Multi-task Modeling for Engineering Applications with Sparse Data
By: Yigitcan Comlek , R. Murali Krishnan , Sandipp Krishnan Ravi and more
Potential Business Impact:
Builds better models with less expensive data.
Modern engineering and scientific workflows often require simultaneous predictions across related tasks and fidelity levels, where high-fidelity data is scarce and expensive, while low-fidelity data is more abundant. This paper introduces an Multi-Task Gaussian Processes (MTGP) framework tailored for engineering systems characterized by multi-source, multi-fidelity data, addressing challenges of data sparsity and varying task correlations. The proposed framework leverages inter-task relationships across outputs and fidelity levels to improve predictive performance and reduce computational costs. The framework is validated across three representative scenarios: Forrester function benchmark, 3D ellipsoidal void modeling, and friction-stir welding. By quantifying and leveraging inter-task relationships, the proposed MTGP framework offers a robust and scalable solution for predictive modeling in domains with significant computational and experimental costs, supporting informed decision-making and efficient resource utilization.
Similar Papers
Physics-augmented Multi-task Gaussian Process for Modeling Spatiotemporal Dynamics
Machine Learning (CS)
Predicts heart electricity flow better using physics.
Efficient multi-fidelity Gaussian process regression for noisy outputs and non-nested experimental designs
Applications
Improves computer predictions with less data.
Derivation of Output Correlation Inferences for Multi-Output (aka Multi-Task) Gaussian Process
Machine Learning (CS)
Helps computers learn from many related tasks.