Open Access

Halide Double Perovskites (HDPs) are quarternary materials with chemical formula A2BB'X6, which have recently been regaining scientific attention because they show beneficial properties for photovoltaic, X-ray detection, sensing, photocatalysis, and spintronic applications. However, with over 40.000 potential HDP compositions, much of the available landscape remains underexplored. For this, we have generated a database of spin-polarized, hybrid functional (HSE06) DFT electronic structure data, combined with an in-depth chemical bonding analysis using LOBSTER. This was done for all HDPs with Cesium on the A-site and that are predicted to be stable by Bartel's tolerance factor, resulting in a database of quantum-chemical data on ~2600 HDP compositions. The database features some interesting findings, e.g., 134 predicted half-metals. We also used dimensionality reduction (UMAP) to visualize the data and highlight underlying trends, which can be explored in an interactive platform. Furthermore, the database of high-quality quantum-chemical data covering the entire chemical landscape serves as a valuable resource for discovering new halide perovskites using data-driven and machine learning techniques.

Halide double perovskites (ABB'X) are a long-known class of materials that has recently been rediscovered for diverse applications, including photovoltaics, photocatalysis, and radiation detection. Their doubled unit cell provides immense chemical tunability, allowing the incorporation of magnetic ions and enabling access to a wide range of electronic-structure features, including different band-edge characters, alignments, and symmetries. Magnetic elements may further introduce spin degrees of freedom and magnetic behaviour, thereby broadening the functional landscape of these compounds. Here, we present the first comprehensive database of spin-polarised electronic-structure data for all halide double perovskites predicted to be stable by the recently introduced tolerance factor by Bartel et al. The dataset focuses on the CsBB'X family, with X = I, Br, Cl, and F, and includes density of states (DOS) for 2,500 compounds, calculated using hybrid-functional density functional theory. Among these, 719 compounds exhibit band gaps in the visible range and 118 display half-metallic character. In addition, we provide chemical-bonding analysis using \textsc{lobster}, which provides insights into orbital interactions across the dataset. To facilitate exploration, we further offer UMAP-based visualisations and an interactive app for systematic investigation of chemical composition, electronic structure, and magnetic properties.

Adding orbital-based features namely, charge, average density of states, integrated crystal orbital bond index and crystal orbital Hamilton populations to MEGNet architecture reduced materials properties predictions error of last phonon peak frequency, bulk modulus, shear modulus, and average mean squared displacement. Those orbital-based features add bond and atom level messages improve properties predictions.

Machine learning (ML) offers powerful new strategies for accelerating the discovery and design of functional materials. In our work, we develop ML models and software frameworks for large-scale screening and advanced materials simulations, starting from robust high throughput quantum chemical workflows, such as those implemented in atomate2.[1,2] These automated workflows enable the creation of large, high quality materials databases that form the foundation for data science and machine learning. In addition to experimentally known crystal structures, increasingly generative models are used to extend materials databases, which also need to be evaluated.[3] To build predictive, scientifically grounded ML models, we use chemical bonding concepts, incorporating quantum chemical bonding strengths and related descriptors as physically meaningful features to predict vibrational properties and heat transport.[4,5] Beyond property prediction, we address the challenge of determining which hypothetical materials are synthesizable. To this end, we introduced co-training into a positive–unlabelled (PU) learning framework, enabling ML based classification even in the absence of true negative data—an essential step for screening synthesizable compounds.[6,7] To advance atomistic simulations of complex materials, we further developed automated training pipelines for ML interatomic potentials that support both general-purpose and system specific potential development, as implemented in our software autoplex.[8] This automated approach has already facilitated detailed investigations of challenging systems, including the computational exploration of amorphous arsenic.[9] Together, these developments provide a toolbox spanning workflow automation, automated ML potential training, and ML models for materials properties and synthesis, enabling scalable, data driven discovery and understanding of advanced materials.

Environmental and scarcity issues of common functional magnetic materials for, e.g., permanent magnets have intensified the search for rare-earth-free alternatives. This challenge is increasingly met by machine learning of magnetic properties of transition-metal compounds. Surprisingly, bond-angle-derived features were not found to be relevant for magnetic structure prediction in previous studies using DFT-computed labels. This contrasts with the Kanamori-Goodenough-Anderson (KGA) rules of superexchange, present in every magnetism textbook. These semiempirical rules predict whether a nearest-neighbor magnetic interaction in insulators is FM or AFM based on the bond angle, orbital symmetry, and orbital occupancy. For some cases, the rules can be simplified further to only consider the bond angle of neighboring magnetic sites (KGA rules of thumb). We review magnetism—bond angle trends within the MAGNDATA database, the largest collection of experimentally determined magnetic structures. Observed trends follow the KGA rules of thumb, and exceptions can be rationalized. In contrast, bond angles in a popular theoretical DFT database show very different trends and do not depend on the magnetic ordering. Building on our analysis, we engineer heuristic-derived features for the machine learning of magnetic structures. We introduce a new, informative label for predicting magnetic structures that can be extended to magnetic sites and structures of arbitrary complexity. We show that features derived from the heuristic are of high importance for this machine learning task. Beyond this, our model enables the prediction of non-collinear magnetic structures. Further, we analyze local and global structural trends of non-collinear magnets in the MAGNDATA database.