A Radial Basis Function Neural Network Surrogate for a Four-Dimensional Ecological Population Model with Refuge and Migration
4 affiliations
- 1Department of Mathematics, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Chennai 601103, India
- 2Department of Artificial Intelligence, Amrita School of Artificial Intelligence, Amrita Vishwa Vidyapeetham, Faridabad 121002, India
- 3Department of Library and Information Science, Artificial Intelligence Development Center, Fu Jen Catholic University, New Taipei City 24205, Taiwan
- 4Department of Computer Science and Information Engineering, Fintech and Blockchain Research Center, Asia University, Taichung City 41354, Taiwan
Abstract
This paper presents a Radial Basis Function Neural Network (RBFNN) that approximates the vector field of a four-dimensional prey–migration–predator–superpredator ecological model with prey refuge, considered in deterministic and stochastic formulations. The network is trained directly on the governing equations without the need for any simulated trajectories for training. The network learns the deterministic vector field, and hence analytical verification is carried out for the deterministic model, with a proof of global existence of the solution, a proof of the boundedness of the solution, a classification of five equilibria via the Jacobian matrix, and a proof of local exponential stability of the coexistence equilibrium via a Lyapunov function. The RBFNN is validated by comparing its trajectories to those of the RK45 solver, checking its long-term behavior, performing phase-space analysis, and computing the eigenvalues of the equilibrium and Jacobian of the learned field. For the stochastic formulation, the learned drift is added with explicit noise terms and is compared with the Euler–Maruyama and Milstein methods using a finer-step Milstein method as a reference. The numerical results presented here establish that the RBFNN can be used as an alternative to a deterministic vector field in standard numerical solvers, and that the framework can be used to compare the computational efficiency of the vector field evaluation in more complex dynamical systems where the field evaluation is more costly.
Related
- Peri-Ovarian Mitochondrial Administration Improves Surrogate Markers of Ovarian Function in Aged Rats: Free Versus Alginate-Encapsulated Mesenchymal Stromal Cell-Derived Mitochondria
- Stage Migration, Treatment Patterns, and Machine Learning-Based Prediction of 12-Month Mortality in Lung Adenocarcinoma Across the COVID-19 Era: A SEER Population-Based Study
- Socio-ecological correlates of children’s diet in the first 2 years of life: influence of socio-economic position and migration background in a French birth cohort
- Stable 2-year migration on radiostereometric analysis and improved gait speed and function after bicruciate-retaining TKA: a prospective cohort of 25 patients
- Assessing the associated factors of anxiety and depression among the adult population to harness the demographic dividend in Nepal using the socio-ecological model.
BibTeX
@article{radhakrishnan2026radial,
title = {{A Radial Basis Function Neural Network Surrogate for a Four-Dimensional Ecological Population Model with Refuge and Migration}},
author = {Prabu Radhakrishnan and Soumyendra Singh and Dharminder Chaudhary and Cheng-Chi Lee},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14213853},
url = {https://www.mdpi.com/2227-7390/14/21/3853},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - A Radial Basis Function Neural Network Surrogate for a Four-Dimensional Ecological Population Model with Refuge and Migration
AU - Prabu Radhakrishnan
AU - Soumyendra Singh
AU - Dharminder Chaudhary
AU - Cheng-Chi Lee
PY - 2026
DA - 2026/10/22
JO - Mathematics
DO - 10.3390/math14213853
UR - https://www.mdpi.com/2227-7390/14/21/3853
AB - This paper presents a Radial Basis Function Neural Network (RBFNN) that approximates the vector field of a four-dimensional prey–migration–predator–superpredator ecological model with prey refuge, considered in deterministic and stochastic formulations. The network is trained directly on the governing equations without the need for any simulated trajectories for training. The network learns the deterministic vector field, and hence analytical verification is carried out for the deterministic model, with a proof of global existence of the solution, a proof of the boundedness of the solution, a classification of five equilibria via the Jacobian matrix, and a proof of local exponential stability of the coexistence equilibrium via a Lyapunov function. The RBFNN is validated by comparing its trajectories to those of the RK45 solver, checking its long-term behavior, performing phase-space analysis, and computing the eigenvalues of the equilibrium and Jacobian of the learned field. For the stochastic formulation, the learned drift is added with explicit noise terms and is compared with the Euler–Maruyama and Milstein methods using a finer-step Milstein method as a reference. The numerical results presented here establish that the RBFNN can be used as an alternative to a deterministic vector field in standard numerical solvers, and that the framework can be used to compare the computational efficiency of the vector field evaluation in more complex dynamical systems where the field evaluation is more costly.
SN - 2227-7390
ER -