Modeling systems with machine learning based differential equations

Abstract:

The pbkp_rediction of behavior in dynamical systems, is frequently associated to the design of models. When a time series obtained from observing the system is available, the task can be performed by designing the model from these observations without additional assumptions or by assuming a preconceived structure in the model, with the help of additional information about the system. In the second case, it is a question of adequately combining theory with observations and subsequently optimizing the mixture. In this work, we proposes the design of time-continuous models of dynamical systems as solutions of differential equations, from non-uniformly sampled or noisy observations, using machine learning techniques. The proposed approach, for design of these models, is simple to interpret and implement computationally and its performance is shown with both, several simulated data sets and experimental data from Hare–Lynx population and Coronavirus 2019 outbreak. The results suggest its usefulness in the case of synthetic or real data, uniformly or non-uniformly sampled.

Año de publicación:

2022

Keywords:

• Continuous models
• Machine learning
• TIME SERIES

Fuente:

scopus