Discovering the ultralow thermal conductive A_(2)B_(2)O_(7)-type high-entropy oxides through the hybrid knowle dge-assiste d data-driven machine learning

Lattice engineering and distortion have been considered one kind of effective strategies for discovering advanced materials.The instinct chemical flexibility of high-entropy oxides(HEOs)motivates/accelerates to tailor the target properties through phase transformations and lattice distortion.Here,a hybrid knowledge-assisted data-driven machine learning(ML)strategy is utilized to discover the A_(2)B_(2)O_(7)-type HEOs with low thermal conductivity(κ)through 17 rare-earth(RE=Sc,Y,La-Lu)solutes optimized A-site.A designing routine integrating the ML and high throughput first principles has been proposed to predict the key physical parameter(KPPs)correlated to the targetedκof advanced HEOs.Among the smart-designed 6188(5RE_(0.2))_(2)Zr_(2)O_(7)HEOs,the best candidates are addressed and validated by the princi-ples of severe lattice distortion and local phase transformation,which effectively reduceκby the strong multi-phonon scattering and weak interatomic interactions.Particularly,(Sc_(0.2)Y_(0.2)La_(0.2)Ce_(0.2)Pr_(0.2))_(2)Zr_(2)O_(7)with predictedκbelow 1.59 Wm^(−1)K^(−1)is selected to be verified,which matches well with the ex-perimentalκ=1.69 Wm^(−1)K^(−1)at 300 K and could be further decreased to 0.14 Wm^(−1)K^(−1)at 1473 K.Moreover,the coupling effects of lattice vibrations and charges on heat transfer are revealed by the cross-validations of various models,indicating that the weak bonds with low electronegativity and few bond-ing charge density and the lattice distortion(r∗)identified by cation radius ratio(r A/r B)should be the KPPs to decreaseκefficiently.This work supports an intelligent designing strategy with limited atomic and electronic KPPs to accelerate the development of advanced multi-component HEOs with proper-ties/performance at multi-scales.