Eric Forgoston

Lyra Zhornyak, Eric Forgoston, M. Ani Hsieh

We present the first method to directly use a learned continuous Lagrangian to forecast the dynamics of systems governed by partial differential equations, exploiting the inherent conservative structure to achieve stable long-range predictions. We develop an optimization-based integrator that minimizes the squared Euler--Lagrange residual via a mesh-free near-symplectic construction on local space-time patches. Different from integrators for analytical models, integrators for learned models should decouple model error (phase error) from integration error (conservation error). By relying on optimization rather than time-stepping, we bypass the global coupling inherent to fixed discretizations, which slows time- and space-stepping and complicates learning. Our method scales linearly with domain size via Jacobi iteration, and places no structural requirements on the learned network, allowing it to be coupled with existing physics-guided machine learning (ML) methods. We validate our approach on a learned representation of a double pendulum, a one-dimensional wave equation, and a two-dimensional wave equation. Our method achieves error comparable to classical symplectic methods while generalizing to spatially varying dynamics and arbitrary boundary conditions without retraining.

Sepideh Vafaie, Deepak Bal, Michael A. S. Thorne et al.

For years, a main focus of ecological research has been to better understand the complex dynamical interactions between species which comprise food webs. Using the connectance properties of a widely explored synthetic food web called the cascade model, we explore the behavior of dynamics on Lotka-Volterra ecological systems. We show how trophic efficiency, a staple assumption in mathematical ecology, produces systems which are not persistent. With clustering analysis we show how straightforward inequalities of the summed values of the birth, death, self-regulation and interaction strengths provide insight into which food webs are more enduring or stable. Through these simplified summed values, we develop a random forest model and a neural network model, both of which are able to predict the number of extinctions that would occur without the need to simulate the dynamics. To conclude, we highlight the variable that plays the dominant role in determining the order in which species go extinct.

Tom Z. Jiahao, M. Ani Hsieh, Eric Forgoston

Extracting predictive models from nonlinear systems is a central task in scientific machine learning. One key problem is the reconciliation between modern data-driven approaches and first principles. Despite rapid advances in machine learning techniques, embedding domain knowledge into data-driven models remains a challenge. In this work, we present a universal learning framework for extracting predictive models from nonlinear systems based on observations. Our framework can readily incorporate first principle knowledge because it naturally models nonlinear systems as continuous-time systems. This both improves the extracted models' extrapolation power and reduces the amount of data needed for training. In addition, our framework has the advantages of robustness to observational noise and applicability to irregularly sampled data. We demonstrate the effectiveness of our scheme by learning predictive models for a wide variety of systems including a stiff Van der Pol oscillator, the Lorenz system, and the Kuramoto-Sivashinsky equation. For the Lorenz system, different types of domain knowledge are incorporated to demonstrate the strength of knowledge embedding in data-driven system identification.

Maan Qraitem, Dhanushka Kularatne, Eric Forgoston et al.

We present a data-driven modeling strategy to overcome improperly modeled dynamics for systems exhibiting complex spatio-temporal behaviors. We propose a Deep Learning framework to resolve the differences between the true dynamics of the system and the dynamics given by a model of the system that is either inaccurately or inadequately described. Our machine learning strategy leverages data generated from the improper system model and observational data from the actual system to create a neural network to model the dynamics of the actual system. We evaluate the proposed framework using numerical solutions obtained from three increasingly complex dynamical systems. Our results show that our system is capable of learning a data-driven model that provides accurate estimates of the system states both in previously unobserved regions as well as for future states. Our results show the power of state-of-the-art machine learning frameworks in estimating an accurate prior of the system's true dynamics that can be used for prediction up to a finite horizon.