High-Throughput Prediction of Ultralow Thermal Conductivity Crystals by Sub-Trillion-Scale Atomic Data Integrated Deep Learning Approach

Existing machine learning potentials for predicting phonon properties of crystals are limited to either small amount of training data or a material-to-material basis, primarily due to the exponential scaling of model parameters with the number of atomic species or elements. This renders high-throughput infeasible when facing large-scale new materials. Unlike previous machine learning models with inherently limited training on small data and global properties, we develop Elemental Spatial Density Neural Network Force Field (Elemental-SDNNFF) with abundant atomic level environments as training data. Benefiting from this innovation, we integrate ~50 million atomic data to train a single deep neural network without increased expensive ab initio simulations. The effectiveness and precision of the Elemental-SDNNFF approach is demonstrated on a set of 150,000 inorganic crystals spanning 63 elements in the periodic table by prediction of complete phonon properties. Our algorithm achieved a competitive force root mean square error of about 40 meV/Å and a speed-up of 3 – 4 orders of magnitude in comparison to first principles. Self-improvement schemes such as active learning and data augmentation techniques are also incorporated allowing human-free refinement of the force accuracy on arbitrary combinations of chemistries. Deep insight into the ultralow lattice thermal conductivity (<1 W/mK) of predicted structures are gained by mean square displacement (MSD) and p-d orbital hybridization analysis, which offer quick approaches for fast screening of crystals with strong intrinsic phonon anharmonicity. Our model also quantitatively reveals the correlation between off-diagonal coherence and diagonal populations and identifies the distinct crossover from particle-like to wave-like heat conduction. Our algorithm is promising for accelerating discovery of novel phononic crystals for emerging applications, such as heat dissipation in electronics, thermoelectrics, and coherent phonons for quantum information technology.