Search papers, labs, and topics across Lattice.
This paper introduces an active-learning (AL)-guided adaptive search-space refinement framework that integrates with multi-objective Bayesian optimization (BO) to enhance materials discovery efficiency. By strategically refining the candidate space, the method significantly reduces the evaluation burden while maintaining over 99% of the original hypervolume, leading to improved early convergence and cumulative Pareto-front discovery. The approach is validated through applications in CH4/N2 separation and pressure-vessel design, showcasing its effectiveness in optimizing large-scale materials under limited evaluation budgets.
Active learning can cut candidate evaluation space in half while retaining nearly all valuable design options in materials optimization.
Advanced materials discovery increasingly relies on machine learning and Bayesian optimization to explore large discrete design spaces under limited evaluation budgets. However, conventional Bayesian optimization (BO) can become inefficient as candidate spaces grow, often evaluating low-value regions before reaching informative areas. We propose an active-learning (AL)-guided adaptive search-space refinement framework combined with multi-objective BO to accelerate materials optimization while preserving Pareto-relevant regions. We evaluate the approach on CH4/N2 separation in covalent-organic frameworks and pressure-vessel design with material-direction stress components and thickness objectives. Results show that the AL-guided refinement reduces the candidate space by approximately half while preserving more than 99 percent of the original hypervolume. The reduced-space strategy improves early convergence and cumulative Pareto-front discovery from the BO, demonstrating efficient large-scale materials optimization across constrained autonomous materials discovery settings.
