Žugec Ivan, Hadži Veljković Tin, Alducin Maite, Juaristi J Iñaki
Centro de Física de Materiales CFM/MPC, CSIC-UPV/EHU, Paseo Manuel de Lardizabal 5, Donostia-San Sebastián 20018, Spain.
Departamento de Polímetros y Materiales Avanzados: Física, Química y Tecnología, Facultad de Química (UPV/EHU), Apartado 1072, Donostia-San Sebastián 20080, Spain.
J Chem Inf Model. 2025 Aug 11;65(15):8033-8041. doi: 10.1021/acs.jcim.5c01180. Epub 2025 Jul 22.
Molecular dynamics (MD) simulations are vital for exploring complex systems in computational physics and chemistry. While machine learning methods dramatically reduce computational costs relative to ab initio methods, their accuracy in long-lasting simulations remains limited. Here we propose dynamic training (DT), a method designed to enhance accuracy of a model over extended MD simulations. Applying DT to an equivariant graph neural network (EGNN) on the challenging system of a hydrogen molecule interacting with a palladium cluster anchored to a graphene vacancy demonstrates a superior prediction accuracy compared to conventional approaches. Crucially, the DT architecture-independent design ensures its applicability across diverse machine learning potentials, making it a practical tool for advancing MD simulations.
分子动力学（MD）模拟对于在计算物理和化学中探索复杂系统至关重要。虽然机器学习方法相对于从头算方法大大降低了计算成本，但其在长时间模拟中的准确性仍然有限。在这里，我们提出了动态训练（DT），这是一种旨在提高模型在扩展MD模拟中的准确性的方法。将DT应用于一个具有挑战性的系统——氢分子与锚定在石墨烯空位上的钯簇相互作用，在一个等变图神经网络（EGNN）上的实验表明，与传统方法相比，它具有更高的预测准确性。至关重要的是，DT与架构无关的设计确保了它在各种机器学习势中的适用性，使其成为推进MD模拟的实用工具。
