Explainability of a Deep Neural Network Model for Prediction of Solar Panels Generation: Comparative Study
Journal of Automation, Mobile Robotics and Intelligent Systems · 25.03.2026 · 79-84
DOI: 10.14313//jamris-2026-008 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Automation, Mobile Robotics and Intelligent Systems, online erschienen am 25.03.2026. Verfasst von Rosalís Amador García und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
The explainability methods LIME, SHAP, Integrated Gradients and Sailency Maps were compared to explain the predictions of a deep learning model trained to predict the electricity generation of a photovoltaic park. These methods allow analyzing the relative importance of the input features for each prediction. The quality of the explanations generated was evaluated using the fidelity and continuity metrics, before and after applying perturbations to the data.
Zitieren
APA
García, R. A., Lorenzo, M. M. G., & Pérez, R. B. (2026). Explainability of a Deep Neural Network Model for Prediction of Solar Panels Generation: Comparative Study. Journal of Automation, Mobile Robotics and Intelligent Systems, 79-84. https://doi.org/10.14313//jamris-2026-008
Vancouver
García RA, Lorenzo MMG, Pérez RB. Explainability of a Deep Neural Network Model for Prediction of Solar Panels Generation: Comparative Study. Journal of Automation, Mobile Robotics and Intelligent Systems. 2026:79-84. doi:10.14313//jamris-2026-008
BibTeX
@article{Garca2026,
author = {García, Rosalís Amador and Lorenzo, María Matilde García and Pérez, Rafael Bello},
title = {Explainability of a Deep Neural Network Model for Prediction of Solar Panels Generation: Comparative Study},
journal = {Journal of Automation, Mobile Robotics and Intelligent Systems},
year = {2026},
pages = {79--84},
doi = {10.14313//jamris-2026-008}
}
EUVIMED