Bayesian emulation and history matching of JUNE

被引:8
|
作者
Vernon, I. [1 ,2 ]
Owen, J. [1 ,2 ]
Aylett-Bullock, J. [1 ,3 ]
Cuesta-Lazaro, C. [1 ,4 ]
Frawley, J. [1 ,5 ]
Quera-Bofarull, A. [1 ,4 ]
Sedgewick, A. [1 ,6 ]
Shi, D. [1 ,4 ]
Truong, H. [1 ,3 ]
Turner, M. [1 ,5 ]
Walker, J. [1 ,3 ]
Caulfield, T. [7 ]
Fong, K. [8 ,9 ]
Krauss, F. [1 ,3 ]
机构
[1] Univ Durham, Inst Data Sci, Durham DH13LE, England
[2] Univ Durham, Dept Math Sci, Durham DH13LE, England
[3] Univ Durham, Inst Particle Phys Phenomenol, Durham DH13LE, England
[4] Univ Durham, Inst Computat Cosmol, Durham DH13LE, England
[5] Univ Durham, Adv Res Comp, Durham DH13LE, England
[6] Univ Durham, Ctr Extragalact Astron, Durham DH13LE, England
[7] Univ Durham, Dept Comp Sci, Durham DH13LE, England
[8] UCL, Dept Sci Technol Engn & Publ Policy, London WC1E6BT, England
[9] Univ Coll London Hosp, Dept Anaesthesia, London NW12BU, England
来源
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES | 2022年 / 380卷 / 2233期
基金
英国惠康基金;
关键词
disease models; Bayes linear; emulation; calibration; history matching; GALAXY FORMATION; COMPUTER CODE; INFERENCE; PREDICTION; DESIGN;
D O I
10.1098/rsta.2022.0039
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
We analyze JUNE: a detailed model of COVID-19 transmission with high spatial and demographic resolution, developed as part of the RAMP initiative. JUNE requires substantial computational resources to evaluate, making model calibration and general uncertainty analysis extremely challenging. We describe and employ the uncertainty quantification approaches of Bayes linear emulation and history matching to mimic JUNE and to perform a global parameter search, hence identifying regions of parameter space that produce acceptable matches to observed data, and demonstrating the capability of such methods.This article is part of the theme issue 'Technical challenges of modelling real-life epidemics and examples of overcoming these'.
引用
收藏
页数:20
相关论文
共 50 条
  • [31] GpABC: a Julia package for approximate Bayesian computation with Gaussian process emulation
    Tankhilevich, Evgeny
    Ish-Horowicz, Jonathan
    Hameed, Tara
    Roesch, Elisabeth
    Kleijn, Istvan
    Stumpf, Michael P. H.
    He, Fei
    BIOINFORMATICS, 2020, 36 (10) : 3286 - 3287
  • [32] Bayesian emulation of complex multi-output and dynamic computer models
    Conti, Stefano
    O'Hagan, Anthony
    JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2010, 140 (03) : 640 - 651
  • [33] The conditioning effect of protest history on the emulation of nonviolent conflict
    Braithwaite, Alex
    Braithwaite, Jessica Maves
    Kucik, Jeffrey
    JOURNAL OF PEACE RESEARCH, 2015, 52 (06) : 697 - 711
  • [34] Future proofing a building design using history matching inspired level-set techniques
    Baker, Evan
    Challenor, Peter
    Eames, Matt
    JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS, 2021, 70 (02) : 335 - 350
  • [35] Robust Algorithms for History Matching of Imperfect Subsurface Models
    Rammay, Muzammil H.
    Elsheikh, Ahmed H.
    Chen, Yan
    SPE JOURNAL, 2020, 25 (06): : 3300 - 3316
  • [36] Assisted history matching using pattern recognition technology
    Shahkarami, Alireza
    Mohaghegh, Shahab D.
    Hajizadeh, Yasin
    INTERNATIONAL JOURNAL OF OIL GAS AND COAL TECHNOLOGY, 2018, 17 (04) : 412 - 442
  • [37] A Simple Method for History Matching
    Song Kao-Ping
    Li Li-Li
    Zhan Fei
    FLOW IN POROUS MEDIA - FROM PHENOMENA TO ENGINEERING AND BEYOND, 2009, : 83 - 88
  • [38] An analysis of history matching errors
    Tavassoli, Z
    Carter, JN
    King, PR
    COMPUTATIONAL GEOSCIENCES, 2005, 9 (2-3) : 99 - 123
  • [39] An analysis of history matching errors
    Z. Tavassoli
    Jonathan N. Carter
    Peter R. King
    Computational Geosciences, 2005, 9 : 99 - 123
  • [40] The history of the future of the Bayesian brain
    Friston, Karl J.
    NEUROIMAGE, 2012, 62 (02) : 1230 - 1233