A Fractional-Order SIQRS–AI Framework for Modeling Ebola Virus Transmission in Human–Animal Systems with Post-Mortem Infectivity

Ebola Virus Disease remains a major public health challenge in Sub-Saharan Africa due to its high fatality rate, zoonotic spillover, post-mortem infectivity, and limited healthcare infrastructure. In this study, a novel fractional-order SIQRS epidemic model based on the Caputo derivative is developed to investigate the transmission dynamics of Ebola in interacting human and animal populations. The proposed framework incorporates quarantine, temporary immunity, natural mortality, disease-induced deaths, and corpse-mediated transmission, thereby capturing key biological and behavioral mechanisms influencing outbreak evolution. Positivity, boundedness, and well-posedness of the system are established, followed by rigorous derivation of the basic reproduction number using the next-generation matrix method. Local and global stability properties of the disease-free and endemic equilibria are analyzed using fractional linearization theory, Mittag–Leffler stability criteria, and Lyapunov-based techniques. To enhance parameter identification, forecasting accuracy, and control optimization under data uncertainty, Artificial Intelligence methodologies are integrated into the mechanistic model. A hybrid fractional–AI architecture is proposed for dynamic calibration, spatial risk assessment, and adaptive intervention design. Numerical simulations based on the fractional Adams– Bashforth–Moulton scheme validate the analytical results and demonstrate the influence of memory effects, quarantine efficiency, burial safety, and AI-assisted transmission reduction on epidemic trajectories. Sensitivity and bifurcation analyses further identify dominant transmission pathways and critical control parameters. The results indicate that fractional memory and adaptive AI-guided interventions play decisive roles in suppressing epidemic peaks, reducing persistence, and minimizing cumulative mortality. The proposed framework provides a unified mathematical and data-driven platform for evidence-based Ebola prevention and control in vulnerable regions.