Michelle Girvan

Alexander Wikner, Joseph Harvey, Michelle Girvan et al.

Recent work has shown that machine learning (ML) models can be trained to accurately forecast the dynamics of unknown chaotic dynamical systems. Short-term predictions of the state evolution and long-term predictions of the statistical patterns of the dynamics (``climate'') can be produced by employing a feedback loop, whereby the model is trained to predict forward one time step, then the model output is used as input for multiple time steps. In the absence of mitigating techniques, however, this technique can result in artificially rapid error growth. In this article, we systematically examine the technique of adding noise to the ML model input during training to promote stability and improve prediction accuracy. Furthermore, we introduce Linearized Multi-Noise Training (LMNT), a regularization technique that deterministically approximates the effect of many small, independent noise realizations added to the model input during training. Our case study uses reservoir computing, a machine-learning method using recurrent neural networks, to predict the spatiotemporal chaotic Kuramoto-Sivashinsky equation. We find that reservoir computers trained with noise or with LMNT produce climate predictions that appear to be indefinitely stable and have a climate very similar to the true system, while reservoir computers trained without regularization are unstable. Compared with other regularization techniques that yield stability in some cases, we find that both short-term and climate predictions from reservoir computers trained with noise or with LMNT are substantially more accurate. Finally, we show that the deterministic aspect of our LMNT regularization facilitates fast hyperparameter tuning when compared to training with noise.

Ravi Chepuri, Dael Amzalag, Thomas Antonsen et al.

Reservoir computers (RCs) are powerful machine learning architectures for time series prediction. Recently, next generation reservoir computers (NGRCs) have been introduced, offering distinct advantages over RCs, such as reduced computational expense and lower training data requirements. However, NGRCs have their own practical difficulties, including sensitivity to sampling time and type of nonlinearities in the data. Here, we introduce a hybrid RC-NGRC approach for time series forecasting of dynamical systems. We show that our hybrid approach can produce accurate short term predictions and capture the long term statistics of chaotic dynamical systems in situations where the RC and NGRC components alone are insufficient, e.g., due to constraints from limited computational resources, sub-optimal hyperparameters, sparsely-sampled training data, etc. Under these conditions, we show for multiple model chaotic systems that the hybrid RC-NGRC method with a small reservoir can achieve prediction performance approaching that of a traditional RC with a much larger reservoir, illustrating that the hybrid approach can offer significant gains in computational efficiency over traditional RCs while simultaneously addressing some of the limitations of NGRCs. Our results suggest that hybrid RC-NGRC approach may be particularly beneficial in cases when computational efficiency is a high priority and an NGRC alone is not adequate.

Declan A. Norton, Yuanzhao Zhang, Michelle Girvan

Machine learning techniques offer an effective approach to modeling dynamical systems solely from observed data. However, without explicit structural priors -- built-in assumptions about the underlying dynamics -- these techniques typically struggle to generalize to aspects of the dynamics that are poorly represented in the training data. Here, we demonstrate that reservoir computing -- a simple, efficient, and versatile machine learning framework often used for data-driven modeling of dynamical systems -- can generalize to unexplored regions of state space without explicit structural priors. First, we describe a multiple-trajectory training scheme for reservoir computers that supports training across a collection of disjoint time series, enabling effective use of available training data. Then, applying this training scheme to multistable dynamical systems, we show that RCs trained on trajectories from a single basin of attraction can achieve out-of-domain generalization by capturing system behavior in entirely unobserved basins.

Declan A. Norton, Edward Ott, Andrew Pomerance et al.

Machine learning models can effectively forecast dynamical systems from time-series data, but they typically require large amounts of past data, making forecasting particularly challenging for systems with limited history. To overcome this, we introduce Meta-learning for Tailored Forecasting using Related Time Series (METAFORS), which generalizes knowledge across systems to enable forecasting in data-limited scenarios. By learning from a library of models trained on longer time series from potentially related systems, METAFORS builds and initializes a model tailored to short time-series data from the system of interest. Using a reservoir computing implementation and testing on simulated chaotic systems, we demonstrate that METAFORS can reliably predict both short-term dynamics and long-term statistics without requiring contextual labels. We see this even when test and related systems exhibit substantially different behaviors, highlighting METAFORS' strengths in data-limited scenarios.

Keshav Srinivasan, Dietmar Plenz, Michelle Girvan

Reservoir computers (RCs) provide a computationally efficient alternative to deep learning while also offering a framework for incorporating brain-inspired computational principles. By using an internal neural network with random, fixed connections$-$the 'reservoir'$-$and training only the output weights, RCs simplify the training process but remain sensitive to the choice of hyperparameters that govern activation functions and network architecture. Moreover, typical RC implementations overlook a critical aspect of neuronal dynamics: the balance between excitatory and inhibitory (E-I) signals, which is essential for robust brain function. We show that RCs characteristically perform best in balanced or slightly over-inhibited regimes, outperforming excitation-dominated ones. To reduce the need for precise hyperparameter tuning, we introduce a self-adapting mechanism that locally adjusts E/I balance to achieve target neuronal firing rates, improving performance by up to 130% in tasks like memory capacity and time series prediction compared with globally tuned RCs. Incorporating brain-inspired heterogeneity in target neuronal firing rates further reduces the need for fine-tuning hyperparameters and enables RCs to excel across linear and non-linear tasks. These results support a shift from static optimization to dynamic adaptation in reservoir design, demonstrating how brain-inspired mechanisms improve RC performance and robustness while deepening our understanding of neural computation.

Daniel Canaday, Andrew Pomerance, Michelle Girvan

Recent research has established the effectiveness of machine learning for data-driven prediction of the future evolution of unknown dynamical systems, including chaotic systems. However, these approaches require large amounts of measured time series data from the process to be predicted. When only limited data is available, forecasters are forced to impose significant model structure that may or may not accurately represent the process of interest. In this work, we present a Meta-learning Approach to Reservoir Computing (MARC), a data-driven approach to automatically extract an appropriate model structure from experimentally observed "related" processes that can be used to vastly reduce the amount of data required to successfully train a predictive model. We demonstrate our approach on a simple benchmark problem, where it beats the state of the art meta-learning techniques, as well as a challenging chaotic problem.

Keshav Srinivasan, Nolan Coble, Joy Hamlin et al.

Forecasting the dynamics of large complex networks from previous time-series data is important in a wide range of contexts. Here we present a machine learning scheme for this task using a parallel architecture that mimics the topology of the network of interest. We demonstrate the utility and scalability of our method implemented using reservoir computing on a chaotic network of oscillators. Two levels of prior knowledge are considered: (i) the network links are known; and (ii) the network links are unknown and inferred via a data-driven approach to approximately optimize prediction.

Alexander Wikner, Jaideep Pathak, Brian R. Hunt et al.

We consider the problem of data-assisted forecasting of chaotic dynamical systems when the available data is in the form of noisy partial measurements of the past and present state of the dynamical system. Recently there have been several promising data-driven approaches to forecasting of chaotic dynamical systems using machine learning. Particularly promising among these are hybrid approaches that combine machine learning with a knowledge-based model, where a machine-learning technique is used to correct the imperfections in the knowledge-based model. Such imperfections may be due to incomplete understanding and/or limited resolution of the physical processes in the underlying dynamical system, e.g., the atmosphere or the ocean. Previously proposed data-driven forecasting approaches tend to require, for training, measurements of all the variables that are intended to be forecast. We describe a way to relax this assumption by combining data assimilation with machine learning. We demonstrate this technique using the Ensemble Transform Kalman Filter (ETKF) to assimilate synthetic data for the 3-variable Lorenz system and for the Kuramoto-Sivashinsky system, simulating model error in each case by a misspecified parameter value. We show that by using partial measurements of the state of the dynamical system, we can train a machine learning model to improve predictions made by an imperfect knowledge-based model.

Matthew Evanusa, Snehesh Shrestha, Michelle Girvan et al.

In many real-world applications, fully-differentiable RNNs such as LSTMs and GRUs have been widely deployed to solve time series learning tasks. These networks train via Backpropagation Through Time, which can work well in practice but involves a biologically unrealistic unrolling of the network in time for gradient updates, are computationally expensive, and can be hard to tune. A second paradigm, Reservoir Computing, keeps the recurrent weight matrix fixed and random. Here, we propose a novel hybrid network, which we call Hybrid Backpropagation Parallel Echo State Network (HBP-ESN) which combines the effectiveness of learning random temporal features of reservoirs with the readout power of a deep neural network with batch normalization. We demonstrate that our new network outperforms LSTMs and GRUs, including multi-layer "deep" versions of these networks, on two complex real-world multi-dimensional time series datasets: gesture recognition using skeleton keypoints from ChaLearn, and the DEAP dataset for emotion recognition from EEG measurements. We show also that the inclusion of a novel meta-ring structure, which we call HBP-ESN M-Ring, achieves similar performance to one large reservoir while decreasing the memory required by an order of magnitude. We thus offer this new hybrid reservoir deep learning paradigm as a new alternative direction for RNN learning of temporal or sequential data.

Alexander Wikner, Jaideep Pathak, Brian Hunt et al.

We consider the commonly encountered situation (e.g., in weather forecasting) where the goal is to predict the time evolution of a large, spatiotemporally chaotic dynamical system when we have access to both time series data of previous system states and an imperfect model of the full system dynamics. Specifically, we attempt to utilize machine learning as the essential tool for integrating the use of past data into predictions. In order to facilitate scalability to the common scenario of interest where the spatiotemporally chaotic system is very large and complex, we propose combining two approaches:(i) a parallel machine learning prediction scheme; and (ii) a hybrid technique, for a composite prediction system composed of a knowledge-based component and a machine-learning-based component. We demonstrate that not only can this method combining (i) and (ii) be scaled to give excellent performance for very large systems, but also that the length of time series data needed to train our multiple, parallel machine learning components is dramatically less than that necessary without parallelization. Furthermore, considering cases where computational realization of the knowledge-based component does not resolve subgrid-scale processes, our scheme is able to use training data to incorporate the effect of the unresolved short-scale dynamics upon the resolved longer-scale dynamics ("subgrid-scale closure").

Sanjukta Krishnagopal, Michelle Girvan, Edward Ott et al.

We demonstrate the utility of machine learning in the separation of superimposed chaotic signals using a technique called Reservoir Computing. We assume no knowledge of the dynamical equations that produce the signals, and require only training data consisting of finite time samples of the component signals. We test our method on signals that are formed as linear combinations of signals from two Lorenz systems with different parameters. Comparing our nonlinear method with the optimal linear solution to the separation problem, the Wiener filter, we find that our method significantly outperforms the Wiener filter in all the scenarios we study. Furthermore, this difference is particularly striking when the component signals have similar frequency spectra. Indeed, our method works well when the component frequency spectra are indistinguishable - a case where a Wiener filter performs essentially no separation.

Pantelis R. Vlachas, Jaideep Pathak, Brian R. Hunt et al.

We examine the efficiency of Recurrent Neural Networks in forecasting the spatiotemporal dynamics of high dimensional and reduced order complex systems using Reservoir Computing (RC) and Backpropagation through time (BPTT) for gated network architectures. We highlight advantages and limitations of each method and discuss their implementation for parallel computing architectures. We quantify the relative prediction accuracy of these algorithms for the longterm forecasting of chaotic systems using as benchmarks the Lorenz-96 and the Kuramoto-Sivashinsky (KS) equations. We find that, when the full state dynamics are available for training, RC outperforms BPTT approaches in terms of predictive performance and in capturing of the long-term statistics, while at the same time requiring much less training time. However, in the case of reduced order data, large scale RC models can be unstable and more likely than the BPTT algorithms to diverge. In contrast, RNNs trained via BPTT show superior forecasting abilities and capture well the dynamics of reduced order systems. Furthermore, the present study quantifies for the first time the Lyapunov Spectrum of the KS equation with BPTT, achieving similar accuracy as RC. This study establishes that RNNs are a potent computational framework for the learning and forecasting of complex spatiotemporal systems.

Jaideep Pathak, Alexander Wikner, Rebeckah Fussell et al.

A model-based approach to forecasting chaotic dynamical systems utilizes knowledge of the physical processes governing the dynamics to build an approximate mathematical model of the system. In contrast, machine learning techniques have demonstrated promising results for forecasting chaotic systems purely from past time series measurements of system state variables (training data), without prior knowledge of the system dynamics. The motivation for this paper is the potential of machine learning for filling in the gaps in our underlying mechanistic knowledge that cause widely-used knowledge-based models to be inaccurate. Thus we here propose a general method that leverages the advantages of these two approaches by combining a knowledge-based model and a machine learning technique to build a hybrid forecasting scheme. Potential applications for such an approach are numerous (e.g., improving weather forecasting). We demonstrate and test the utility of this approach using a particular illustrative version of a machine learning known as reservoir computing, and we apply the resulting hybrid forecaster to a low-dimensional chaotic system, as well as to a high-dimensional spatiotemporal chaotic system. These tests yield extremely promising results in that our hybrid technique is able to accurately predict for a much longer period of time than either its machine-learning component or its model-based component alone.

Keith Burghardt, Emanuel F. Alsina, Michelle Girvan et al.

Crowds can often make better decisions than individuals or small groups of experts by leveraging their ability to aggregate diverse information. Question answering sites, such as Stack Exchange, rely on the "wisdom of crowds" effect to identify the best answers to questions asked by users. We analyze data from 250 communities on the Stack Exchange network to pinpoint factors affecting which answers are chosen as the best answers. Our results suggest that, rather than evaluate all available answers to a question, users rely on simple cognitive heuristics to choose an answer to vote for or accept. These cognitive heuristics are linked to an answer's salience, such as the order in which it is listed and how much screen space it occupies. While askers appear to depend more on heuristics, compared to voting users, when choosing an answer to accept as the most helpful one, voters use acceptance itself as a heuristic: they are more likely to choose the answer after it is accepted than before that very same answer was accepted. These heuristics become more important in explaining and predicting behavior as the number of available answers increases. Our findings suggest that crowd judgments may become less reliable as the number of answers grow.

David Darmon, Jared Sylvester, Michelle Girvan et al.

There is a large amount of interest in understanding users of social media in order to predict their behavior in this space. Despite this interest, user predictability in social media is not well-understood. To examine this question, we consider a network of fifteen thousand users on Twitter over a seven week period. We apply two contrasting modeling paradigms: computational mechanics and echo state networks. Both methods attempt to model the behavior of users on the basis of their past behavior. We demonstrate that the behavior of users on Twitter can be well-modeled as processes with self-feedback. We find that the two modeling approaches perform very similarly for most users, but that they differ in performance on a small subset of the users. By exploring the properties of these performance-differentiated users, we highlight the challenges faced in applying predictive models to dynamic social data.