Search for: All records

We consider a multispecies competition model in a one- and two-dimensional formulation. To solve the problem numerically, we construct a discrete system using finite volume approximation by space with semi-implicit time approximation. The solution of the multispecies competition model converges to the final equilibrium state that does not depend on the initial condition of the system. The final equilibrium state characterizes the survival status of the multispecies system (one or more species survive or no one survives). In real-world problems values of the parameters are unknown and vary in some range. For such problems, the series of Monte Carlo simulations can be used to estimate the system, where a large number of simulations are needed to be performed with random values of the parameters. A numerical solution is expensive, especially for high-dimensional problems, and requires a large amount of time to perform. In this work, to reduce the cost of simulations, we use a deep neural network to fast predict the survival status. Numerical results are presented for different neural network configurations. The comparison with convenient classifiers is presented.