A Bayesian machine learning approach for inverse prediction of high-performance concrete ingredients with targeted performance

Xinyuan Ke, Yu Duan

Research output: Contribution to journalArticlepeer-review

36 Citations (SciVal)


High-performance concrete (HPC) plays an important role in improving the sustainability and reliability of buildings and infrastructures. Machine learning predictive models have been used for predicting concrete performance from ingredients, however it remains a challenge to achieve inverse prediction of ingredients from targeted performances. This study proposes an in-house coded informatics-based materials analysis framework to enable computational design of HPC with targeted strength performance. The Gaussian processes (GP) emulator is used to construct the surrogate predictive model based-on 453 experimental measurements. The validity of the GP emulator is assessed using the leave-one-out cross-validation (LOO-CV) and also a separate validation dataset. The variance-based global sensitivity analysis, Sobol indices, is applied to understand the impact of physical ingredients on the HPC performances. The results suggest that the trained GP emulator can provide sufficiently accurate and reliable predictions, as well as reflect the real-world physicochemical nature of HPC materials. The inverse material design is achieved by the Bayesian inference method with a Markov chain Monte Carlo stochastic sampling method, the Metropolis-Hastings (MH) algorithm. Combining with the Bayesian inference method, the proposed design framework can infer a list of potential HPC formulae of a targeted performance, each evaluated by the likelihood of resulting in the targeted strength. The data-driven material analysis and design framework proposed in this study provides a novel approach to achieve performance-based design of HPC, with the potential to maximise resource efficiency and reduce economical cost. The methodology presented in this study can also be extended to be applied to a wide range of construction materials, targeting difference service performances including durability.

Original languageEnglish
Article number121424
JournalConstruction and Building Materials
Early online date6 Nov 2020
Publication statusPublished - 8 Feb 2021

Bibliographical note

Funding Information:
The participation of XKe is sponsored by the University of Bath Prize Fellowship . The authors would like to thank Professor I-Cheng Yeh for providing the database.

Publisher Copyright:
© 2020 Elsevier Ltd

Copyright 2020 Elsevier B.V., All rights reserved.


  • Bayesian inference
  • Global sensitivity analysis
  • High-performance concrete
  • Informatics design
  • Markov chain Monte Carlo
  • Sobol indices

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • General Materials Science


Dive into the research topics of 'A Bayesian machine learning approach for inverse prediction of high-performance concrete ingredients with targeted performance'. Together they form a unique fingerprint.

Cite this