Edinburgh Research Explorer

Statistical abstraction for multi-scale spatio-temporal systems

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationInternational Conference on Quantitative Evaluation of Systems QEST 2017
Subtitle of host publicationQuantitative Evaluation of Systems
PublisherSpringer, Cham
Pages243-258
Number of pages16
ISBN (Electronic)978-3-319-66335-7
ISBN (Print)978-3-319-66334-0
DOIs
StatePublished - 11 Aug 2017

Publication series

NameLecture Notes in Computer Science
Publisher Springer, Cham
Volume10503
ISSN (Print)0302-9743

Abstract

Spatio-temporal systems exhibiting multi-scale behaviour are common in applications ranging from cyber-physical systems to systems biology, yet they present formidable challenges for computational modelling and analysis. Here we consider a prototypic scenario where spatially distributed agents decide their movement based on external inputs and a fast-equilibrating internal computation. We propose a generally applicable strategy based on statistically abstracting the internal system using Gaussian Processes, a powerful class of non-parametric regression techniques from Bayesian Machine Learning. We show on a running example of bacterial chemotaxis that this approach leads to accurate and much faster simulations in a variety of scenarios.

ID: 37015174