Interpretable multi-source data fusion through Latent Variable Gaussian Process

With the advent of artificial intelligence and machine learning, various domains of science and engineering communities have leveraged data-driven surrogates to model complex systems through fusing numerous sources of information (data) from published papers, patents, open repositories, or other available resources. However, very little attention has been paid to the differences in quality and comprehensiveness of the known and unknown underlying physical parameters of the information sources, which could have downstream implications during system optimization. Towards resolving this issue, an interpretable multi-source data fusion framework based on Latent Variable Gaussian Process (LVGP) model is proposed. The individual data sources are first labeled as categorical variables and then mapped into a physically meaningful latent space, enabling the development of a source-aware data fusion model. Additionally, a dissimilarity metric based on the learned latent variables of the LVGP is introduced to study and understand the differences between the data sources. The proposed approach is demonstrated on and analyzed through two mathematical and two materials engineering case studies. From the case studies, it is observed that the proposed multi-source data fusion framework provides more accurate predictions for sparse data scenarios compared to single-source or source-unaware data fusion models.

Authors

• Sandipp Krishnan Ravi
• Yigitcan Comlek
• Arjun Pathak
• Vipul Gupta
• Rajnikant Umretiya
• Andrew Hoffman
• Ghanshyam Pilania
• Piyush Pandita
• Sayan Ghosh
• Nathaniel Mckeever
• Wei Chen
• Liping Wang

Keywords

• Latent Variable Gaussian Process
• Gaussian process regression
• Multi-source modeling
• Data fusion
• Interpretable Artificial Intelligence
• Uncertainty quantification
• Probabilistic machine learning