M., & Rane, N. L. (2025). Sustainable solar energy site suitability using explainable Generative Artificial Intelligence (GenXAI) enhanced MCDM. International Journal of Applied Resilience and Sustainability. https://doi.org/10.70593/deepsci.0101008

Vancouver

Paramesha M, Rane NL. Sustainable solar energy site suitability using explainable Generative Artificial Intelligence (GenXAI) enhanced MCDM. International Journal of Applied Resilience and Sustainability. 2025. doi:10.70593/deepsci.0101008

BibTeX
@article{Paramesha2025,
  author = {Paramesha, Mallikarjuna and Rane, Nitin Liladhar},
  title = {Sustainable solar energy site suitability using explainable Generative Artificial Intelligence (GenXAI) enhanced MCDM},
  journal = {International Journal of Applied Resilience and Sustainability},
  year = {2025},
  doi = {10.70593/deepsci.0101008}
}
Kostenlos starten →