Journal of Engineering in Industrial Research

h-index: 18     i10-index: 25

AI Bridges Theory and Practice: 18% Efficient SIS ‎Solar Cells via Defect-Tuned ZnO/TiO₂/p-Si structure

Document Type : Original Research Article

Authors

A. Bouriche 1, 2
C.E. Benouis 1, 2
M. Benhaliliba 1, 2
K. Dris 1, 2, 3

1 Film Device Fabrication-Characterization and Application FDFCA Research Group USTOMB, 31130, Oran, Algeria

2 Physics Faculty, USTOMB University POBOX 1505 31130, Mnaouer Oran Algeria

3 ‎3Laboratoire d’études Physiques des matériaux, Université des Sciences et de la Technologie d’Oran Mohamed Boudiaf USTO-MB, El ‎M’naouer, BP 1505, 31000 Oran, Algeria

https://doi.org/10.48309/jeires.2025.519634.1207
Abstract
Persistent efficiency limitations and manufacturing challenges in silicon photovoltaics necessitate innovative strategies. This study introduces an artificial intelligence AI-driven optimization framework for n-ZnO/TiO₂/p-Si solar cells using semiconductor-insulator-semiconductor (SIS) heterojunction engineering. A hybrid deep learning model DeepSeek combined with Bayesian-optimized SCAPS-1D simulations, tuned critical parameters: ZnO thickness, TiO₂/Si interface defects, and p-Si doping. The AI-optimized design achieved 16.93% power conversion efficiency (PCE) under AM1.5G illumination, closely aligning with the predicted 17.99%. Key innovations include an 80 nm ZnO layer to minimize resistive losses and enhance carrier extraction, paired with ultra-low TiO₂/Si interface defect density (5×10¹¹ cm⁻²). The SIS architecture employs TiO₂ as an electron transport layer and ZnO as a hole-blocking layer. AI analysis revealed a Type-II band alignment at the TiO₂/ZnO interface, synergistically enhancing open-circuit voltage (Voc) and fill factor (FF >79%). This defect-aware design suppresses carrier recombination, outperforming conventional PN-junction cells through superior carrier selectivity. The AI-driven workflow reduced computational costs by 15%, offering a scalable pathway for high-efficiency photovoltaics. By bridging theoretical modelling with experimental feasibility, this work highlights AI’s transformative potential in accelerating material discovery and device optimization. These advancements position AI as a cornerstone for next-generation, cost-effective solar technologies, accelerating the global transition to sustainable energy solutions.

Graphical Abstract

AI Bridges Theory and Practice: 18% Efficient SIS ‎Solar Cells via Defect-Tuned ZnO/TiO₂/p-Si structure

Keywords

SIS solar cell
AI-driven optimization
&lrm
SCAPS-1D simulation
Power &lrm
conversion efficiency

OPEN ACCESS

©2025 The author(s). This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit: http://creativecommons.org/licenses/by/4.0/

[1]. T. Ahmad, D. Zhang, A critical review of comparative global historical energy consumption and future demand: The story told so far, Energy Reports, 2020, 6, 1973-1991. [Crossref], [Google Scholar], [Publisher]
[2]. F. Kaka, M. Keshav, P.C. Ramamurthy, Optimising the photovoltaic parameters in donor–acceptor–acceptor ternary polymer solar cells using Machine Learning framework, Solar Energy, 2022, 231, 447-457. [Crossref], [Google Scholar], [Publisher]
[3]. M. Benhaliliba, M.D. Kaya, S. Özçelik, C. Benouis, K. Dris, Fabrication and characterization of WS2/AlN/Si SIS heterojunction for emergent material photovoltaic applications, Applied Physics A, 2025, 131, 269. [Crossref], [Google Scholar], [Publisher]
[4]. K. Dasgupta, A. Mondal, S. Ray, U. Gangopadhyay, Mathematical modelling of a novel hetero-junction dual SIS ZnO-Si-SnO solar cell, Silicon, 2022, 14, 3329-3338. [Crossref], [Google Scholar], [Publisher]
[5]. K. Dasgupta, S. Bose, A. Mondal, S. Jana, U. Gangopadhyay, Fabrication and mathematical modelling of a ITO-Al2O3-Si SIS solar cell, Silicon, 2022, 14, 11963-11977. [Crossref], [Google Scholar], [Publisher]
[6]. M.A. Shameli, S.R. Mirnaziry, L. Yousefi, A thin-film sis solar cell based on distributed silicon nanoparticles, 2021 29th Iranian Conference on Electrical Engineering (ICEE), IEEE, 2021, pp. 816-820. [Crossref], [Google Scholar], [Publisher]
[7]. S.O. Malumi, T. Malumi, M.O. Osiele, A. Ekpekpo, I.L. Ikhioya, Enhance and performance evolution of silver-doped titanium dioxide dye-sensitized solar cells using different dyes, Journal of Engineering in Industrial Research, 2023, 4, 189-200. [Crossref], [Google Scholar], [Publisher]
[8] A. Belbia, K. Dris, M. Benhaliliba, and A. Ayeshamariam, Insertion of the MnSnI₃ and CsGeI₃ two absorber layers in order to perform the photovoltaic behavior of the perovskite solar cell, J. Eng. Innov. Res. Sci., vol. 6, no. 3, pp. 195–211, May 2025. [Crossref], [Publisher]
[9]. M. Benhaliliba, C. Benouis, Effect of Nitrogen Gas Pressure on Properties of Sputtered Layer-based Au/ZnO/Si/Au Photodiode: Occurrence of p-type ZnO Semiconductor Material, Semiconductors, 2024, 58, 750-761. [Crossref], [Google Scholar], [Publisher]
[10]. Y. Duan, J.S. Edwards, Y.K. Dwivedi, Artificial intelligence for decision making in the era of Big Data–evolution, challenges and research agenda, International journal of information management, 2019, 48, 63-71. [Crossref], [Google Scholar], [Publisher]
[11]. A. Kopka, N. Grashof, Artificial intelligence: catalyst or barrier on the path to sustainability?, Technological Forecasting and Social Change, 2022, 175, 121318. [Crossref], [Google Scholar], [Publisher]
[12]. C. Chauhan, V. Parida, A. Dhir, Linking circular economy and digitalisation technologies: A systematic literature review of past achievements and future promises, Technological Forecasting and Social Change, 2022, 177, 121508. [Crossref], [Google Scholar], [Publisher]
[13]. D. Edler, T. Ribakova, The impact of industrial robots on the level and structure of employment in Germany—A simulation study for the period 1980–2000, Technological Forecasting and Social Change, 1994, 45, 255-274. [Crossref], [Google Scholar], [
Journal of Engineering in Industrial Research
Volume 6, Issue 4
Summer 2025
Pages 282-297

  • Receive Date 12 July 2025

Home

A-Z Journals

Indexing and Abstracting

Editorial Board

Guide for Authors

Submit Manuscript

Contact Us