TY - JOUR A1 - Riebesell, Janosh A1 - Goodall, Rhys E. A. A1 - Benner, Philipp A1 - Chiang, Yuan A1 - Deng, Bowen A1 - Ceder, Gerbrand A1 - Asta, Mark A1 - Lee, Alpha A. A1 - Jain, Anubhav A1 - Persson, Kristin A. T1 - A framework to evaluate machine learning crystal stability predictions N2 - The rapid adoption of machine learning in various scientific domains calls for the development of best practices and community agreed-upon benchmarking tasks and metrics. We present Matbench Discovery as an example evaluation framework for machine learning energy models, here applied as pre-filters to first-principles computed data in a high-throughput search for stable inorganic crystals. We address the disconnect between (1) thermodynamic stability and formation energy and (2) retrospective and prospective benchmarking for materials discovery. Alongside this paper, we publish a Python package to aid with future model submissions and a growing online leaderboard with adaptive user-defined weighting of various performance metrics allowing researchers to prioritize the metrics they value most. To answer the question of which machine learning methodology performs best at materials discovery, our initial release includes random forests, graph neural networks, one-shot predictors, iterative Bayesian optimizers and universal interatomic potentials. We highlight a misalignment between commonly used regression metrics and more task-relevant classification metrics for materials discovery. Accurate regressors are susceptible to unexpectedly high false-positive rates if those accurate predictions lie close to the decision boundary at 0 eV per atom above the convex hull. The benchmark results demonstrate that universal interatomic potentials have advanced sufficiently to effectively and cheaply pre-screen thermodynamic stable hypothetical materials in future expansions of high-throughput materials databases. KW - Machine Learning KW - Interatomic Potentials PY - 2025 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-637139 DO - https://doi.org/10.1038/s42256-025-01055-1 SN - 2522-5839 VL - 7 IS - 6 SP - 836 EP - 847 PB - Springer Science and Business Media LLC AN - OPUS4-63713 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - INPR A1 - Ueltzen, Katharina A1 - Naik, Aakash A. A1 - Ertural, Christina A1 - Benner, Philipp A1 - George, Janine T1 - Can simple exchange heuristics guide us in predicting magnetic properties of solids? N2 - A popular heuristic derived from the Kanamori-Goodenough-Anderson rules of superexchange connects bond angles and magnetism in certain transition metal compounds. We evaluate the fulfillment of this heuristic on databases of magnetic structures. The heuristic is partly satisfied in magnetic structures from experiment, and exceptions can be rationalized. We further show that incorporating this heuristic into machine learning models for magnetism improves the prediction. KW - Magnetism KW - Transition Metal Compounds KW - Materials Design KW - Sustainable Materials Design KW - Machine Learning KW - Materials Understanding PY - 2025 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-639290 DO - https://doi.org/10.26434/chemrxiv-2025-xj84d VL - Version 1 SP - 1 EP - 43 AN - OPUS4-63929 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - INPR A1 - Amariamir, Sasan A1 - George, Janine A1 - Benner, Philipp T1 - SynCoTrain: A Dual Classifier PU-learning Framework for Synthesizability Prediction N2 - Material discovery is a cornerstone of modern science, driving advancements in diverse disciplines from biomedical technology to climate solutions. Predicting synthesizability, a critical factor in realizing novel materials, remains a complex challenge due to the limitations of traditional heuristics and thermodynamic proxies. While stability metrics such as formation energy offer partial insights, they fail to account for kinetic factors and technological constraints that influence synthesis outcomes. These challenges are further compounded by the scarcity of negative data, as failed synthesis attempts are often unpublished or context-specific. We present SynCoTrain, a semi-supervised machine learning model designed to predict the synthesizability of materials. SynCoTrain employs a co-training framework leveraging two complementary graph convolutional neural networks: SchNet and ALIGNN. By iteratively exchanging predictions between classifiers, SynCoTrain mitigates model bias and enhances generalizability. Our approach uses Positive and Unlabeled (PU) Learning to address the absence of explicit negative data, iteratively refining predictions through collaborative learning. The model demonstrates robust performance, achieving high recall on internal and leave-out test sets. By focusing on oxide crystals, a well-characterized material family with extensive experimental data, we establish SynCoTrain as a reliable tool for predicting synthesizability while balancing dataset variability and computational efficiency. This work highlights the potential of co-training to advance high-throughput materials discovery and generative research, offering a scalable solution to the challenge of synthesizability prediction. KW - Materials Design KW - Materials Discovery KW - Synthesizability KW - Machine Learning KW - Cotraining KW - New Materials KW - Materials Acceleration Platforms PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-622104 DO - https://doi.org/10.48550/arXiv.2411.12011 SP - 1 EP - 39 AN - OPUS4-62210 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Naik, Aakash A1 - Ertural, Christina A1 - Dhamrait, Nidal A1 - Benner, Philipp A1 - George, Janine T1 - A Quantum-Chemical Bonding Database for Solid-State Materials N2 - An in-depth insight into the chemistry and nature of the individual chemical bonds is essential for understanding materials. Bonding analysis is thus expected to provide important features for large-scale data analysis and machine learning of material properties. Such chemical bonding information can be computed using the LOBSTER software package, which post-processes modern density functional theory data by projecting the plane wave-based wave functions onto an atomic orbital basis. With the help of a fully automatic workflow, the VASP and LOBSTER software packages are used to generate the data. We then perform bonding analyses on 1520 compounds (insulators and semiconductors) and provide the results as a database. The projected densities of states and bonding indicators are benchmarked on standard density-functional theory computations and available heuristics, respectively. Lastly, we illustrate the predictive power of bonding descriptors by constructing a machine learning model for phononic properties, which shows an increase in prediction accuracies by 27% (mean absolute errors) compared to a benchmark model differing only by not relying on any quantum-chemical bonding features. KW - Bonding Analysis KW - DFT KW - High-throughput KW - Database KW - Phonons KW - Machine Learning PY - 2023 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-582892 DO - https://doi.org/10.1038/s41597-023-02477-5 VL - 10 IS - 1 SP - 1 EP - 18 AN - OPUS4-58289 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Benner, Philipp A1 - Grandel, Jonas T1 - A shortcut towards phonon predictions N2 - Phonon calculations with ab-initio methods are computationally expensive. The use of universal machine learning models reduces the cost, but raises concerns about prediction quality. Fine-tuning with only a few structures, improves predictions of phonons, thermal properties and especially diffusive thermal conductivity, while reducing computational cost by a factor of 10 in average compared to DFT methods. T2 - DPG Frühjahrstagung CY - Regensburg, Germany DA - 16.03.2025 KW - Machine Learning KW - MACE KW - Phonons PY - 2025 AN - OPUS4-62770 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Nowatzky, Yannek A1 - Russo, Francesco Friedrich A1 - Lisec, Jan A1 - Kister, Alexander A1 - Reinert, Knut A1 - Muth, Thilo A1 - Benner, Philipp T1 - FIORA: Local neighborhood-based prediction of compound mass spectra from single fragmentation events N2 - Non-targeted metabolomics holds great promise for advancing precision medicine and biomarker discovery. However, identifying compounds from tandem mass spectra remains a challenging task due to the incomplete nature of spectral reference libraries. Augmenting these libraries with simulated mass spectra can provide the necessary references to resolve unmatched spectra, but generating high-quality data is difficult. In this study, we present FIORA, an open-source graph neural network designed to simulate tandem mass spectra. Our main contribution lies in utilizing the molecular neighborhood of bonds to learn breaking patterns and derive fragment ion probabilities. FIORA not only surpasses state-of-the-art fragmentation algorithms, ICEBERG and CFM-ID, in prediction quality, but also facilitates the prediction of additional features, such as retention time and collision cross section. Utilizing GPU acceleration, FIORA enables rapid validation of putative compound annotations and large-scale expansion of spectral reference libraries with high-quality predictions. KW - Metabolomics KW - Machine Learning KW - Mass spectrometry KW - Bioinformatics PY - 2025 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-627585 DO - https://doi.org/10.1038/s41467-025-57422-4 SN - 2041-1723 VL - 16 IS - 1 SP - 1 EP - 17 PB - Springer Science and Business Media LLC AN - OPUS4-62758 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - INPR A1 - Naik, Aakash A. A1 - Dhamrait, Nidal A1 - Ueltzen, Katharina A1 - Ertural, Christina A1 - Benner, Philipp A1 - Rignanese, Gian-Marco A1 - George, Janine T1 - A critical assessment of bonding descriptors for predicting materials properties N2 - Most machine learning models for materials science rely on descriptors based on materials compositions and structures, even though the chemical bond has been proven to be a valuable concept for predicting materials properties. Over the years, various theoretical frameworks have been developed to characterize bonding in solid-state materials. However, integrating bonding information from these frameworks into machine learning pipelines at scale has been limited by the lack of a systematically generated and validated database. Recent advances in high-throughput bonding analysis workflows have addressed this issue, and our previously computed Quantum-Chemical Bonding Database for Solid-State Materials was extended to include approximately 13,000 materials. This database is then used to derive a new set of quantum-chemical bonding descriptors. A systematic assessment is performed using statistical significance tests to evaluate how the inclusion of these descriptors influences the performance of machine-learning models that otherwise rely solely on structure- and composition-derived features. Models are built to predict elastic, vibrational, and thermodynamic properties typically associated with chemical bonding in materials. The results demonstrate that incorporating quantum-chemical bonding descriptors not only improves predictive performance but also helps identify intuitive expressions for properties such as the projected force constant and lattice thermal conductivity via symbolic regression. KW - Bonding Analysis KW - Machine Learning KW - Symbolic Regression KW - Chemical Understanding KW - Phonons KW - Thermal Conductivity PY - 2026 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-655150 DO - https://doi.org/10.48550/arXiv.2602.12109 SP - 1 EP - 28 PB - Cornell University CY - Ithaca, NY AN - OPUS4-65515 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - GEN A1 - Ueltzen, Katharina A1 - Naik, Aakash A1 - Ertural, Christina A1 - Benner, Philipp A1 - George, Janine T1 - Software and data repository: Can simple exchange heuristics guide us in predicting magnetic properties of solids? N2 - Software and data for the publication "Can simple exchange heuristics guide us in predicting magnetic properties of solids?" Release that corresponds to the first preprint version of the article. Full Changelog: https://github.com/DigiMatChem/paper-exchange-heuristics-in-magnetic-materials/commits/v1.0.0 KW - Magnetism KW - Machine Learning KW - Materials Design KW - Chemically Complex Materials KW - Sustainable Materials Design PY - 2025 DO - https://doi.org/10.5281/zenodo.16811104 PB - Zenodo CY - Geneva AN - OPUS4-64672 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -