NepTrain and NepTrainKit: Automated Active Learning and Visualization Toolkit for Neuroevolution Potentials

2025-06-02

AI Summary

To address the inefficiency and heavy manual reliance in training data construction for Neural Evolution Potential (NEP) modeling, this work proposes the first end-to-end automated workflow. The method integrates physics-informed constraints—specifically bond-length filtering—with GUI-driven active learning (e.g., farthest-point sampling), anomalous structure identification, and atomic configuration classification. Built upon the open-source Python library NepTrain and the cross-platform GUI tool NepTrainKit, the framework unifies MD trajectory preprocessing, non-physical structure detection, interactive visualization, and manual data curation. Validated on the CsPbI₃ system, it substantially improves both data curation efficiency and NEP model accuracy, enabling high-fidelity prediction of material properties. The core contributions are a physics-guided active learning paradigm and a standardized, interactive, and reproducible data construction framework for NEP development.

Technology Category

• Machine Learning: Active Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Web data integration and cleaning

Abstract

As a machine-learned potential, the neuroevolution potential (NEP) method features exceptional computational efficiency and has been successfully applied in materials science. Constructing high-quality training datasets is crucial for developing accurate NEP models. However, the preparation and screening of NEP training datasets remain a bottleneck for broader applications due to their time-consuming, labor-intensive, and resource-intensive nature. In this work, we have developed NepTrain and NepTrainKit, which are dedicated to initializing and managing training datasets to generate high-quality training sets while automating NEP model training. NepTrain is an open-source Python package that features a bond length filtering method to effectively identify and remove non-physical structures from molecular dynamics trajectories, thereby ensuring high-quality training datasets. NepTrainKit is a graphical user interface (GUI) software designed specifically for NEP training datasets, providing functionalities for data editing, visualization, and interactive exploration. It integrates key features such as outlier identification, farthest-point sampling, non-physical structure detection, and configuration type selection. The combination of these tools enables users to process datasets more efficiently and conveniently. Using $ m CsPbI_3$ as a case study, we demonstrate the complete workflow for training NEP models with NepTrain and further validate the models through materials property predictions. We believe this toolkit will greatly benefit researchers working with machine learning interatomic potentials.

Problem

• Automating high-quality training dataset preparation for NEP models
• Streamlining NEP model training with bond length filtering and visualization
• Reducing time and resource costs in neuroevolution potential applications

Innovation

• Automated active learning for NEP training
• Bond length filtering for dataset quality
• GUI for data editing and visualization