Multi-objective optimisation using expected quantile improvement for decision making in disease outbreaks

TL;DR

This paper introduces a multi-objective optimization method using expected quantile improvement with Gaussian process emulators, effectively handling environmental uncertainties to identify optimal solutions in public health scenarios like anthrax spore dispersion.

Contribution

It extends expected quantile improvement to multi-objective problems with environmental uncertainty, providing a sequential design strategy to find Pareto fronts using emulators and Monte Carlo sampling.

Findings

Successfully identified Pareto front in a public health case study

Effectively incorporated environmental uncertainty into optimization

Demonstrated robustness in complex, uncertain scenarios

Abstract

Optimization under uncertainty is important in many applications, particularly to inform policy and decision making in areas such as public health. A key source of uncertainty arises from the incorporation of environmental variables as inputs into computational models or simulators. Such variables represent uncontrollable features of the optimization problem and reliable decision making must account for the uncertainty they propagate to the simulator outputs. Often, multiple, competing objectives are defined from these outputs such that the final optimal decision is a compromise between different goals. Here, we present emulation-based optimization methodology for such problems that extends expected quantile improvement (EQI) to address multi-objective optimization. Focusing on the practically important case of two objectives, we use a sequential design strategy to identify the Pareto front of optimal solutions. Uncertainty from the environmental variables is integrated out using Monte Carlo samples from the simulator. Interrogation of the expected output from the simulator is facilitated by use of (Gaussian process) emulators. The methodology is demonstrated on an optimization problem from public health involving the dispersion of anthrax spores across a spatial terrain. Environmental variables include meteorological features that impact the dispersion, and the methodology identifies the Pareto front even when there is considerable input uncertainty.