Efficient Emulation of Computer Models Utilising Multiple Known Boundaries of Differing Dimension

Emulation has been successfully applied across a wide variety of scientific disciplines for efficiently analysing computationally intensive models. We develop known boundary emulation strategies which utilise the fact that, many computer models, there exist hyperplanes in input parameter space model output can be evaluated far more efficiently, whether this analytically or just significantly faster using efficient and simpler numerical solver. The information contained on these hyperplanes, boundaries, incorporated into process via analytical update, thus involving no additional computational cost. In article, we show that such updates are available multiple boundaries various dimensions. subsequently demonstrate configurations for, particular by presenting set conditions must satisfy. powerful advantages techniques developed both an illustrative low-dimensional simulated example scientifically relevant high-dimensional systems biology hormonal crosstalk roots Arabidopsis plant.