The Hybrid Feedback Model: An Exploratory Study of AI-Supported Eco-Digital Twins on Systemic Awareness Among Libyan Students
DOI:
https://doi.org/10.65405/ea5sam52Keywords:
Digital Twin, Generative Artificial Intelligence, Environmental Education, Systems Awareness, LibyaAbstract
Traditional environmental education tools suffer from a severe experiential gap that limits students’ ability to comprehend the complexity and interconnectedness of ecological systems. Although emerging artificial intelligence solutions offer promising alternatives, they remain burdened by issues of accuracy, reliability, and so-called “AI hallucinations.” This study investigates the feasibility of the Hybrid Guided Simulation Framework (HGSF) as an integrative model that combines the rigor of deterministic mathematical models with the flexibility of generative intelligent narratives.
The study employed a quasi-experimental design involving three groups: an experimental group (n = 28) that used the hybrid GEDT system, and two control groups—one using conventional digital learning tools (n = 25) and the other relying on lecture-based instruction (n = 27)—within a university setting in . A minimum viable prototype (MVP) was developed to simulate groundwater management in the using the Unity engine integrated with a large language model (LLM). Quantitative and qualitative data were collected, including awareness assessments, the System Usability Scale (SUS), interaction logs, and in-depth interviews, alongside a two-month follow-up study.
The experimental group demonstrated a statistically significant improvement in systems-awareness levels compared with the two control groups (F = 4.89, p = .034, d = 0.67). The mean usability score (SUS) reached 68.4, corresponding to an “acceptable” level of usability. A detailed analysis of 420 generated responses revealed that 22% contained errors; however, the automated verification layer successfully corrected 83% of these before they reached learners. Follow-up findings indicated a 90% knowledge retention rate, as well as a significant behavioral impact reflected in students’ discussions with their families about water conservation practices (p = .013).
The hybrid model demonstrates tangible cognitive effectiveness and strong technical reliability owing to its dual-layer architecture centered on automated verification. Nevertheless, further improvements to the user interface and the inclusion of reinforcement sessions are recommended to strengthen long-term behavioral impact.
Downloads
References
1.Ajzen, I. (2020). The theory of planned behavior: Frequently asked questions. Human Behavior and Emerging Technologies, 2(4), 314–324. https://doi.org/10.1002/hbe2.195
2 Bangor, A., Kortum, P. T., & Miller, J. T. (2008). An empirical evaluation of the system usability scale. International Journal of Human–Computer Interaction, 24(6), 574–594.
3.Brooke, J. (1996). SUS: A quick and dirty usability scale. In P. Jordan, B. Thomas, & B. Weerdmeester (Eds.), Usability evaluation in industry (pp. 189–194). Taylor & Francis.
4.El-Rawy, M., Batelaan, O., & Al-Arabi, T. (2022). Groundwater depletion in North Africa. Hydrogeology Journal, 30, 1123–1141.
Alnnale, T. (2026). Predictive Governance in Digital Enterprises: An LSTM-Enhanced Deep Learning Framework for Economic Optimization of IT Incident Management Using Enriched Process Logs. Al-Farooq Journal of Sciences, 2(3), 86-113.
5 Hayes, A. F. (2018). Introduction to mediation, moderation, and conditional process analysis: A regression-based approach (2nd ed.). Guilford Press.
6.Kolb, D. A. (2014). Experiential learning: Experience as the source of learning and development (2nd ed.). Pearson Education.
7.Merchant, Z., Goetz, E. T., Cifuentes, L., Keeney-Kennicutt, W., & Davis, T. J. (2014). Effectiveness of virtual reality-based instruction on students' learning outcomes in K-12 and higher education. Computers & Education, 70, 29–40.
8.Radianti, J., Majchrzak, T. A., Fromm, J., & Wohlgenannt, I. (2020). A systematic review of immersive virtual reality applications for higher education: Design elements, lessons learned, and research agenda. Computers & Education, 147, 103777.
Alboueishi, F. A. A. (2026). Efficacy of Curcumin on Inflammatory Biomarkers in Type 2 Diabetes: A Meta-Analysis of Clinical Trials and Animal Studies Systematic Review & Meta-Analysis (PRISMA 2020) Field: Botany & Complementary Medicine. Al-Farooq Journal of Sciences, 2(2), 15-35.
