Neural network potentials (NNPs) are crucial for accelerating computational materials science by surrogating density functional theory (DFT) calculations. Improving their accuracy is possible through pre-training and fine-tuning, where an NNP model is first pre-trained on a large-scale dataset and then fine-tuned on a smaller target dataset. However, this approach is computationally expensive, mainly due to the cost of DFT-based dataset labeling and load imbalances during large-scale pre-training. To address this, we propose LaMM, a semi-supervised pre-training method incorporating improved denoising self-supervised learning and a load-balancing algorithm for efficient multi-node training. We demonstrate that our approach effectively leverages a large-scale dataset of $\sim$300 million semi-labeled samples to train a single NNP model, resulting in improved fine-tuning performance in terms of both speed and accuracy.

The discovery and optimization of high-energy materials (HEMs) are constrained by the prohibitive computational expense and prolonged development cycles inherent in conventional approaches. In this work, we develop a general neural network potential (NNP) that efficiently predicts the structural, mechanical, and decomposition properties of HEMs composed of C, H, N, and O. Our framework leverages pre-trained NNP models, fine-tuned using transfer learning on energy and force data derived from density functional theory (DFT) calculations. This strategy enables rapid adaptation across 20 different HEM systems while maintaining DFT-level accuracy, significantly reducing computational costs. A key aspect of this work is the ability of NNP model to capture the chemical activity space of HEMs, accurately describe the key atomic interactions and reaction mechanisms during thermal decomposition. The general NNP model has been applied in molecular dynamics (MD) simulations and validated with experimental data for various HEM structures. Results show that the NNP model accurately predicts the structural, mechanical, and decomposition properties of HEMs by effectively describing their chemical activity space. Compared to traditional force fields, it offers superior DFT-level accuracy and generalization across both microscopic and macroscopic properties, reducing the computational and experimental costs. This work provides an efficient strategy for the design and development of HEMs and proposes a promising framework for integrating DFT, machine learning, and experimental methods in materials research. (To facilitate further research and practical applications, we open-source our NNP model on GitHub: https://github.com/MingjieWen/General-NNP-model-for-C-H-N-O-Energetic-Materials.)

First-principles calculations based on Density Functional Theory (DFT) have been widely utilized as a powerful tool for understanding electronic structures and material properties [1-3]. Although DFT calculations can accurately predict energies and forces acting on atoms, they are often hindered by high computational costs. This limitation can become a significant bottleneck, particularly for large-scale systems or long-time simulations. To address this issue, Neural Network Potentials (NNPs) have emerged as a promising alternative to accelerate DFT calculations [4-10]. NNPs learn the relationship between atomic configurations and energies from data obtained through DFT calculations, enabling significant reduction in computational cost while maintaining accuracy comparable to DFT calculations. In particular, NNPs based on the Graph Neural Network (GNN) are well-suited for constructing accurate potential models, as they can effectively capture the local atomic environments [6, 11-13]. However, most conventional NNPs do not account for spin degrees of freedom, limiting their application to material systems where spin states play a critical role in determining properties, such as transition metal oxides (TMOs). TMOs are known to exhibit diverse magnetic properties due to the presence of transition metal ions with partially filled d-orbitals, and incorporating spin degrees of freedom is crucial for understanding their properties [14].