Multi-Step Time Series Generator for Molecular Dynamics

Authors: Katsuhiro Endo, Katsufumi Tomobe, Kenji Yasuoka

AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 4. Experimental results We performed three experiments: harmonic oscillator with noise, water vibrational spectra, and polymer melts.
Researcher Affiliation Academia Katsuhiro Endo, Katsufumi Tomobe, Kenji Yasuoka Department of Mechanical Engineering, Keio University 3-14-1 Hiyoshi, Kohoku-ku, Yokohama Kanagawa, Japan 223-8522
Pseudocode No The paper describes the architecture and training process in text and diagrams but does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statements or links indicating that the source code for the methodology is openly available.
Open Datasets No The paper describes generating its own simulation data using MD simulations with specific software and force fields (e.g., CPMD code, NAMD 2.9, GROMACS package) but does not provide concrete access information (link, DOI, repository, or formal citation) for a publicly available or open dataset used for training.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology) for training, validation, and testing. It discusses generating time series for learning and comparison, but not formal splits.
Hardware Specification Yes Table 2 shows calculation performance of the MD simulation and our model with one process of the Intel Core i7-4930K.
Software Dependencies Yes For the ab initio MD simulations, we used the CPMD code (Hutter and Iannuzzi 2005)... The CPMD simulation was conducted... by the classical isothermal and isobaric classical MD simulation using the NAMD 2.9 software (Phillips et al. 2005)... The MD simulations were conducted using the Tra PPE-UA force field (Martin and Siepmann 1998) and the GROMACS package (Pronk et al. 2013)...
Experiment Setup No The paper describes the network architecture and some general structural parameters (e.g., Table 1 showing dimensions of x, Y, z; U-net based networks, multi-layer convolutional network) but does not provide specific hyperparameter values such as learning rate, batch size, or optimizer settings. It states, 'Other parameters of the networks are needed to be tuned for each dataset.'