The high-entropy strategy has demonstrated significant advantages in improving the recoverable energy storage density (W_rec) and efficiency (η) of lead-free dielectric capacitors. However, exploring high-performance ceramics within the vast composition space of high-entropy systems using traditional trial-and-error methods remains highly challenging and inefficient. In this study, we employed a machine learning (ML)-accelerated strategy to overcome this limitation. A random forest regression model was developed using a dataset of BaTiO₃ (BT)-based ceramics. Combined with the expected improvement acquisition function, this approach enabled efficient navigation through a space of 660,000 candidate compositions, markedly reducing the experimental burden compared with conventional methods. The optimal composition guided by ML, Ba_0.24Sr_0.24Bi_0.26Na_0.26Ti_0.85Zr_0.15O₃, was experimentally verified to lie in the crossover region between relaxor ferroelectrics and superparaelectrics. In this region, the synergistic coexistence of nanodomains and polar nanoclusters leads to a large polarization difference between the maximum polarization and the remnant polarization (ΔP = P_max − P_r), which is the structural origin of the ultrahigh W_rec of 10.8 J·cm⁻³ and high η of 86%. Furthermore, its excellent charge–discharge performance and stability in terms of temperature and frequency highlight its potential for practical applications, demonstrating the efficacy of machine learning in advancing energy storage ceramics.

Single-phase multiferroic materials of rare-earth orthoferrites with magnetism and ferroelectricity are of great technological importance in storage devices. However, the polarization (P) of these materials is generally weak (0.01 μC·cm⁻²), and the ferroelectricity is reported to exist below room temperature (25 ℃). Here, (Bi_0.2La_0.2Y_0.2Dy_0.2Tb_0.2)FeO₃ (BLYDTFO) high-entropy oxides that exhibit a saturation P of 5.3 μC·cm⁻² at the electric field (E) of 45 kV·cm⁻¹ at room temperature was designed and fabricated by the conventional solid-phase method. The results show that configurational entropy introduces atomic disorder and a larger tilt of BO₆ octahedron, which facilitates non-centrosymmetric distortion and ferroelectricity at room temperature compared with other single components (LaFeO₃, YFeO₃, DyFeO₃, and TbFeO₃). This high-entropy approach expands the compositional window of the rare-earth orthoferrites to enhance the ferroelectricity in multiferroic applications.

High-entropy oxides with complex compositions can be designed as novel ferroelectric materials with interesting physical consequences. A single-phase (K_0.5Bi_0.5)_0.2Ba_0.2Sr_0.2Ca_0.2Mg_0.2TiO₃ high-entropy ceramic with a perovskite structure was synthesized by a conventional high-temperature solid-state method, and the dielectric and ferroelectric properties of the ceramic were investigated. The results show that there are no relaxation peaks in the test temperature range because of the multi-element doping. The dielectric constant of ceramic has a high-temperature stability at < 300 ℃ . The maximum dielectric constant of 8887 is obtained at 100 Hz and 650 ℃ . The introduction of high-entropy oxide in the ceramic can have high-entropy ferroelectrics in complex materials, and modify the properties of electronic ceramic.