Explainable AI along with Intelligent Decision-Making for Optimizing Green Synthesis of Nanoparticles Using Medicinal Plants
Computer and Decision Making: An International Journal · 09.11.2026 · 3 (7S) · 118-127
DOI: 10.1922/comdem.v3i7s.19167 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer and Decision Making: An International Journal, online erschienen am 09.11.2026. Verfasst von Ruchita Shrivastava und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Plant-mediated synthesis of metal nanoparticles is attractive because medicinal-plant species phytochemicals can contribute to both reductions along with surface stabilization; however, variable botanical composition as well as processing conditions make reported outcomes difficult to reproduce. This paper proposes an explainable artificial intelligence (XAI) as well as intelligent decision-support framework for optimizing the green synthesis of nanoparticles from medicinal plants. It integrates a critical narrative synthesis of verified studies here in this way with a prospective, multi-objective computational design. Reported empirical findings is used to identify candidate descriptors, measurable quality attributes, data-quality requirements, along with safeguards against misleading optimization. The proposed nature of architecture combines standardized metadata, interpretable baseline models, uncertainty-aware based prediction, feature-attribution analysis, as well as constrained Bayesian recommendation. Its intended outcomes include particle-size consistency, colloidal stability, functional suitability, resource efficiency, along with an explicit account of safety aspects of environmental trade-offs. A published cross-plant dataset is illustrated descriptively, not treated as a controlled experiment or an AI validation dataset herein. The central contribution is a transparent research-decision workflow that makes more on proposed choices traceable to empirical findings along with here more uncertainty rather than to opaque predictive model scores. No new nanoparticles were synthesized, no predictive model was mostly fitted, as well as no improvements in yield, antimicrobial efficacy, or environmental impact here are claimed. The decision-support framework is offered as a testable research based agenda for future laboratory studies with independent external validation.
Zitieren
APA
Shrivastava, R., Diddigi, G., Admuthe, N. B., Dave, L., Kakati, D., Sahu, S. C., & Tamboli, S. P. (2026). Explainable AI along with Intelligent Decision-Making for Optimizing Green Synthesis of Nanoparticles Using Medicinal Plants. Computer and Decision Making: An International Journal, 3(7S), 118-127. https://doi.org/10.1922/comdem.v3i7s.19167
Vancouver
Shrivastava R, Diddigi G, Admuthe NB, Dave L, Kakati D, Sahu SC, et al. Explainable AI along with Intelligent Decision-Making for Optimizing Green Synthesis of Nanoparticles Using Medicinal Plants. Computer and Decision Making: An International Journal. 2026;3(7S):118-127. doi:10.1922/comdem.v3i7s.19167
BibTeX
@article{Shrivastava2026,
author = {Shrivastava, Ruchita and Diddigi, Geeta and Admuthe, Namdeo Bhagwan and Dave, Leena and Kakati, Debashree and Sahu, Subash Chandra and Tamboli, Santosh Purushottam},
title = {Explainable AI along with Intelligent Decision-Making for Optimizing Green Synthesis of Nanoparticles Using Medicinal Plants},
journal = {Computer and Decision Making: An International Journal},
year = {2026},
volume = {3},
number = {7S},
pages = {118--127},
doi = {10.1922/comdem.v3i7s.19167}
}
EUVIMED