Conventional phase diagram generation involves experimentation to provide an initial estimate of the set of thermodynamically accessible phases and their boundaries, followed by use of phenomenological models to interpolate between the available experimental data points and extrapolate to experimentally inaccessible regions. Such an approach, combined with high throughput first-principles calculations and data-mining techniques, has led to exhaustive thermodynamic databases (e.g. compatible with the CALPHAD method), albeit focused on the reduced set of phases observed at distinct thermodynamic equilibria. In contrast, materials during their synthesis, operation, or processing, may not reach their thermodynamic equilibrium state but, instead, remain trapped in a local (metastable) free energy minimum, which may exhibit desirable properties. Here, we introduce an automated workflow that integrates first-principles physics and atomistic simulations with machine learning (ML), and high-performance computing to allow rapid exploration of the metastable phases to construct “metastable” phase diagrams for materials far-from-equilibrium. Using carbon as a prototypical system, we demonstrate automated metastable phase diagram construction to map hundreds of metastable states ranging from near equilibrium to far-from-equilibrium (400 meV/atom). We incorporate the free energy calculations into a neural-network-based learning of the equations of state that allows for efficient construction of metastable phase diagrams. We use the metastable phase diagram and identify domains of relative stability and synthesizability of metastable materials. High temperature high pressure experiments using a diamond anvil cell on graphite sample coupled with high-resolution transmission electron microscopy (HRTEM) confirm our metastable phase predictions. In particular, we identify the previously ambiguous structure of n-diamond as a cubic-analog of diaphite-like lonsdaelite phase. Exploration of metastable phases of a given elemental composition is a data-intensive task. Here the authors integrate first-principles atomistic simulations with machine learning and high-performance computing to allow a rapid exploration of the metastable phases of carbon.

AUSTIN – The Railroad Commission has turned to artificial intelligence to optimize the time the agency's technical analysts spend on seismicity reviews to ensure residents and the environment are protected. Seismicity reviews are conducted by the Underground Injection Control (UIC) Department for injection/disposal well permits in areas susceptible to earthquakes and in certain geologic zones. UIC staff programed a machine learning algorithm to help with the large amount of information that needs to be processed and digested. Along with some other changes, tasks performed by the machine learning algorithm have enabled UIC to wipe out a backlog of seismic reviews to zero today. Like the technical analyst, the AI program weighs many factors related to the number, severity and proximity of earthquakes and uses a decision tree to assign a grade to the review.