A design principle is proposed for advanced metal nitride HEDMs: prioritizing high nitrogen-to-metal ratios, light metal elements, and structures wherein nitrogen atoms are spatially separated by the metal matrix, which minimizes N-N bonds and favors dominant M-N bonding.
Abstract
Metal nitrides exhibit broad prospects as high-energy-density materials (HEDMs) due to their exceptional energy release characteristics and environmentally friendly decomposition products. However, a fundamental challenge for this class of HEDMs lies in the trade-off between high energy density and high stability. Here, we employed a crystal structure search method to obtain numerous metal nitride configurations with different elements and stoichiometries and characterized their properties using first-principles calculations and
ab initio
molecular dynamics (AIMD) simulations. Based on the dataset, we developed descriptors related to the elemental and structural properties and trained regression models to predict the energy density of the metal nitrides. Additionally, multiple classifier models were trained to assess their stability. Through these machine learning models, we analyzed the features affecting the energy density and stability of metal nitrides and identified three key descriptors: the average distance between each nitrogen atom and its nearest neighbor (DNN), the stoichiometric ratio (N:M), and the average number of N-N bonds per nitrogen atom (aveNNBonds). Based on these insights, we propose a design principle for advanced metal nitride HEDMs: prioritizing high nitrogen-to-metal ratios, light metal elements, and structures wherein nitrogen atoms are spatially separated by the metal matrix, which minimizes N-N bonds and favors dominant M-N bonding. Moreover, our analysis revealed a class of metal nitrides with high nitrogen content that combines considerable stability and high energy density, demonstrating the power of machine learning in material HEDM design.
An explainable machine-learning framework was developed for dielectric constant prediction using 52,168 crystalline materials extracted from the Joint Automated Repository for Various Integrated Simulations (JARVIS-DFT) database, demonstrating the complementary roles of electronic structure and elemental chemistry.
D. Pundhir, Ashok Kumar· Applied Physics A· 0 citations
An adaptation of the Δ-ML strategy for quantum property prediction of transition metal complexes is presented, which consistently achieves higher accuracy in the prediction of high-fidelity targets, while demonstrating improved data efficiency and out-of-domain transferability.
Hannes Kneiding, David Balcells· Chemistry· 0 citations
This study combines high-throughput DFT calculations with machine learning techniques to uncover the key descriptors governing the nitrogen reduction reaction (NRR) in intermetallic compounds (IMCs). A dataset of 47 bimetallic IMCs was constructed, and the adsorption energies of key intermediates (N2, N2H, and NH3) were systematically evaluated across all accessible surface sites, yielding approximately 1,200 data points. By incorporating intrinsic material properties along with electronic descriptors including s-, p- and d-band centers and fillings, as well as Bader charges of atoms neighboring the adsorbate, predictive ML models were developed with mean absolute errors of 0.26 eV for N2, 0.39 eV for N2H, and 0.17 eV for NH3 adsorption. Importantly, accurate predictions are obtained with only 20 key features, enabling the use of simple and computationally efficient ML models. SHAP analysis indicates that p- and s-band characteristics play a more prominent role in determining adsorption strength than the traditionally used d-band center, particularly for N2 and N2H intermediates. Beyond their established importance in systems containing p-block elements or nearly filled d-band metals, s- and p-orbitals are also found to contribute significantly to transition-metal alloys activity such as Fe-Co, driven by adsorption-induced sp-d hybridization. By challenging the d-band-centric paradigm and identifying s- and p-band descriptors as critical yet overlooked contributors, this work redefines the electronic descriptor space for intermetallic NRR catalysts and lays the groundwork for DFT-ML-guided discovery of non-noble materials for sustainable ammonia synthesis.
Machine learning has become an effective tool for accelerating materials discovery by predicting material properties with far lower computational cost than exhaustive first-principles calculations. However, its application to dopant engineering in two-dimensional (2D) oxide semiconductors remains relatively unexplored. In this work, we combine supervised machine learning with density functional theory-derived data from the Materials Project database to predict the electronic, thermodynamic, transport, and optical properties of undoped and doped 2D tin monoxide (SnO). Several supervised regression algorithms are evaluated for predicting the band gap, formation energy, carrier mobility, electrical conductivity, and optical absorption coefficient. Among the models considered, gradient boosting regression provides the highest predictive accuracy and consistently reproduces the complex structure–property relationships of both undoped and doped systems. Feature-importance analysis reveals that electronic band descriptors, particularly band width, followed by band asymmetry and electronic anisotropy, are the primary factors governing band-gap prediction, while structural descriptors provide complementary contributions. The predictions indicate that monolayer SnO has a wider band gap, slightly higher formation energy, and higher carrier mobility than bulk SnO due to quantum confinement. Mg and Zn substitution allow systematic tuning of the material properties over a moderate concentration range. The band gap changes only slightly with doping, while Mg incorporation is thermodynamically more favorable than Zn, whose stability decreases with increasing concentration. Dopant-induced impurity scattering reduces carrier mobility and electrical conductivity, whereas optical absorption is enhanced in both Mg- and Zn-doped systems. These results demonstrate that machine learning can efficiently identify promising dopant configurations while providing reliable predictions of dopant-dependent material properties. The proposed framework offers a practical approach for the computational design of doped 2D oxide semiconductors for future optoelectronic and sensing applications.
Optimizing catalysis requires the efficient exploration of immense chemical spaces, particularly for high-entropy (multielement) systems where properties depend on complex variables like geometry, composition, and site-specific interactions. In this work, we demonstrate a global active learning framework to map these landscapes efficiently. By coupling genetic algorithms with deep neural networks trained on density functional theory data, our approach learns the potential energy surface while optimizing chemical structures simultaneously, bypassing costly density functional theory relaxations. We apply this framework to predict H2, N2, and NH3 adsorption energies on 10–50 atom clusters composed of Ag, Au, Cu, Ni, Pd, and Pt. The model achieves a mean absolute error of less than 0.10 eV against density functional theory validation. Results identify regions with moderate H2 physisorption (−0.1 to −0.5 eV) and other regions with strong chemisorption (−1.0 to −2.0 eV). Physisorption mainly consists of adsorption on Ag, Au, Ni, and Cu, while chemisorption involves Pd and Pt sites. High-entropy environments can provide a diverse distribution of local chemical conditions. This site variance is critical for multistep reactions where intermediate steps possess conflicting optimal binding energies that cannot be simultaneously satisfied by low-entropy surfaces, thereby offering entropy as a tunable parameter for catalyst design. This framework provides a scalable and resource-efficient strategy for high-throughput materials discovery in applications such as hydrogen storage and ammonia synthesis.
Johnathan von der Heyde, Walter Malone, A. Kara· Journal of Physical Chemistr...· 0 citations
Identification of the crystal structure of the cathodes of Li-ion batteries is important to improve energy storage technologies. This research has three goals: (1) to determine the important parameters to predict the crystal systems (monoclinic, orthorhombic, and triclinic); (2) to evaluate different machine learning algorithms to make the correct prediction; and (3) to give insights on how to optimize materials used in batteries. We have studied a Kaggle dataset comprising a number of physicochemical descriptors such as chemical formula, energy above the convex hull, band gap, number of atomic sites in the crystal, density, and volume. We evaluate and compare systematically the predictive performance of 10 machine learning algorithms, including Random Forest, Support Vector Machine, Logistic Regression, K-Nearest Neighbor, Decision Tree, Gradient Boosting, XGBoost, Naive Bayes, AdaBoost, and CatBoost. The final model with the best predictive performance resulted from the optimized stacking model that achieved an accuracy of 72.06% and an Receiver Operating Characteristic–Area Under the Curve (ROC–AUC) of 0.8438 after removing leaky features and applying advanced validation methods. These results are consistent with past research that reveals that ensemble learning methods can be used to extract intricate trends in materials information. Nevertheless, this study is based on one dataset with a rather small sample size, which can impact the broader applicability of the findings.
Received: 25 November 2025 | Revised: 17 April 2026 | Accepted: 24 June 2026
Conflicts of Interest
The authors declare that they have no conflicts of interest to this work.
Data Availability Statement
The data that support the findings of this study are openly available in Kaggle at https://www.kaggle.com/datasets/divyansh22/crystal-system-properties-for-liion-batteries/data. All
source code, model implementation, and experimental workfloware available from the GitHub repository at https://github.com/alokchauhan-collab/Crystal-Structure-Predictive-Modeling-of-Li-ion-Battery-Cathodes.
Author Contribution Statement
Mega Novita: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing – original draft, Visualization, Project administration. Alok Singh Chauhan: Conceptualization, Methodology, Software, Formal analysis, Writing – review & editing, Visualization, Supervision. Rizky Muliani Dwi Ujianti: Software, Investigation, Data curation, Visualization. Sigit Ristanto: Methodology, Validation, Writing – review & editing, Project administration. Bambang Agus Herlambang: Writing – review & editing. Kazuyoshi Ogasawara: Resources, Writing – review & editing. Chong Geng Ma: Resources. Mikhail Brik: Resources, Writing – review & editing, Supervision. Michal Piasecki: Resources, Writing – review & editing.
M. Novita, A. Chauhan, Rizky Muliani Dwi Ujianti et al.· Journal of Data Science and...· 0 citations
