Saved in:
Bibliographic Details
Main Authors: Williams, Jan P., Zahn, Olivia, Kutz, J. Nathan
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2301.12011
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910472139177984
author Williams, Jan P.
Zahn, Olivia
Kutz, J. Nathan
author_facet Williams, Jan P.
Zahn, Olivia
Kutz, J. Nathan
contents Sensing is a universal task in science and engineering. Downstream tasks from sensing include inferring full state estimates of a system (system identification), control decisions, and forecasting. These tasks are exceptionally challenging to achieve with limited sensors, noisy measurements, and corrupt or missing data. We propose a SHallow REcurrent Decoder (SHRED) neural network structure for sensing which incorporates (i) a recurrent neural network (LSTM) to learn a latent representation of the temporal dynamics of the sensors, and (ii) a shallow decoder that learns a mapping between this latent representation and the high-dimensional state space. By explicitly accounting for the time-history, or trajectory, of the sensor measurements, SHRED enables accurate reconstructions with far fewer sensors, outperforms existing techniques when more measurements are available, and is agnostic towards sensor placement. In addition, a compressed representation of the high-dimensional state is directly obtained from sensor measurements, which provides an on-the-fly compression for modeling physical and engineering systems. Forecasting is also achieved from the sensor time-series data alone, producing an efficient paradigm for predicting temporal evolution with an exceptionally limited number of sensors. In the example cases explored, including turbulent flows, complex spatio-temporal dynamics can be characterized with exceedingly limited sensors that can be randomly placed with minimal loss of performance.
format Preprint
id arxiv_https___arxiv_org_abs_2301_12011
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Sensing with shallow recurrent decoder networks
Williams, Jan P.
Zahn, Olivia
Kutz, J. Nathan
Dynamical Systems
Sensing is a universal task in science and engineering. Downstream tasks from sensing include inferring full state estimates of a system (system identification), control decisions, and forecasting. These tasks are exceptionally challenging to achieve with limited sensors, noisy measurements, and corrupt or missing data. We propose a SHallow REcurrent Decoder (SHRED) neural network structure for sensing which incorporates (i) a recurrent neural network (LSTM) to learn a latent representation of the temporal dynamics of the sensors, and (ii) a shallow decoder that learns a mapping between this latent representation and the high-dimensional state space. By explicitly accounting for the time-history, or trajectory, of the sensor measurements, SHRED enables accurate reconstructions with far fewer sensors, outperforms existing techniques when more measurements are available, and is agnostic towards sensor placement. In addition, a compressed representation of the high-dimensional state is directly obtained from sensor measurements, which provides an on-the-fly compression for modeling physical and engineering systems. Forecasting is also achieved from the sensor time-series data alone, producing an efficient paradigm for predicting temporal evolution with an exceptionally limited number of sensors. In the example cases explored, including turbulent flows, complex spatio-temporal dynamics can be characterized with exceedingly limited sensors that can be randomly placed with minimal loss of performance.
title Sensing with shallow recurrent decoder networks
topic Dynamical Systems
url https://arxiv.org/abs/2301.12011