TY - CONF A1 - George, Janine T1 - Materials design using chemical heuristics, workflows, and machine learning N2 - Bonds and local atomic environments are key descriptors of material properties, used to establish design rules and heuristics, and serve as descriptors in machine-learned interatomic potentials and the general machine learning of material properties. Software implementations such as ChemEnv and LobsterEnv identify local atomic environments based on geometrical characteristics and quantum-chemical bonding analysis (here using Crystal Orbital Hamilton Populations as computed with LOBSTER). Fully automated workflows and analysis tools now enable large-scale quantum-chemical bonding analysis. The first part of the lecture will demonstrate how these tools help develop new machine-learning models and intuitive understandings of material properties. New universal machine-learned interatomic potentials, such as MACE-MP-0, have been developed. The second part of the lecture will showcase how these potentials, combined with DFT, can accelerate research. It will focus on the interplay between DFT and machine-learned interatomic potentials, presenting automated workflows for training, fine-tuning, and benchmarking these potentials, implemented in our software autoplex. Additionally, it will show how to train new interatomic potentials from scratch by exploring potential energy surfaces, with the potential to enhance current universal machine-learned potentials. The lecture will also discuss the trend toward automation in computational materials science and our recent contributions. T2 - FAIRmat Seminar CY - Berlin, Germany DA - 05.06.2025 KW - Automation KW - Machine learning KW - Synthesizability KW - Sustainable materials design KW - High-throughput KW - Bonding analysis KW - Materials acceleration platforms PY - 2025 AN - OPUS4-63315 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Naik, Aakash T1 - Harnessing quantum chemical bonding analysis descriptors for material property predictions N2 - Examining the bonding between their constituent atoms in crystalline materials has played a vital role in understanding material properties.[1–4] For instance, low thermal conductivity in materials is typically attributed to its anharmonicity, which has been reported to arise from strong antibonding interactions and local environment distortions.[5–7] The bonds in the material are often quantified in terms of bond strength and can be extracted from crystalline materials using density-based[8], energy-based[9], and orbital-based[10] methods. LOBSTER[11] is a program that relies on an orbital-based method to extract such bonding information by projecting the plane wave-based wave functions of modern density functional theory computations (DFT) onto a local atomic orbital basis. Since our goal was to use bonding analysis descriptors for material property predictions, we needed to first systematically generate large quantities of bonding analysis data. To streamline this process, we have developed a user-friendly workflow[12], which is now also part of the atomate2[13] package that can generate bonding information data extracted using the LOBSTER program for crystalline materials. This workflow requires only the structure as input from the user. Employing this workflow, we have generated for ~13000 crystalline compounds such bonding analysis data. To create new descriptors from these data, we use our package LobsterPy.[14] The curated descriptors span different types, including statistical representations of bonding characteristics for traditional ML algorithms (e.g., random forests), textual descriptions for large language models (LLMs), and structure graphs for graph neural networks (GNNs). These descriptors are then tested by employing them in several state-of-the-art ML algorithms and architectures to predict the mechanical, vibrational, and thermal properties of crystalline materials. Through this work, we are not only able to demonstrate how one can enhance the model’s predictive accuracy[15] by incorporating quantum chemical bonding-based descriptors alongside typical composition and structure-based descriptors but it also aids in uncovering relationships between bonding and materials properties on a larger scale, which was not possible before. T2 - MRS SPRING 2025 CY - Seattle, WA, USA DA - 07.04.2025 KW - Bonding analysis KW - Machine learning KW - Materials Descriptors PY - 2025 AN - OPUS4-63001 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Naik, Aakash Ashok T1 - Linking quantum chemical bonding analysis descriptors to material property predictions N2 - Examining the bonding between their constituent atoms in crystalline materials has played a vital role in understanding material properties. For instance, low thermal conductivity in materials is typically attributed to its anharmonicity, which has been reported to arise from strong antibonding interactions and local environment distortions. Employing an automated for bonding analysis that we developed, we have generated for ~13000 crystalline compounds such bonding analysis data. To create new descriptors from these data automatically, we extended our package LobsterPy. The curated descriptors span different types, including statistical representations of bonding characteristics for traditional ML algorithms (e.g., random forests), textual descriptions for large language models (LLMs), and structure graphs for graph neural networks (GNNs). These descriptors are then tested by employing them in several state-of-the-art ML algorithms and architectures to predict the mechanical, vibrational, and thermal properties of crystalline materials. Through this work, we are not only able to demonstrate how one can enhance the model’s predictive accuracy by incorporating quantum chemical bonding-based descriptors alongside typical composition and structure-based descriptors, but it also aids in uncovering relationships between bonding and materials properties on a larger scale, which was not possible before. T2 - AI MSE 2025 CY - Bochum, Germany DA - 18.11.2025 KW - Bonding analysis KW - Machine learning KW - Materials Descriptors KW - Force constants PY - 2025 AN - OPUS4-64791 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Ghosh, Sheuly A1 - Ueltzen, Katharina A1 - George, Janine A1 - Neugebauer, Jörg A1 - Körmann, Fritz T1 - Chemical ordering and magnetism in face-centered cubic CrCoNi alloy N2 - AbstractThe impact of magnetism on chemical ordering in face-centered cubic CrCoNi medium entropy alloy is studied by a combination of ab initio simulations, machine learning potentials, and Monte Carlo simulations. Large magnetic energies are revealed for some mixed L12/L10 type ordered configurations, which are rooted in strong nearest-neighbor magnetic exchange interactions and chemical bonding among the constituent elements. There is a delicate interplay between magnetism and stability of MoPt2 and L12/L10 type of order, which may explain opposing experimental and theoretical findings. KW - Chemically complex materials KW - Alloys KW - Magnetism KW - Bonding analysis KW - Machine learning KW - Machine-learned interatomic potentials PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-623114 DO - https://doi.org/10.1038/s41524-024-01439-8 SN - 2057-3960 VL - 10 IS - 1 SP - 1 EP - 10 PB - Springer Science and Business Media LLC AN - OPUS4-62311 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - GEN A1 - Ghosh, Sheuly A1 - Ueltzen, Katharina A1 - George, Janine A1 - Neugebauer, Jörg A1 - Körmann, Fritz T1 - Chemical ordering and magnetism in face-centered cubic CrCoNi alloy N2 - The impact of magnetism on chemical ordering in face-centered cubic CrCoNi medium entropy alloy is studied by a combination of ab initio simulations, machine learning potentials, and Monte Carlo simulations. Large magnetic energies are revealed for some mixed L12 /L10 type ordered configurations, which are rooted in strong nearest-neighbor magnetic exchange interactions and chemical bonding among the constituent elements. There is a delicate interplay between magnetism and stability of MoPt2 and L12 /L10 type of ordering which may explain opposing experimental and theoretical findings. KW - Bonding analysis KW - Alloys KW - Magnetism KW - Material design PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-600040 DO - https://doi.org/10.21203/rs.3.rs-3978660/v1 SN - 2693-5015 SP - 1 EP - 13 PB - Research Square Platform LLC CY - Durham, NC AN - OPUS4-60004 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Naik, Aakash T1 - Material property predictions by incorporating quantum chemical bonding information N2 - Interactions between constituent atoms in crystalline materials have been shown to influence the properties of materials, such as elasticity, ionic and thermal conductivity, etc.[1–3] These interactions between constituent atoms, often quantified as bond strengths, can be extracted from crystalline materials using density-based[4], energy-based[5], and orbital-based methods. LOBSTER[6] is a software that relies on the orbital-based method to extract such bonding information by projecting the plane wave-based wave functions of modern density functional theory computations (DFT) onto a local atomic orbital basis. To garner a better understanding of how this bonding information relates to material properties on a larger scale, machine learning seems an obvious choice. However, for such data-driven studies, large quantities of data that are systematically generated, validated, and post-processed (feature engineering) in a form suitable for input in state-of-the-art ML models are often needed.[7] Here, we first present a workflow implemented in atomate2[8] that can generate such bonding-related data using the LOBSTER program with minimal user input and a post-processing tool, LobsterPy[9], which can summarize and engineer features that could be directly used as input for ML studies. Lastly, we demonstrate the utility of these newly generated features by building a simple machine-learned model to predict harmonic phonon properties using the bonding dataset[10] generated by us for 1500 materials. We find a clear correlation between the bonding information and the phonon property. T2 - STC 2024 CY - Braunschweig, Germany DA - 02.09.2024 KW - Bonding analysis KW - Machine learning KW - Feature engineering PY - 2024 AN - OPUS4-61130 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Naik, Aakash T1 - Enhancing material property predictions using quantum chemical bonding descriptors N2 - The properties of crystalline materials, such as elasticity, ionic conductivity, and thermal conductivity, are influenced by interactions between their constituent atoms.[1–3] These interactions, which are often quantified in terms of bond strength, can be extracted from crystalline materials using density-based[4], energy-based[5] and orbital-based methods. LOBSTER[6] is a software that relies on the orbital-based method to extract such bonding information by projecting the plane wave-based wave functions of modern density functional theory computations (DFT) onto a local atomic orbital basis. To garner a better understanding of how this bonding information relates to material properties on a larger scale, machine learning seems an obvious choice. However, for such data-driven studies, large quantities of data need to be systematically generated, validated, and post-processed (e.g., by feature engineering), as they can only then be used as input for state-of-the-art ML models. We have, therefore, previously developed workflows for high-throughput bonding analysis[7]. In this work, we use the results[8] from high-throughput LOBSTER calculations using our workflows to generate bonding-based features. To extract such features from the LOBSTER computations, we use our package LobsterPy.[9] The importance of these features is then tested by employing them in several state-of-the-art ML algorithms and architectures to predict the mechanical and vibrational properties of crystalline materials. We show that including these bonding-based features alongside typical composition and structure-based features helps enhance the model’s predictive accuracy. T2 - 18th German Conference on Cheminformatics CY - Bad Soden am Taunus, Germany DA - 03.11.2024 KW - Bonding analysis KW - Machine learning KW - Materials Descriptors PY - 2024 AN - OPUS4-62217 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - GEN A1 - Naik, Aakash A1 - Ertural, Christina A1 - Dhamrait, Nidal A1 - Benner, Philipp A1 - George, Janine T1 - Quantum-Chemical Bonding Database (Unprocessed data : Part 8) N2 - This data is associated with the manuscript "A Quantum-Chemical Bonding Database for Solid-State Materials." Refer to mpids.txt to see data related to which compounds are available in the tar file. (mp-xxx refer to Materials Project ID) KW - Bonding analysis KW - Automation KW - Materials Informatics KW - Computational Chemistry KW - Database PY - 2023 DO - https://doi.org/10.5281/zenodo.7852823 PB - Zenodo CY - Geneva AN - OPUS4-57448 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - GEN 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 (JSONS: Part 2) N2 - This database consists of bonding data computed using Lobster for 1520 solid-state compounds consisting of insulators and semiconductors. The files are named as per ID numbers in the materials project database. Here we provide the larger computational data JSON files for the rest of the 820 compounds. This file consists of all important LOBSTER computation output files data stored as a dictionary. KW - Bonding analysis KW - Automation KW - Materials Informatics KW - Computational Chemistry KW - Database PY - 2023 DO - https://doi.org/10.5281/zenodo.7821727 PB - Zenodo CY - Geneva AN - OPUS4-57440 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - GEN 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 (JSONS: Part 1) N2 - This database consists of bonding data computed using Lobster for 1520 solid-state compounds consisting of insulators and semiconductors. It consists of two kinds of json files. Smaller lightweight JSONS consists of summarized bonding information for each of the compounds. The files are named as per ID numbers in the materials project database. Here we provide also the larger computational data json files for 700 compounds. This files consists of all important LOBSTER computation output files data stored as dictionary. KW - Bonding analysis KW - Automation KW - Materials Informatics KW - Computational Chemistry KW - Database PY - 2023 DO - https://doi.org/10.5281/zenodo.7794811 PB - Zenodo CY - Geneva AN - OPUS4-57439 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -