AI Paper Atlas

Research map / Time series / Causal and generative time series

Multi-Step Time Series Generator for Molecular Dynamics

Katsuhiro Endo, Katsufumi Tomobe, Kenji Yasuoka

AAAI 2018 · Time series › Causal and generative time series · approach: State-space and latent dynamics forecasting · 27 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
evolve a dense low-dimensional latent variable z instead of the raw feature sequence (latent variable model) (ablation)MD-GAN · Harmonic oscillator with noise, 128 to 1024 stepsMSE of normalized spectra: 79 times better than naive modelImproved
use MD-GAN instead of C-RNN-GANtime series generator · Harmonic oscillator with noiseMSE of normalized spectra: 104 times betterImproved
use MD-GAN instead of GROMACS MD to get averaged MSD for 40 nspolymer melts MSD · Polymer meltscomputation time: 55.2 days -> 2.83 daysImproved
increase training data size (ablation)MD-GAN · Water vibrational spectralibration peak noiseImproved
use U-net based generator instead of deconvolution-only network (ablation)MD-GAN generator G_Y · MD time series generationaccuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy