🤖 AI Summary
Conventional high-dimensional analysis methods struggle to simultaneously capture the coupling between structure and dynamics in complex many-body systems. This work proposes the Time Derivative (TiDe) space framework, which constructs higher-order time derivatives directly from temporal observational data as intrinsic dimensions, enabling joint unsupervised learning of structure and dynamics without dimensionality reduction. By naturally embedding physical information into high-dimensional representations, TiDe achieves both interpretability and computational robustness. Experiments on molecular dynamics simulations and experimental trajectory data demonstrate that TiDe efficiently uncovers key dynamical patterns in complex systems, significantly outperforming existing approaches.
📝 Abstract
Understanding the physics of many-body complex dynamical systems is typically non-trivial. High-dimensional analysis approaches are often deemed necessary to prevent losing important information. Typically, these use order parameters or descriptors capturing information related to, e.g., relative positions, symmetries, etc., of the units in the studied system. However, in many cases, gaining information related to the relative positions (or velocities) of the constitutive units alone may be insufficient, and to reach a more complete physical knowledge, one should ideally learn and correlate with each other both structure and dynamics. Here we demonstrate how to efficiently achieve such a goal by building and navigating high-dimensional Time-Derivatives (TiDe) space. A TiDe space can be easily generated for virtually any type of system/phenomenon under study from the time-series data collected along its observation over time. Each TiDe's dimension corresponds to a growing-order time-derivative of the extracted data, thus containing information related to different types of physical phenomena/events that can be easily extracted via unsupervised approaches. We demonstrate how, by definition, TiDes can be directly analyzed without a need for prior dimensionality reduction, providing results that are intrinsically intuitive to interpret. We show the potential of the method by analyzing two prototypical example datasets extracted from molecular dynamics simulations or experimental tracking of different complex dynamical systems. Our results demonstrate how efficiently one can navigate and learn in such information-rich TiDe spaces, which provide robust general frameworks for data analysis and for studying complex dynamical systems from the data collected along their observation over time.