The thermal conductivity of minerals is a fundamental parameter in understanding the evolution and dynamics of the Earth. Wadsleyite, the major mineral in the mantle transition zone (MTZ), can contain abundant water. However, how water affects its thermal conductivity remains unknown. Here, we predicted the thermal conductivity of dry and hydrous wadsleyite at high pressure and temperature ( P‐T) by combining non‐equilibrium molecular dynamics and machine learning potential trained with data from first‐principles calculations. We found that the thermal conductivity of wadsleyite is anisotropic and is reduced by ∼10% in the P‐T conditions of the MTZ by the presence of 0.81 wt.% water. The heat flow toward the slab tends to follow the direction with the lowest thermal conductivity due to the lattice‐preferred orientation of wadsleyite and olivine. Both hydration and thermal‐conductivity anisotropy slow down the heating of slabs, allowing hydrous minerals and metastable olivine to survive in the deeper mantle.
The subducted slab was heated by conduction from the ambient mantle. Minerals' thermal conductivity is crucial for us in evaluating the temperature of the slab. Wadsleyite, the high‐pressure polymorph of olivine, can contain significant amounts of water in the wet mantle transition zone and subducting slabs. However, the thermal conductivity of hydrous wadsleyite remains unknown. First‐principles calculations of the thermal conductivity of hydrous wadsleyite are very expensive. Here, we apply machine learning to break the limits of computational costs and obtain the thermal conductivity of dry and hydrous wadsleyite at high temperatures and pressures. We found that water remarkably reduces the thermal conductivity of wadsleyite. The lattice‐preferred orientation and thermal‐conductivity anisotropy of olivine and wadsleyite would have further slowed the heating of the slab. Low temperatures facilitate the survival of hydrous minerals and metastable olivine. Thus, more water could be transported to the deeper Earth by subducting slabs, and the dehydration of hydrous minerals and the transformation of metastable olivine, which may trigger the deep earthquakes, would occur at deeper depths.
A machine learning potential for dry and hydrous wadsleyite approaches the accuracy of first‐principles calculations
The thermal conductivity of wadsleyite is anisotropic with the lowest thermal conductivity along [001] direction and decreases with water
More water could reach the deep mantle and deep‐focus earthquakes could occur deeper due to hydration and lattice‐preferred orientation