English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A majority of experimental disciplines face the challenge of exploring largeand high-dimensional parameter spaces in search of new scientific discoveries.Materials science is no exception; the wide variety of synthesis, processing,and environmental conditions that influence material properties gives rise toparticularly vast parameter spaces. Recent advances have led to an increase inefficiency of materials discovery by increasingly automating the explorationprocesses. Methods for autonomous experimentation have become moresophisticated recently, allowing for multi-dimensional parameter spaces to beexplored efficiently and with minimal human intervention, thereby liberatingthe scientists to focus on interpretations and big-picture decisions. Gaussianprocess regression (GPR) techniques have emerged as the method of choice forsteering many classes of experiments. We have recently demonstrated thepositive impact of GPR-driven decision-making algorithms on autonomouslysteering experiments at a synchrotron beamline. However, due to the complexityof the experiments, GPR often cannot be used in its most basic form, but ratherhas to be tuned to account for the special requirements of the experiments. Tworequirements seem to be of particular importance, namely inhomogeneousmeasurement noise (input dependent or non-i.i.d.) and anisotropic kernelfunctions, which are the two concepts that we tackle in this paper. Oursynthetic and experimental tests demonstrate the importance of both conceptsfor experiments in materials science and the benefits that result fromincluding them in the autonomous decision-making process.

Autonomous Materials Discovery Driven by Gaussian Process Regression with Inhomogeneous Measurement Noise and Anisotropic Kernels