Corpus ID: 222310265

Accurate Calibration of Agent-based Epidemiological Models with Neural Network Surrogates

  title={Accurate Calibration of Agent-based Epidemiological Models with Neural Network Surrogates},
  author={Rushil Anirudh and Jayaraman J. Thiagarajan and P. Bremer and T. Germann and S. D. Valle and F. Streitz},
Calibrating complex epidemiological models to observed data is a crucial step to provide both insights into the current disease dynamics, i.e.\ by estimating a reproductive number, as well as to provide reliable forecasts and scenario explorations. Here we present a new approach to calibrate an agent-based model -- EpiCast -- using a large set of simulation ensembles for different major metropolitan areas of the United States. In particular, we propose: a new neural network based surrogate… Expand

Figures and Tables from this paper

Differentiable Agent-Based Simulation for Gradient-Guided Simulation-Based Optimization
The use of Automatic differentiation in the context of time-driven agent-based simulations is explored and it is demonstrated that the approach enables gradient-based training of neural network-controlled simulation entities embedded in the model logic. Expand
Enabling Machine Learning-Ready HPC Ensembles with Merlin
Merlin is presented, a workflow framework to enable large ML-friendly ensembles of scientific HPC simulations by augmenting traditional HPC with distributed compute technologies and aims to lower the barrier for scientific subject matter experts to incorporate ML into their analysis. Expand


The use of mixture-density networks in the emulation of complex epidemiological individual-based models
The use of emulation will provide a method to package an infectious disease model such that it can be disseminated to the widest audience possible, and an open-access library of the method has been released alongside this manuscript. Expand
Dynamic calibration of agent-based models using data assimilation
This paper describes how ABMs can be dynamically calibrated using the ensemble Kalman filter (EnKF), a standard method of data assimilation, and builds a hierarchy of exemplar models that are used to demonstrate how to apply the EnKF and calibrate these using open data of footfall counts in Leeds. Expand
Calibration of individual-based models to epidemiological data: A systematic review
An overview of calibration methods used in IBMs modelling infectious disease spread, identified articles on PubMed employing simulation-based methods to calibrate IBMs informing public health policy in HIV, tuberculosis, and malaria epidemiology published between 1 January 2013 and 31 December 2018. Expand
Improved surrogates in inertial confinement fusion with manifold and cycle consistencies
This paper advocates for the training of surrogates that are 1) consistent with the physical manifold, resulting in physically meaningful predictions, and 2) cyclically consistent with a jointly trained inverse model; i.e., backmapping predictions through the inverse results in the original input parameters. Expand
SIRNet: Understanding Social Distancing Measures with Hybrid Neural Network Model for COVID-19 Infectious Spread
A new hybrid machine learning model, SIRNet, is proposed for forecasting the spread of the COVID-19 pandemic that couples with the epidemiological models and can support in studying non-pharmacological interventions and approaches that minimize societal collateral damage and control mechanisms for an extended period of time. Expand
Calibration Methods Used in Cancer Simulation Models and Suggested Reporting Guidelines
The review shows that the use of cancer simulation modelling is increasing, although thorough descriptions of calibration procedures are rare in the published literature for these models, and proposes a standardized Calibration Reporting Checklist for model documentation. Expand
Calibration of a SEIR-SEI epidemic model to describe the Zika virus outbreak in Brazil
This work deals with the development and calibration of an epidemic model to describe the 2016 outbreak of Zika virus in Brazil and presents realistic parameters and returns reasonable descriptions, with the curve shape similar to the outbreak evolution and peak value close to the highest number of infected people during 2016. Expand
An agent-based approach for modeling dynamics of contagious disease spread
The GIS-agent based model designed for this study can be easily customized to study the disease spread dynamics of any other communicable disease by simply adjusting the modeled disease timeline and/or the infection model and modifying the transmission process. Expand
The challenges of modeling and forecasting the spread of COVID-19
Three regional-scale models for forecasting and assessing the course of the COVID-19 pandemic demonstrate the utility of parsimonious models for early-time data and provides an accessible framework for generating policy-relevant insights into its course. Expand
Modeling targeted layered containment of an influenza pandemic in the United States
The simulations suggest that at the expected transmissibility of a pandemic strain, timely implementation of a combination of targeted household antiviral prophylaxis, and social distancing measures could substantially lower the illness attack rate before a highly efficacious vaccine could become available. Expand