Zichen Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zichen Song has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Lei Li
Department of Materials Science and Engineering Southern University of Science and Technology Shenzhen China
5 shared publications Jiaqi Wang
Southern University of Science and Technology
3 shared publications- Akksay Singh
Department of Materials Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, People’s Republic of China
2 shared publications - Jian Han
Department of Materials Science and Engineering City University of Hong Kong Hong Kong SAR China
2 shared publications Bai Li
Department of Materials Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, People’s Republic of China
1 shared publicationBenrui Tang
College of Physical Science and Technology
1 shared publication
Latest Publications
- 15 October 2026
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 137 (16) , 168001
Thermodynamically Consistent Machine Learning Potentials for Constant-Potential Simulations
Simulating electrochemical interfaces under an applied voltage requires a grand-canonical treatment of electrons, yet standard machine-learning potentials (MLPs) are canonical or rely on electronic-property supervision. We introduce a thermodynamically consistent constant-potential MLP (TCCP-MLP) trained solely on energies and forces. The work function emerges as the exact derivative of a unified energy functional, capturing long-range electrostatics and charge transfer. We demonstrate TCCP-MLP by predicting voltage-dependent activation barriers and charge transfer for C-C coupling on the Cu (100) surface.
- 15 October 2026
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 137 (16) , 168001
Thermodynamically Consistent Machine Learning Potentials for Constant-Potential Simulations
Simulating electrochemical interfaces under an applied voltage requires a grand-canonical treatment of electrons, yet standard machine-learning potentials (MLPs) are canonical or rely on electronic-property supervision. We introduce a thermodynamically consistent constant-potential MLP (TCCP-MLP) trained solely on energies and forces. The work function emerges as the exact derivative of a unified energy functional, capturing long-range electrostatics and charge transfer. We demonstrate TCCP-MLP by predicting voltage-dependent activation barriers and charge transfer for C-C coupling on the Cu (100) surface.
- Top Cited PapersOpen Access
- 20 April 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 22 (9) , 4787-4801
qNEP: A Highly Efficient Neuroevolution Potential with Dynamic Charges for Large-Scale Atomistic Simulations
Although electrostatics can be incorporated into machine-learned interatomic potentials, existing approaches are computationally very demanding, limiting large-scale, long-time simulations of electrostatics-driven phenomena such as dielectric response, infrared activity, and field–matter coupling. Here, we extend the neuroevolution potential (NEP), a highly efficient machine-learned interatomic potential, to a charge-aware framework (qNEP) by introducing explicit, environment-dependent partial charges. Each ionic partial charge is represented by a neural network as a function of the local descriptor vector, analogous to the NEP site-energy model. This formulation enables the direct prediction of the Born effective charge tensor for each ion and, consequently, the polarization. As a result, dielectric properties, infrared spectra, and coupling to external electric fields can be evaluated within a unified framework. We derive consistent expressions for the forces and virials that explicitly account for the position dependence of the partial charges. The qNEP method has been implemented in the free-and-open-source GPUMD package with support for both Ewald summation and particle–particle particle–mesh treatments of electrostatics. We demonstrate the accuracy and efficiency of the qNEP approach through representative applications to water, Li7La3Zr2O12, BaTiO3, and a magnesium–water interface. These results show that qNEP enables accurate atomistic simulations with explicit long-range electrostatics, scalable to million-atom systems on nanosecond time scales using consumer-grade GPUs.
- 20 April 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 22 (9) , 4787-4801
Top Cited PapersOpen AccessqNEP: A Highly Efficient Neuroevolution Potential with Dynamic Charges for Large-Scale Atomistic Simulations
Although electrostatics can be incorporated into machine-learned interatomic potentials, existing approaches are computationally very demanding, limiting large-scale, long-time simulations of electrostatics-driven phenomena such as dielectric response, infrared activity, and field–matter coupling. Here, we extend the neuroevolution potential (NEP), a highly efficient machine-learned interatomic potential, to a charge-aware framework (qNEP) by introducing explicit, environment-dependent partial charges. Each ionic partial charge is represented by a neural network as a function of the local descriptor vector, analogous to the NEP site-energy model. This formulation enables the direct prediction of the Born effective charge tensor for each ion and, consequently, the polarization. As a result, dielectric properties, infrared spectra, and coupling to external electric fields can be evaluated within a unified framework. We derive consistent expressions for the forces and virials that explicitly account for the position dependence of the partial charges. The qNEP method has been implemented in the free-and-open-source GPUMD package with support for both Ewald summation and particle–particle particle–mesh treatments of electrostatics. We demonstrate the accuracy and efficiency of the qNEP approach through representative applications to water, Li7La3Zr2O12, BaTiO3, and a magnesium–water interface. These results show that qNEP enables accurate atomistic simulations with explicit long-range electrostatics, scalable to million-atom systems on nanosecond time scales using consumer-grade GPUs.
- 11 September 2025
- Published by Elsevier in Acta Materialia
- Vol. 301
Resolving vacancy clustering mechanisms in tungsten via machine-learning-potential-based simulations at experimental time scales
- 11 September 2025
- Published by Elsevier in Acta Materialia
- Vol. 301
Resolving vacancy clustering mechanisms in tungsten via machine-learning-potential-based simulations at experimental time scales
- 19 November 2024
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 20 (23) , 10564-10573
Automatic Feature Selection for Atom-Centered Neural Network Potentials Using a Gradient Boosting Decision Algorithm
Atom-centered neural network (ANN) potentials have shown high accuracy and computational efficiency in modeling atomic systems. A crucial step in developing reliable ANN potentials is the proper selection of atom-centered symmetry functions (ACSFs), also known as atomic features, to describe atomic environments. Inappropriate selection of ACSFs can lead to poor-quality ANN potentials. Here, we propose a gradient boosting decision tree (GBDT)-based framework for the automatic selection of optimal ACSFs. This framework takes uniformly distributed sets of ACSFs as input and evaluates their relative importance. The ACSFs with high average importance scores are selected and used to train an ANN potential. We applied this method to the Ge system, resulting in an ANN potential with root-mean-square errors (RMSE) of 10.2 meV/atom for energy and 84.8 meV/& Aring; for force predictions, utilizing only 18 ACSFs to achieve a balance between accuracy and computational efficiency. The framework is validated using the grid searching method, demonstrating that ACSFs selected with our framework are in the optimal region. Furthermore, we also compared our method with commonly used feature selection algorithms. The results show that our algorithm outperforms the others in terms of effectiveness and accuracy. This study highlights the significance of the ACSF parameter effect on the ANN performance and presents a promising method for automatic ACSF selection, facilitating the development of machine learning potentials.
- 19 November 2024
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 20 (23) , 10564-10573
Automatic Feature Selection for Atom-Centered Neural Network Potentials Using a Gradient Boosting Decision Algorithm
Atom-centered neural network (ANN) potentials have shown high accuracy and computational efficiency in modeling atomic systems. A crucial step in developing reliable ANN potentials is the proper selection of atom-centered symmetry functions (ACSFs), also known as atomic features, to describe atomic environments. Inappropriate selection of ACSFs can lead to poor-quality ANN potentials. Here, we propose a gradient boosting decision tree (GBDT)-based framework for the automatic selection of optimal ACSFs. This framework takes uniformly distributed sets of ACSFs as input and evaluates their relative importance. The ACSFs with high average importance scores are selected and used to train an ANN potential. We applied this method to the Ge system, resulting in an ANN potential with root-mean-square errors (RMSE) of 10.2 meV/atom for energy and 84.8 meV/& Aring; for force predictions, utilizing only 18 ACSFs to achieve a balance between accuracy and computational efficiency. The framework is validated using the grid searching method, demonstrating that ACSFs selected with our framework are in the optimal region. Furthermore, we also compared our method with commonly used feature selection algorithms. The results show that our algorithm outperforms the others in terms of effectiveness and accuracy. This study highlights the significance of the ACSF parameter effect on the ANN performance and presents a promising method for automatic ACSF selection, facilitating the development of machine learning potentials.
- 21 February 2024
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 20 (5) , 2088-2097
Charge-Optimized Electrostatic Interaction Atom-Centered Neural Network Algorithm
Machine-learning algorithms have been proposed to capture electrostatic interactions by using effective partial charges. These algorithms often rely on a pretrained model for partial charge prediction using density functional theory-calculated partial charges as references, which introduces complexity to the force field model. The accuracy of the trained model also depends on the reliability of charge partition methods, which can be dependent on the specific system and methodology employed. In this study, we propose an atom-centered neural network (ANN) algorithm that eliminates the need for reference charges. Our algorithm requires only a single NN model for each element to obtain both atomic energy and charges. These atomic charges are then employed to compute electrostatic energies using the Ewald summation algorithm. Subsequently, the force field model is trained on total energy and forces, with the inclusion of electrostatic energy. To evaluate the performance of our algorithm, we conducted tests on three benchmark systems, including a Ge slab with an O adatom system, a TiO2 crystalline system, and a Pd-O nanoparticle system. Our results demonstrate reasonably accurate predictions of partial charges and electrostatic interactions. This algorithm provides a self-consistent charge prediction strategy and possibilities for robust and reliable modeling of electrostatic interactions in machine-learning potentials.
- 21 February 2024
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 20 (5) , 2088-2097
Charge-Optimized Electrostatic Interaction Atom-Centered Neural Network Algorithm
Machine-learning algorithms have been proposed to capture electrostatic interactions by using effective partial charges. These algorithms often rely on a pretrained model for partial charge prediction using density functional theory-calculated partial charges as references, which introduces complexity to the force field model. The accuracy of the trained model also depends on the reliability of charge partition methods, which can be dependent on the specific system and methodology employed. In this study, we propose an atom-centered neural network (ANN) algorithm that eliminates the need for reference charges. Our algorithm requires only a single NN model for each element to obtain both atomic energy and charges. These atomic charges are then employed to compute electrostatic energies using the Ewald summation algorithm. Subsequently, the force field model is trained on total energy and forces, with the inclusion of electrostatic energy. To evaluate the performance of our algorithm, we conducted tests on three benchmark systems, including a Ge slab with an O adatom system, a TiO2 crystalline system, and a Pd-O nanoparticle system. Our results demonstrate reasonably accurate predictions of partial charges and electrostatic interactions. This algorithm provides a self-consistent charge prediction strategy and possibilities for robust and reliable modeling of electrostatic interactions in machine-learning potentials.