Fusing Direct and Indirect Measurements Through Multi‐Fidelity Learning For Accelerated Electrocaloric Materials Discovery

Abstract

ABSTRACT The data‐driven discovery of high‐performance electrocaloric (EC) materials is challenged by sparse direct measurements and systematic discrepancies between direct and indirect measurements, resulting in heterogeneous datasets with varying fidelity levels. Here, a co‐kriging‐based multi‐fidelity learning framework is developed to integrate these data sources and construct a robust predictive model for BaTiO3‐based ferroelectric ceramics by explicitly modeling cross‐fidelity correlation and discrepancy. Combined with a multi‐objective active learning strategy, the framework enables efficient optimization of low‐temperature EC strength and operational temperature span across the composition–processing space. Guided by this approach, a multi‐element‐doped BaTiO3‐based ceramic exhibiting an EC strength of 0.06×10−6 K·m/V at together with a broad operational temperature span of 75 K is identified. Experimental characterization reveals that the enhanced performance originates from a suppressed and diffuse phase transition associated with a relaxor‐like or weakly ordered state, enabling broad temperature stability together with large reversible polarization. These results demonstrate that integrating multi‐fidelity learning with active learning provides an effective strategy for accelerating functional materials discovery under realistic experimental constraints.