The primary challenge in the field of high-temperature superconductivity in hydrides is to achieve a superconducting state at ambient pressure rather than the extreme pressures that have been required in experiments so far. Here, we propose a family of compounds, of composition Mg₂XH₆ with X = Rh, Ir, Pd, or Pt, that achieves this goal. These materials were identified by scrutinizing more than a million compounds using a machine-learning accelerated high-throughput workflow. We predict that their superconducting transition temperatures are in the range of 45–80 K, or even above 100 K with appropriate electron doping of the Pt compound. These results indicate that, although very rare, high-temperature superconductivity in hydrides is achievable at room pressure.

A machine‐learning‐assisted approach is employed to search for superconducting hydrides under ambient pressure within an extensive dataset comprising over 150 000 compounds. The investigation yields ≈50 systems with transition temperatures surpassing 20 K, and some even reaching above 70 K. These compounds have very different crystal structures, with different dimensionality, chemical composition, stoichiometry, and arrangement of the hydrogens. Interestingly, most of these systems display slight thermodynamic instability, implying that their synthesis will re quire conditions beyond ambient equilibrium. Moreover, a consistent chemical composition is found in the majority of these systems, which combines alkali or alkali‐earth elements with noble metals. This observation suggests a promising avenue for future experimental investigations into high‐temperature superconductivity within hydrides at ambient pressure.

A large scale study of conventional superconducting materials using a machine‐learning accelerated high‐throughput workflow is performed, starting by creating a comprehensive dataset of around 7000 electron–phonon calculations performed with reasonable convergence parameters. This dataset is then used to train a robust machine learning model capable of predicting the electron–phonon and superconducting properties based on structural, compositional, and electronic ground‐state properties. Using this machine, the transition temperatures (T_c) of approximately 200 000 metallic compounds are evaluated, all of which are on the convex hull of thermodynamic stability (or close to it) to maximize the probability of synthesizability. Compounds predicted to have T_c values exceeding 5 K are further validated using density‐functional perturbation theory. As a result, 541 compounds with T_c values surpassing 10 K, encompassing a variety of crystal structures and chemical compositions, are identified. This work is complemented with a detailed examination of several interesting materials, including nitrides, hydrides, and intermetallic compounds. Particularly noteworthy is LiMoN₂, which is predicted to be superconducting in the stoichiometric trigonal phase, with a T_c exceeding 38 K. LiMoN₂ has previously been synthesized in this phase, further heightening its potential for practical applications.

Delafossite crystals are fascinating ternary oxides that have demonstrated transparent conductivity and ambipolar doping. Here we use a high-throughput approach based on density functional theory to find delafossite and related layered phases of composition ABX₂, where A and B are elements of the periodic table, and X is a chalcogen (O, S, Se, and Te). From the 15 624 compounds studied in the trigonal delafossite prototype structure, 285 are within 50 meV/atom from the convex hull of stability. These compounds are further investigated using global structural prediction methods to obtain their lowest-energy crystal structure. We find 79 systems not present in the materials project database that are thermodynamically stable and crystallize in the delafossite or in closely related structures. These novel phases are then characterized by calculating their band gaps and hole effective masses. This characterization unveils a large diversity of properties, ranging from normal metals, magnetic metals, and some candidate compounds for p-type transparent electrodes.