arXiv subjects

Yannis Kevrekidis

Publications and source records attributed to Yannis Kevrekidis.

11 recordsLinked to original sources

arXiv2026

The Future of Artificial Intelligence and the Mathematical and Physical Sciences (AI+MPS)

This community paper developed out of the NSF Workshop on the Future of Artificial Intelligence (AI) and the Mathematical and Physics Sciences (MPS), which was held in March 2025 with the goal of understanding how the MPS domains (Astronomy, Chemistry, Materials Research, Mathematical Sciences, and Physics) can best capitalize on, and contribute to, the future of AI. We present here a summary and snapshot of the MPS community's perspective, as of Spring/Summer 2025, in a rapidly developing field. The link between AI and MPS is becoming increasingly inextricable; now is a crucial moment to strengthen the link between AI and Science by pursuing a strategy that proactively and thoughtfully leverages the potential of AI for scientific discovery and optimizes opportunities to impact the development of AI by applying concepts from fundamental science. To achieve this, we propose activities and strategic priorities that: (1) enable AI+MPS research in both directions; (2) build up an interdisciplinary community of AI+MPS researchers; and (3) foster education and workforce development in AI for MPS researchers and students. We conclude with a summary of suggested priorities for funding agencies, educational institutions, and individual researchers to help position the MPS community to be a leader in, and take full advantage of, the transformative potential of AI+MPS.

cs.AI↗

arXiv2025

A simulation that recapitulates the dynamics of PER-directed colloidal assembly

The self-assembly of DNA-coated colloids controlled by enzymatic reactions has the potential to enable the formation of materials with hierarchical organization and switchable configurations. However, the problem of designing such self-assembly is complex, and an effective simulation is necessary to assist in searching for appropriate design protocols. Typical computational methodologies such as molecular dynamics and Brownian dynamics have limited ability to access the long time scales required for these hierarchical self-assembly processes. Here we adopt a particle-based reaction-diffusion algorithm to model the spatial-temporal evolution of hundreds to thousands of micron-scale DNA-coated colloid self-assembly process over hours. In order to demonstrate the capability of this digital twin, we compared its predicted core-shell assembly process to results from experiments. The model can qualitatively reproduce the core-shell structures observed in experiment by recapitulating the emergence of compositional heterogeneity when delays between distinct assembly times are introduced. These results support the idea that this approach can successfully capture dynamics over long time scales and the appropriate scale of structure formation. We then use the model to explore different protocols for structure evolution, suggesting how this tool can aid in the design of complex self-organization processes.

math.DS↗

arXiv2024

Gaussian Processes simplify differential equations

In this paper we use Gaussian processes (kernel methods) to learn mappings between trajectories of distinct differential equations. Our goal is to simplify both the representation and the solution of these equations. We begin by examining the Cole-Hopf transformation, a classical result that converts the nonlinear, viscous Burgers' equation into the linear heat equation. We demonstrate that this transformation can be effectively learned using Gaussian process regression, either from single or from multiple initial conditions of the Burgers equation. We then extend our methodology to discover mappings between initial conditions of a nonlinear partial differential equation (PDE) and a linear PDE, where the exact form of the linear PDE remains unknown and is inferred through Computational Graph Completion (CGC), a generalization of Gaussian Process Regression from approximating single input/output functions to approximating multiple input/output functions that interact within a computational graph. Further, we employ CGC to identify a local transformation from the nonlinear ordinary differential equation (ODE) of the Brusselator to its Poincaré normal form, capturing the dynamics around a Hopf bifurcation. We conclude by addressing the broader question of whether systematic transformations between nonlinear and linear PDEs can generally exist, suggesting avenues for future research.

math.DS↗

arXiv2024

Data-driven cold starting of good reservoirs

Using short histories of observations from a dynamical system, a workflow for the post-training initialization of reservoir computing systems is described. This strategy is called cold-starting, and it is based on a map called the starting map, which is determined by an appropriately short history of observations that maps to a unique initial condition in the reservoir space. The time series generated by the reservoir system using that initial state can be used to run the system in autonomous mode, to produce accurate forecasts of the time series under consideration immediately. By utilizing this map, the lengthy "washouts" that are necessary to initialize reservoir systems can be eliminated, enabling the generation of forecasts using any selection of appropriately short histories of the observations.

math.DS↗

arXiv2023

Tipping points in overturning circulation mediated by ocean mixing and the configuration and magnitude of the hydrological cycle: A simple model

The current configuration of the ocean overturning involves upwelling predominantly in the Southern Ocean and sinking predominantly in the Atlantic basin. The reasons for this remain unclear, as both models and paleoclimatic observations suggest that sinking can sometimes occur in the Pacific. We present a six-box model of the overturning in which temperature, salinity and low-latitude pycnocline depths are allowed to vary prognostically in both the Atlantic and Pacific. The overturning is driven by temperature, winds, and mixing and modulated by the hydrological cycle. In each basin there are three possible flow regimes, depending on whether low-latitude water flowing into northern surface boxes is transformed into dense deep water, somewhat lighter intermediate water, or light water that is returned at the surface. The resulting model combines insights from a number of previous studies and allows for nine possible global flow regimes. For the modern ocean, we find that although the interbasin atmospheric freshwater flux suppresses Pacific sinking, the equator-to-pole flux enhances it. When atmospheric temperatures are held fixed, seven possible flow regimes can be accessed by changing the amplitude and configuration of the modern hydrological cycle . North Pacific overturning can strengthen with either increases or decreases in the hydrological cycle, as well as under reversal of the interbasin freshwater flux. Tipping-point behavior of both transient and equilibrium states is modulated by parameters such as the poorly constrained lateral diffusive mixing. If hydrological cycle amplitude is varied consistently with global temperature, northern polar amplification is necessary for the Atlantic overturning to collapse

physics.ao-ph↗

arXiv2023

Benchmarking optimality of time series classification methods in distinguishing diffusions

Statistical optimality benchmarking is crucial for analyzing and designing time series classification (TSC) algorithms. This study proposes to benchmark the optimality of TSC algorithms in distinguishing diffusion processes by the likelihood ratio test (LRT). The LRT is an optimal classifier by the Neyman-Pearson lemma. The LRT benchmarks are computationally efficient because the LRT does not need training, and the diffusion processes can be efficiently simulated and are flexible to reflect the specific features of real-world applications. We demonstrate the benchmarking with three widely-used TSC algorithms: random forest, ResNet, and ROCKET. These algorithms can achieve the LRT optimality for univariate time series and multivariate Gaussian processes. However, these model-agnostic algorithms are suboptimal in classifying high-dimensional nonlinear multivariate time series. Additionally, the LRT benchmark provides tools to analyze the dependence of classification accuracy on the time length, dimension, temporal sampling frequency, and randomness of the time series.

stat.ML↗

arXiv2023

A Generative Adversarial Network for Climate Tipping Point Discovery (TIP-GAN)

We propose a new Tipping Point Generative Adversarial Network (TIP-GAN) for better characterizing potential climate tipping points in Earth system models. We describe an adversarial game to explore the parameter space of these models, detect upcoming tipping points, and discover the drivers of tipping points. In this setup, a set of generators learn to construct model configurations that will invoke a climate tipping point. The discriminator learns to identify which generators are generating each model configuration and whether a given configuration will lead to a tipping point. The discriminator is trained using an oracle (a surrogate climate model) to test if a generated model configuration leads to a tipping point or not. We demonstrate the application of this GAN to invoke the collapse of the Atlantic Meridional Overturning Circulation (AMOC). We share experimental results of modifying the loss functions and the number of generators to exploit the area of uncertainty in model state space near a climate tipping point. In addition, we show that our trained discriminator can predict AMOC collapse with a high degree of accuracy without the use of the oracle. This approach could generalize to other tipping points, and could augment climate modeling research by directing users interested in studying tipping points to parameter sets likely to induce said tipping points in their computationally intensive climate models.

cs.LG↗

arXiv2023

Using Artificial Intelligence to aid Scientific Discovery of Climate Tipping Points

We propose a hybrid Artificial Intelligence (AI) climate modeling approach that enables climate modelers in scientific discovery using a climate-targeted simulation methodology based on a novel combination of deep neural networks and mathematical methods for modeling dynamical systems. The simulations are grounded by a neuro-symbolic language that both enables question answering of what is learned by the AI methods and provides a means of explainability. We describe how this methodology can be applied to the discovery of climate tipping points and, in particular, the collapse of the Atlantic Meridional Overturning Circulation (AMOC). We show how this methodology is able to predict AMOC collapse with a high degree of accuracy using a surrogate climate model for ocean interaction. We also show preliminary results of neuro-symbolic method performance when translating between natural language questions and symbolically learned representations. Our AI methodology shows promising early results, potentially enabling faster climate tipping point related research that would otherwise be computationally infeasible.

cs.AI↗

arXiv2023

Accurate and efficient multiscale simulation of a heterogeneous elastic beam via computation on small sparse patches

Modern `smart' materials have complex microscale structure, often with unknown macroscale closure. The Equation-Free Patch Scheme empowers us to non-intrusively, efficiently, and accurately simulate over large scales through computations on only small well-separated patches of the microscale system. Here the microscale system is a solid beam of random heterogeneous elasticity. The continuing challenge is to compute the given physics on just the microscale patches, and couple the patches across un-simulated macroscale space, in order to establish efficiency, accuracy, consistency, and stability on the macroscale. Dynamical systems theory supports the scheme. This research program is to develop a systematic non-intrusive approach, both computationally and analytically proven, to model and compute accurately macroscale system levels of general complex physical and engineering systems.

math.NA↗

arXiv2022

Unsupervised learning of observation functions in state-space models by nonparametric moment methods

We investigate the unsupervised learning of non-invertible observation functions in nonlinear state-space models. Assuming abundant data of the observation process along with the distribution of the state process, we introduce a nonparametric generalized moment method to estimate the observation function via constrained regression. The major challenge comes from the non-invertibility of the observation function and the lack of data pairs between the state and observation. We address the fundamental issue of identifiability from quadratic loss functionals and show that the function space of identifiability is the closure of a RKHS that is intrinsic to the state process. Numerical results show that the first two moments and temporal correlations, along with upper and lower bounds, can identify functions ranging from piecewise polynomials to smooth functions, leading to convergent estimators. The limitations of this method, such as non-identifiability due to symmetry and stationarity, are also discussed.

stat.ML↗

arXiv2020

Applications of Koopman Mode Analysis to Neural Networks

We consider the training process of a neural network as a dynamical system acting on the high-dimensional weight space. Each epoch is an application of the map induced by the optimization algorithm and the loss function. Using this induced map, we can apply observables on the weight space and measure their evolution. The evolution of the observables are given by the Koopman operator associated with the induced dynamical system. We use the spectrum and modes of the Koopman operator to realize the above objectives. Our methods can help to, a priori, determine the network depth; determine if we have a bad initialization of the network weights, allowing a restart before training too long; speeding up the training time. Additionally, our methods help enable noise rejection and improve robustness. We show how the Koopman spectrum can be used to determine the number of layers required for the architecture. Additionally, we show how we can elucidate the convergence versus non-convergence of the training process by monitoring the spectrum, in particular, how the existence of eigenvalues clustering around 1 determines when to terminate the learning process. We also show how using Koopman modes we can selectively prune the network to speed up the training procedure. Finally, we show that incorporating loss functions based on negative Sobolev norms can allow for the reconstruction of a multi-scale signal polluted by very large amounts of noise.

cs.LG↗