Scientific machine learning in ecological systems: A study on the predator-prey dynamics

TL;DR

This paper applies Neural ODEs and UDEs to model predator-prey dynamics in ecology, demonstrating that UDEs outperform Neural ODEs in accuracy and robustness, especially with noisy data, and introduces the forecasting breakdown point.

Contribution

The study introduces the use of Neural ODEs and UDEs for ecological modeling, highlighting UDEs' superior performance and robustness in noisy conditions, with extensive hyperparameter analysis.

Findings

UDEs outperform Neural ODEs in accuracy and robustness.

UDEs effectively recover underlying dynamics with less data.

UDEs maintain performance under high noise levels.

Abstract

In this study, we apply two pillars of Scientific Machine Learning: Neural Ordinary Differential Equations (Neural ODEs) and Universal Differential Equations (UDEs) to the Lotka Volterra Predator Prey Model, a fundamental ecological model describing the dynamic interactions between predator and prey populations. The Lotka-Volterra model is critical for understanding ecological dynamics, population control, and species interactions, as it is represented by a system of differential equations. In this work, we aim to uncover the underlying differential equations without prior knowledge of the system, relying solely on training data and neural networks. Using robust modeling in the Julia programming language, we demonstrate that both Neural ODEs and UDEs can be effectively utilized for prediction and forecasting of the Lotka-Volterra system. More importantly, we introduce the forecasting breakdown point: the time at which forecasting fails for both Neural ODEs and UDEs. We observe how UDEs outperform Neural ODEs by effectively recovering the underlying dynamics and achieving accurate forecasting with significantly less training data. Additionally, we introduce Gaussian noise of varying magnitudes (from mild to high) to simulate real-world data perturbations and show that UDEs exhibit superior robustness, effectively recovering the underlying dynamics even in the presence of noisy data, while Neural ODEs struggle with high levels of noise. Through extensive hyperparameter optimization, we offer insights into neural network architectures, activation functions, and optimizers that yield the best results. This study opens the door to applying Scientific Machine Learning frameworks for forecasting tasks across a wide range of ecological and scientific domains.