Burrill Daniel J, Liu Chang, Taylor Michael G, Cawkwell Marc J, Perez Danny, Batista Enrique R, Lubbers Nicholas, Yang Ping
Theoretical Division, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, United States.
Computer, Computational and Statistical Sciences Division, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, United States.
J Chem Theory Comput. 2025 Feb 11;21(3):1089-1097. doi: 10.1021/acs.jctc.4c00858. Epub 2025 Jan 28.
We present a hybrid semiempirical density functional tight-binding (DFTB) model with a machine learning neural network potential as a correction to the repulsive term. This hybrid model, termed machine learning tight-binding (MLTB), employs the standard self-consistent charge (SCC) DFTB formalism as a baseline, enhanced by the HIP-NN potential as an effective many-body correction for short-range pairwise repulsive interactions. The MLTB model demonstrates significantly improved transferability and extensibility compared to the SCC-DFTB and HIP-NN models. This work provides a practical computational framework for developing reliable SCC-DFTB models with additional many-body corrections that more closely approach the DFT level of accuracy. We illustrate this method with the development of an accurate model for the thorium-oxygen system, applied to the study of its nanocluster structures (ThO).
我们提出了一种混合半经验密度泛函紧束缚（DFTB）模型，该模型带有一个机器学习神经网络势，用于校正排斥项。这种混合模型，称为机器学习紧束缚（MLTB），采用标准的自洽电荷（SCC）DFTB形式作为基线，并通过HIP-NN势进行增强，作为对短程成对排斥相互作用的有效多体校正。与SCC-DFTB和HIP-NN模型相比，MLTB模型表现出显著提高的可迁移性和可扩展性。这项工作为开发具有额外多体校正的可靠SCC-DFTB模型提供了一个实用的计算框架，这些模型更接近密度泛函理论（DFT）的精度水平。我们通过开发钍-氧系统的精确模型来说明这种方法，并将其应用于研究其纳米团簇结构（ThO）。
