Intelligent Optimization Analysis of the Cholera Epidemic Model

Cholera is a global threat to public health and is an indicator of inequity and lack of social development. By the World Health Organization (WHO), there are 1.3–4.0 million cases of cholera and 21,000–143,000 deaths worldwide due to the infection each year. This innovative work discusses the spread of the cholera virus; the model of this disease was formulated mathematically and solved with the help of the artificial neural network technique. The developed model identified the nonlinear ordinary differential equations represented by susceptible (Sc), vaccinated (Vc), infectious (Ic), recovery (Rc), and concentration of cholera in water (Bc) and the cholera model reference dataset is formed using the explicit Runge–Kutta method. A dataset is arbitrarily used for each cyclic update in Levenberg–Marquardt backpropagation for the numerical study of cholera dynamics. The Levenberg–Marquardt backpropagation is implemented to refine the dataset of the cholera model for training, testing, and validation. The accuracy of the proposed technique is evaluated through mean squared error (MSE), error histograms, merit functions, reliable performance, and regression. These findings underscore the potential of intelligent optimization to enhance the precision of epidemic predictions and inform more effective, targeted cholera control strategies. Thus, intelligent optimization offers a valuable tool for public health response in vulnerable areas.