Mathematical Analysis and Modeling of Ebola Virus Dynamics via Optimal Control and Neural Network Paradigms

TL;DR

This paper presents a fractional-order Ebola virus model with neural network predictions, analyzing disease dynamics, stability, and control strategies, achieving high accuracy and identifying key transmission factors.

Contribution

It introduces a novel fractional-order model with neural network-based prediction for Ebola, including stability analysis and optimal control strategies, which is a new approach in this context.

Findings

Safe burial reduces morbidity-mortality by 86.5%.

Neural network predicts Ebola spread with over 99% accuracy.

Transmission rate and incubation period are most sensitive parameters.

Abstract

Ebola virus disease is a severe hemorrhagic fever with rapid transmission through infected fluids and surfaces. We develop a fractional-order model using Caputo derivatives to capture memory effects in disease dynamics. An eight-compartment structure distinguishes symptomatic, asymptomatic, and post-mortem transmission pathways. We prove global well-posedness, derive the basic reproduction number $\mathcal{R}_0$, and establish stability theorems. Sensitivity analysis shows $\mathcal{R}_0$ is most sensitive to transmission rate, incubation period, and deceased infectivity. Treatment-safe burial synergy achieves 86.5\% morbidity-mortality control, with safe burial being most effective. Our disease-informed neural network achieves near-perfect predictive accuracy ($R^2$: 0.991-0.999, 99.1-99.9\% accuracy), closely matching real epidemic behavior.