arXiv subjects

Marisa Eisenberg

Publications and source records attributed to Marisa Eisenberg.

9 recordsLinked to original sources

arXiv2026

Reservoir: A Large-Scale Simulated Dataset for Training and Evaluating Epidemiological Models

Large-scale, standardized datasets have driven many advances in AI-based scientific modeling, from protein structure prediction to natural language processing. Infectious disease epidemiology is increasingly adopting AI methods for forecasting, surveillance, and outbreak analytics, but the time-series data available to train them remains orders of magnitude smaller than the corpora behind the advances seen in other fields. Because the scope of real-world epidemiological data cannot practically reach the scale needed to train truly large-scale AI methods, simulated data provides a possible alternative. Here we introduce Reservoir, a large open simulator and dataset of realistic epidemic simulations in which every trajectory carries complete ground-truth labels, including quantities that cannot be measured directly in a real outbreak, such as true infection counts, time-varying reproduction numbers, and counterfactual intervention effects. Reservoir is generated by a stochastic simulator with realistic noise and reporting artifacts, together with interventions with configurable timing, compliance, and age-dependent efficacy. The current release contains 500,000 outbreak trajectories spanning one billion simulated days across diverse pathogen characteristics, population structures, and intervention regimes. Reservoir enables counterfactual experiments, surveillance-design studies, and training of epidemic models at a scale real-world datasets cannot provide.

q-bio.PE↗

arXiv2026

Benchmarking Counterfactual Prediction in Epidemic Time Series with Time-Varying Interventions

Deep learning has enabled significant advances in time-series causal inference, yet progress remains constrained by the lack of realistic benchmarks with observable counterfactual outcomes. Existing datasets either rely on real-world observations without ground-truth counterfactuals or on simplified simulations that fail to capture complex causal dynamics. To address this gap, we develop a large-scale benchmark for counterfactual prediction in epidemic time series under dynamic interventions. Unlike existing benchmarks, it supports static and time-varying treatments, as well as both single-policy and multi-policy intervention settings, enabling evaluation of causal inference methods across a broad range of causal inference scenarios. Leveraging a calibrated agent-based model grounded in real-world demographic, mobility, epidemiological, and policy data, we generate realistic counterfactual trajectories across more than 150 U.S. counties. Using this benchmark, we evaluate widely used and state-of-the-art causal inference methods, revealing substantial performance differences and highlighting the challenges of realistic time-series causal reasoning.

cs.LG↗

arXiv2026

Simulation as Supervision: Mechanistic Pretraining for Scientific Discovery

Scientific modeling faces a tradeoff between the interpretability of mechanistic theory and the predictive power of machine learning. While existing hybrid approaches have made progress by incorporating domain knowledge into machine learning methods as functional constraints, they can be limited by a reliance on precise mathematical specifications. When the underlying equations are partially unknown or misspecified, enforcing rigid constraints can introduce bias and hinder a model's ability to learn from data. We introduce Simulation-Grounded Neural Networks (SGNNs), a framework that incorporates scientific theory by using mechanistic simulations as training data for neural networks. By pretraining on diverse synthetic corpora that span multiple model structures and realistic observational noise, SGNNs internalize the underlying dynamics of a system as a structural prior. We evaluated SGNNs across multiple disciplines, including epidemiology, ecology, social science, and chemistry. In forecasting tasks, SGNNs outperformed both standard data-driven baselines and physics-constrained hybrid models. They nearly tripled the forecasting skill of the average CDC models in COVID-19 mortality forecasts and accurately forecasted high-dimensional ecological systems. SGNNs demonstrated robustness to model misspecification, performing well even when trained on data with incorrect assumptions. Our framework also introduces back-to-simulation attribution, a method for mechanistic interpretability that explains real-world dynamics by identifying their most similar counterparts within the simulated corpus. By unifying these techniques into a single framework, we demonstrate that diverse mechanistic simulations can serve as effective training data for robust scientific inference.

cs.LG↗

arXiv2026

Mantis: A Foundation Model for Mechanistic Disease Forecasting

Infectious disease forecasting in novel outbreaks or low-resource settings is hampered by the need for large disease and covariate data sets, bespoke training, and expert tuning, all of which can hinder rapid generation of forecasts for new settings. To help address these challenges, we developed Mantis, a foundation model trained entirely on mechanistic simulations, which enables out-of-the-box forecasting across diseases, regions, and outcomes, even in settings with limited historical data. We evaluated Mantis against 78 forecasting models across sixteen diseases with diverse modes of transmission, assessing both point forecast accuracy (mean absolute error) and probabilistic performance (weighted interval score and coverage). Despite using no real-world data during training, Mantis achieved lower mean absolute error than all models in the CDC's COVID-19 Forecast Hub when backtested on early pandemic forecasts which it had not previously seen. Across all other diseases tested, Mantis consistently ranked in the top two models across evaluation metrics. Mantis further generalized to diseases with transmission mechanisms not represented in its training data, demonstrating that it can capture fundamental contagion dynamics rather than memorizing disease-specific patterns. These capabilities illustrate that purely simulation-based foundation models such as Mantis can provide a practical foundation for disease forecasting: general-purpose, accurate, and deployable where traditional models struggle.

cs.AI↗

arXiv2026

Not All Accuracy Is Equal: Prioritizing Independence in Infectious Disease Forecasting

Ensemble forecasts have become a cornerstone of large-scale disease response, underpinning decision making at agencies such as the US Centers for Disease Control and Prevention (CDC). Their growing use reflects the goal of combining multiple models to improve accuracy and stability versus relying on any single model. However, while ensembles regularly demonstrate stability against individual model failures, improved accuracy is not guaranteed. During the COVID-19 pandemic, the CDC's multi-model ensemble outperformed the best single model by only 1\%, and CDC flu ensembles have often ranked below individual models. Prior work has established that ensemble performance depends critically on diversity: when models make independent errors, combining them yields substantial gains. In practice, however, this diversity is often lacking. Here, we propose that this is due in part to how models are developed and selected: both modelers and ensemble builders optimize for stand-alone accuracy rather than ensemble contribution, and most epidemic forecasts are built from a small set of approaches trained on the same surveillance data. The result is highly correlated errors, limiting the benefit of ensembling. This suggests that in developing models and ensembles, we should prioritize models that contribute complementary information rather than replicating existing approaches. We present a toy example illustrating the theoretical cost of correlated errors, analyze correlations among COVID-19 forecasting models, and propose improvements to model fitting and ensemble construction that foster genuine diversity. Ensembles built with this principle in mind produce forecasts that are more robust and more valuable for epidemic preparedness and response.

stat.AP↗

arXiv2025

Learning From Simulators: A Theory of Simulation-Grounded Learning

Simulation-Grounded Neural Networks (SGNNs) are predictive models trained entirely on synthetic data from mechanistic simulations. They have achieved state-of-the-art performance in domains where real-world labels are limited or unobserved, but lack a formal underpinning. We place SGNNs in a unified statistical framework. Under standard loss functions, they can be interpreted as amortized Bayesian predictors trained under a simulator-induced prior. Empirical risk minimization then yields convergence to the Bayes-optimal predictor under the synthetic distribution. We employ classical results on distribution shift to characterize how performance degrades when the simulator diverges from reality. Beyond these consequences, we develop SGNN-specific results: (i) conditions under which unobserved scientific parameters are learnable via simulation, and (ii) a back-to-simulation attribution method that provides mechanistic explanations of predictions by linking them to the simulations the model deems similar, with guarantees of posterior consistency. We provide numerical experiments to validate theoretical predictions. SGNNs recover latent parameters, remain robust under mismatch, and outperform classical tools: in a model selection task, SGNNs achieve half the error of AIC in distinguishing mechanistic dynamics. These results establish SGNNs as a principled and practical framework for scientific prediction in data-limited regimes.

cs.LG↗

arXiv2021

Structural identifiability analysis of PDEs: A case study in continuous age-structured epidemic models

Computational and mathematical models rely heavily on estimated parameter values for model development. Identifiability analysis determines how well the parameters of a model can be estimated from experimental data. Identifiability analysis is crucial for interpreting and determining confidence in model parameter values and to provide biologically relevant predictions. Structural identifiability analysis, in which one assumes data to be noiseless and arbitrarily fine-grained, has been extensively studied in the context of ordinary differential equation (ODE) models, but has not yet been widely explored for age-structured partial differential equation (PDE) models. These models present additional difficulties due to increased number of variables and partial derivatives as well as the presence of boundary conditions. In this work, we establish a pipeline for structural identifiability analysis of age-structured PDE models using a differential algebra framework and derive identifiability results for specific age-structured models. We use epidemic models to demonstrate this framework because of their wide-spread use in many different diseases and for the corresponding parallel work previously done for ODEs. In our application of the identifiability analysis pipeline, we focus on a Susceptible-Exposed-Infected model for which we compare identifiability results for a PDE and corresponding ODE system and explore effects of age-dependent parameters on identifiability. We also show how practical identifiability analysis can be applied in this example.

q-bio.QM↗

arXiv2019

Input-output equivalence and identifiability: some simple generalizations of the differential algebra approach

In this paper, we give an overview of the differential algebra approach to identifiability, and then note a very simple observation about input-output equivalence and identifiability, that describes the identifiability equivalence between input-output equivalent models. We then give several simple consequences of this observation that can be useful in showing identifiability, including examining non-first order ODE models, nondimensionalization and rescaling, model reducibility, and a modular approach to evaluating identifiability. We also examine how input-output equivalence can allow us to generate input output equations in the differential algebra approach through a wider range of methods (e.g. substitution and differential or standard Groebner basis approaches).

q-bio.QM↗

arXiv2014

Identifiability results for several classes of linear compartment models

Identifiability concerns finding which unknown parameters of a model can be estimated from given input-output data. If some subset of the parameters of a model cannot be determined given input-output data, then we say the model is unidentifiable. In past work we identified a class of models, that we call identifiable cycle models, which are not identifiable but have the simplest possible identifiable functions (so-called monomial cycles). Here we show how to modify identifiable cycle models by adding inputs, adding outputs, or removing leaks, in such a way that we obtain an identifiable model. We also prove a constructive result on how to combine identifiable models, each corresponding to strongly connected graphs, into a larger identifiable model. We apply these theoretical results to several real-world biological models from physiology, cell biology, and ecology.

math.AG↗