.png){kind=icon}
返回
Automatic Feature Selection for Atom-Centered Neural Network Potentials Using a Gradient Boosting Decision Algorithm
.png){kind=icon}
PRE
AI
DOI：10.1021/acs.jctc.4c01176.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
LIQUID-METAL
FORCE-FIELD
APPROXIMATION
DYNAMICS
PERFORMANCE
SIMULATION
MODEL
期刊
IF:
5.5
论文数:
1.1W
被引数:
5.6W
机构
暂无机构信息
引用论文
Job tenure and quality of work life of people with psychiatric disabilities working in social enterprises在社会企业工作的精神病患者的工作任期和工作生活质量
PREAI
分享收藏Machine Learning a General-Purpose Interatomic Potential for Silicon机器学习硅的通用原子间潜力.png)
PHYSICAL REVIEW X
OAAI
PHYSICAL REVIEW XIF15.7
OAAI分享收藏Ab initiomolecular-dynamics simulation of the liquid-metal–amorphous-semiconductor transition in germanium 从头算 锗中液态-金属-非晶-半导体跃迁的分子动力学模拟
PREAI
分享收藏Using CBM as an Indicator of Decoding, Word Reading, and Comprehension: Do the Relations Change With Grade?使用CBM作为解码，单词阅读和理解的指标: 关系是否随年级而变化？
PREAI
分享收藏An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2用于原子材料模拟的人工神经网络潜力的实现: TiO2的性能
PREAI
分享收藏Atom-centered symmetry functions for constructing high-dimensional neural network potentials以原子为中心的对称函数构造高维神经网络势
PREAI
分享收藏DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamicsDeepmd-kit: 用于多体势能表示和分子动力学的深度学习软件包OAAI
OAAI分享收藏
查看更多内容