ABC for climate: dealing with expensive simulators

Holden, Philip; Edwards, Neil R.; Hensman, James; Wilkinson, Richard D.

doi:10.48550/arxiv.1511.03475

Cited by 2 publications

(3 citation statements)

References 41 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to note though, that with certain emulators such as GPs the prediction cost is O(N ) where N is number of training points. See Holden et al (2015) for further discussion on different emulator training strategies. We suggest that SMC might also be useful in this sequential training approach, and we leave that for future research.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Semi-Automatic Method for History Matching using Sequential Monte Carlo

Drovandi¹,

Nott²,

Pagendam³

2017

Preprint

View full text Add to dashboard Cite

The aim of the history matching method is to locate non-implausible regions of the parameter space of complex deterministic or stochastic models by matching model outputs with data. It does this via a series of waves where at each wave an emulator is fitted to a small number of training samples. An implausibility measure is defined which takes into account the closeness of simulated and observed outputs as well as emulator uncertainty. As the waves progress, the emulator becomes more accurate so that training samples are more concentrated on promising regions of the space and poorer parts of the space are rejected with more confidence. Whilst history matching has proved to be useful, existing implementations are not fully automated and some ad-hoc choices are made during the process, which involves user intervention and is time consuming. This occurs especially when the non-implausible region becomes small and it is difficult to sample this space uniformly to generate new training points. In this article we develop a sequential Monte Carlo (SMC) algorithm for implementation which is semi-automated. Our novel SMC approach reveals that the history matching method yields a non-implausible distribution that can be multi-modal, highly irregular and very difficult to sample uniformly. Our SMC approach offers a much more reliable sampling of the nonimplausible space, which requires additional computation compared to other approaches used in the literature.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Chen et al (2017)), climate (e.g. Holden et al (2015)), cosmology (e.g. Vernon et al (2014)) and many other disciplines.…”

Section: Introductionmentioning

confidence: 99%

A Semi-Automatic Method for History Matching using Sequential Monte Carlo

Drovandi¹,

Nott²,

Pagendam³

2017

Preprint

View full text Add to dashboard Cite

show abstract

“…Emulators have now been successfully employed across several scientific disciplines, including cosmology [41,42,8,38,20,43,32], climate modelling [46,35,25,22] (the later employing emulation to in-crease the efficiency of an Approximate Bayesian Computation algorithm), epidemiology [2,3,1,31,30], systems biology [45,24], oil reservoir modelling [11,12], environmental science [16], traffic modelling [7], vulcanology [5] and even to Bayesian analysis itself [44]. The development of improved emulation strategies therefore has the potential to benefit multiple scientific areas, allowing more accurate analyses with lower computational cost.…”

mentioning

confidence: 99%

Known Boundary Emulation of Complex Computer Models

Vernon¹,

Jackson²,

Cumming³

2019

SIAM/ASA J. Uncertainty Quantification

View full text Add to dashboard Cite

Computer models are now widely used across a range of scientific disciplines to describe various complex physical systems, however to perform full uncertainty quantification we often need to employ emulators. An emulator is a fast statistical construct that mimics the complex computer model, and greatly aids the vastly more computationally intensive uncertainty quantification calculations that a serious scientific analysis often requires. In some cases, the complex model can be solved far more efficiently for certain parameter settings, leading to boundaries or hyperplanes in the input parameter space where the model is essentially known. We show that for a large class of Gaussian process style emulators, multiple boundaries can be formally incorporated into the emulation process, by Bayesian updating of the emulators with respect to the boundaries, for trivial computational cost. The resulting updated emulator equations are given analytically. This leads to emulators that possess increased accuracy across large portions of the input parameter space. We also describe how a user can incorporate such boundaries within standard black box GP emulation packages that are currently available, without altering the core code. Appropriate designs of model runs in the presence of known boundaries are then analysed, with two kinds of general purpose designs proposed. We then apply the improved emulation and design methodology to an important systems biology model of hormonal crosstalk in Arabidopsis Thaliana.

show abstract

ABC for climate: dealing with expensive simulators

Cited by 2 publications

References 41 publications

A Semi-Automatic Method for History Matching using Sequential Monte Carlo

A Semi-Automatic Method for History Matching using Sequential Monte Carlo

Known Boundary Emulation of Complex Computer Models

Contact Info

Product

Resources

About