arrow
返回

Deeptime: a Python library for machine learning dynamical models from time series data

delete2021-12-10
delete61
delete
OA
AI
M
Moritz Hoffmann
M
Martin K. Scherer
T
Tim Hempel
A
Andreas Mardt
B
Brian M. de Silva
B
Brooke E. Husic
S
Stefan Klus
H
Hao Wu
N
Nathan Kutz
S
Steven L. Brunton
F
Frank Noé *
DOI:10.1088/2632-2153/ac3de0delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Generation and analysis of time-series data is relevant to many quantitative fields ranging from economics to fluid mechanics. In the physical sciences, structures such as metastable and coherent sets, slow relaxation processes, collective variables, dominant transition pathways or manifolds and channels of probability flow can be of great importance for understanding and characterizing the kinetic, thermodynamic and mechanistic properties of the system. Deeptime is a general purpose Python library offering various tools to estimate dynamical models based on time-series data including conventional linear learning methods, such as Markov state models (MSMs), Hidden Markov Models and Koopman models, as well as kernel and deep learning approaches such as VAMPnets and deep MSMs. The library is largely compatible with scikit-learn, having a range of Estimator classes for these different models, but in contrast to scikit-learn also provides deep Model classes, e.g. in the case of an MSM, which provide a multitude of analysis methods to compute interesting thermodynamic, kinetic and dynamical quantities, such as free energies, relaxation times and transition paths. The library is designed for ease of use but also easily maintainable and extensible code. In this paper we introduce the main features and structure of the deeptime software. Deeptime can be found under https://deeptime-ml.github.io/.
Keyword:
machine-learning
time-series analysis
transfer operators
metastable and coherent sets
Markov state models
coarse graining
system identification

期刊

M
Machine Learning-Science and Technology
IF:
4.6
论文数:
1.1K
被引数:
3.4K

机构

P
Princeton University
学者数:
2.1W
论文数: 2.3W
被引数: 5.1W
U
University of Washington
学者数:
8.0W
论文数: 7.0W
被引数: 12.5W
F
Free University of Berlin
学者数:
3.8W
论文数: 3.2W
被引数: 51
T
tongji university
学者数:
7.9W
论文数: 6.0W
被引数: 98
U
University of Surrey
学者数:
1.2W
论文数: 1.3W
被引数: 22
学者 查看更多机构
引用论文

引用论文

Variation of seawater 87Sr/86Sr throughout Phanerozoic time
err1982-01-01
err0
PREAI
errW. H. Burke; R. E. Denison; E. A. Hetherington; R. B. Koepnick; H. F. Nelson; J. B. Otto
err分享
err收藏
Inventory of Potential Reconstructive Needs in the Patient with Burns
err1989-11-01
err0
PREAI
errJ. A. Brou; M. C. Robson; R. L. McCauley; D. N. Herndon; L. G. Phillips; M. Ortega; E. B. Evans; M. I. Alvaredo
err分享
err收藏
Chaos as an intermittently forced linear system
err2017-05-30
err401
errOAAI
errBrunton, Steven L.; Brunton, Bingni W.; Proctor, Joshua L.; Kaiser, Eurika; Kutz, J. Nathan
err分享
err收藏
err分享
err收藏
学者 查看更多内容