Imperial College London
Portrait Picture

DrSarahFilippi

Faculty of Natural Sciences, Department of Mathematics

Reader in Statistical Machine Learning
 
 
 
//

Contact

 

+44 (0)20 7594 8562s.filippi

 
 
//

Location

 

523Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Reiker:2021:10.1038/s41467-021-27486-z,
author = {Reiker, T and Golumbeanu, M and Shattock, A and Burgert, L and Smith, TA and Filippi, S and Cameron, E and Penny, MA},
doi = {10.1038/s41467-021-27486-z},
journal = {Nature Communications},
title = {Emulator-based Bayesian optimization for efficient multi-objective calibration of an individual-based model of malaria},
url = {http://dx.doi.org/10.1038/s41467-021-27486-z},
volume = {12},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Individual-based models have become important tools in the global battle against infectious diseases, yet model complexity can make calibration to biological and epidemiological data challenging. We propose using a Bayesian optimization framework employing Gaussian process or machine learning emulator functions to calibrate a complex malaria transmission simulator. We demonstrate our approach by optimizing over a high-dimensional parameter space with respect to a portfolio of multiple fitting objectives built from datasets capturing the natural history of malaria transmission and disease progression. Our approach quickly outperforms previous calibrations, yielding an improved final goodness of fit. Per-objective parameter importance and sensitivity diagnostics provided by our approach offer epidemiological insights and enhance trust in predictions through greater interpretability.
AU  - Reiker,T
AU  - Golumbeanu,M
AU  - Shattock,A
AU  - Burgert,L
AU  - Smith,TA
AU  - Filippi,S
AU  - Cameron,E
AU  - Penny,MA
DO  - 10.1038/s41467-021-27486-z
PY  - 2021///
SN  - 2041-1723
TI  - Emulator-based Bayesian optimization for efficient multi-objective calibration of an individual-based model of malaria
T2  - Nature Communications
UR  - http://dx.doi.org/10.1038/s41467-021-27486-z
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000729179400031&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://www.nature.com/articles/s41467-021-27486-z
UR  - http://hdl.handle.net/10044/1/97114
VL  - 12
ER  -
Download