scholarly journals Estimating the state of a geophysical system with sparse observations: time delay methods to achieve accurate initial states for prediction

2017 ◽  
Vol 24 (1) ◽  
pp. 9-22 ◽  
Author(s):  
Zhe An ◽  
Daniel Rey ◽  
Jingxin Ye ◽  
Henry D. I. Abarbanel
Keyword(s):  
Time Delays ◽  
Time Series Data ◽  
Chaotic Behavior ◽  
Weather Prediction ◽  
Series Data ◽  
State Variables ◽  
Nonlinear Shallow Water Equations ◽  
Delayed Measurements ◽  
Lagrangian Drifter ◽  
Geophysical System

Abstract. The problem of forecasting the behavior of a complex dynamical system through analysis of observational time-series data becomes difficult when the system expresses chaotic behavior and the measurements are sparse, in both space and/or time. Despite the fact that this situation is quite typical across many fields, including numerical weather prediction, the issue of whether the available observations are "sufficient" for generating successful forecasts is still not well understood. An analysis by Whartenby et al. (2013) found that in the context of the nonlinear shallow water equations on a β plane, standard nudging techniques require observing approximately 70 % of the full set of state variables. Here we examine the same system using a method introduced by Rey et al. (2014a), which generalizes standard nudging methods to utilize time delayed measurements. We show that in certain circumstances, it provides a sizable reduction in the number of observations required to construct accurate estimates and high-quality predictions. In particular, we find that this estimate of 70 % can be reduced to about 33 % using time delays, and even further if Lagrangian drifter locations are also used as measurements.

scholarly journals Estimating the State of a Geophysical System with Sparse Observations: Time Delay Methods to Achieve Accurate Initial States for Prediction

2016 ◽  
Author(s):  
Zhe An ◽  
Daniel Rey ◽  
Jing Xin Ye ◽  
Henry D. I. Abarbanel
Keyword(s):  
Time Delays ◽  
Chaotic Behavior ◽  
Weather Prediction ◽  
Critical Threshold ◽  
State Variables ◽  
Nonlinear Shallow Water Equations ◽  
Assimilation Process ◽  
Transfer Of Information ◽  
Lagrangian Drifter ◽  
Geophysical System

Abstract. The data assimilation process, in which observational data is used to estimate the states and parameters of a dynamical model, becomes seriously impeded when the model expresses chaotic behavior and the number of measurements is below a critical threshold, Ls. Since this problem of insufficient measurements is typical across many fields, including numerical weather prediction, we analyze a method introduced in Rey et al. (2014a, b) to remedy this matter, in the context of the nonlinear shallow water equations on a β-plane. This approach generalizes standard nudging methods by utilizing time delayed measurements to augment the transfer of information from the data to the model. We will show it provides a sizable reduction in the number of observations required to construct accurate estimates and high-quality predictions. For instance, in Whartenby et al. (2013) we found that to achieve this goal, standard nudging requires observing approximately 70 % of the full set of state variables. Using time delays, this number can be reduced to about 33 %, and even further if Lagrangian drifter information is also incorporated.

Neural Network Techniques for Time Series Prediction: A Review

2019 ◽  
Vol 3 (3) ◽  
Author(s):  
Muhammad Faheem Mushtaq ◽  
Urooj Akram ◽  
Muhammad Aamir ◽  
Haseeb Ali ◽  
Muhammad Zulqarnain
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Time Series Data ◽  
Weather Prediction ◽  
Time Series Prediction ◽  
Series Data ◽  
Prediction Problem ◽  
Neural Network Models ◽  
Physical Time

It is important to predict a time series because many problems that are related to prediction such as health prediction problem, climate change prediction problem and weather prediction problem include a time component. To solve the time series prediction problem various techniques have been developed over many years to enhance the accuracy of forecasting. This paper presents a review of the prediction of physical time series applications using the neural network models. Neural Networks (NN) have appeared as an effective tool for forecasting of time series.  Moreover, to resolve the problems related to time series data, there is a need of network with single layer trainable weights that is Higher Order Neural Network (HONN) which can perform nonlinearity mapping of input-output. So, the developers are focusing on HONN that has been recently considered to develop the input representation spaces broadly. The HONN model has the ability of functional mapping which determined through some time series problems and it shows the more benefits as compared to conventional Artificial Neural Networks (ANN). The goal of this research is to present the reader awareness about HONN for physical time series prediction, to highlight some benefits and challenges using HONN.

scholarly journals Developing an Embedding, Koopman and Autoencoder Technologies-Based Multi-Omics Time Series Predictive Model (EKATP) for Systems Biology research

2021 ◽  
Vol 12 ◽  
Author(s):  
Suran Liu ◽  
Yujie You ◽  
Zhaoqi Tong ◽  
Le Zhang
Keyword(s):  
Time Series ◽  
Predictive Model ◽  
Time Series Data ◽  
Chaotic Behavior ◽  
Flow Behavior ◽  
Series Data ◽  
High Dimensional ◽  
Future State ◽  
Disease Occurrence ◽  
The Future

It is very important for systems biologists to predict the state of the multi-omics time series for disease occurrence and health detection. However, it is difficult to make the prediction due to the high-dimensional, nonlinear and noisy characteristics of the multi-omics time series data. For this reason, this study innovatively proposes an Embedding, Koopman and Autoencoder technologies-based multi-omics time series predictive model (EKATP) to predict the future state of a high-dimensional nonlinear multi-omics time series. We evaluate this EKATP by using a genomics time series with chaotic behavior, a proteomics time series with oscillating behavior and a metabolomics time series with flow behavior. The computational experiments demonstrate that our proposed EKATP can substantially improve the accuracy, robustness and generalizability to predict the future state of a time series for multi-omics data.

scholarly journals Soft Computing Research For Weather Prediction Using Multilayer Architecture

2019 ◽  
Vol 8 (6) ◽  
pp. 3779-3783
Keyword(s):  
Neural Network ◽  
Time Series Data ◽  
Weather Prediction ◽  
Series Data ◽  
Feed Forward Neural Network ◽  
Rainfall Prediction ◽  
Agriculture Sector ◽  
Precise Prediction ◽  
Multilayer Architecture ◽  
Artificial Neural Network Ann

Rainfall prediction is helpful for the agriculture sector. Early prediction of drought and torrent situations is achieved through time series data. For the precise prediction, Artificial Neural Network(ANN) technique is used. The rainy dataset is tested using Feed Forward Neural Network(FFNN). The performance of this model is evaluated using Mean Square Error(MSE) and Magnitude of Relative Error(MRE). Better performance achieved when compared with other data mining techniques.

scholarly journals Windowed Granger causal inference strategy improves discovery of gene regulatory networks

2018 ◽  
Vol 115 (9) ◽  
pp. 2252-2257 ◽  
Author(s):  
Justin D. Finkle ◽  
Jia J. Wu ◽  
Neda Bagheri
Keyword(s):  
Time Series ◽  
Network Structure ◽  
Time Delays ◽  
Regulatory Networks ◽  
Network Inference ◽  
Time Series Data ◽  
Series Data ◽  
Directed Network ◽  
Rapid Characterization

Accurate inference of regulatory networks from experimental data facilitates the rapid characterization and understanding of biological systems. High-throughput technologies can provide a wealth of time-series data to better interrogate the complex regulatory dynamics inherent to organisms, but many network inference strategies do not effectively use temporal information. We address this limitation by introducing Sliding Window Inference for Network Generation (SWING), a generalized framework that incorporates multivariate Granger causality to infer network structure from time-series data. SWING moves beyond existing Granger methods by generating windowed models that simultaneously evaluate multiple upstream regulators at several potential time delays. We demonstrate that SWING elucidates network structure with greater accuracy in both in silico and experimentally validated in vitro systems. We estimate the apparent time delays present in each system and demonstrate that SWING infers time-delayed, gene–gene interactions that are distinct from baseline methods. By providing a temporal framework to infer the underlying directed network topology, SWING generates testable hypotheses for gene–gene influences.

scholarly journals Learning Delays in Biological Regulatory Networks from Time Series Data

2017 ◽  
Vol 3 (2) ◽  
pp. 43
Author(s):  
Emna Ben Abdallah ◽  
Tony Ribeiro ◽  
Morgan Magnin ◽  
Olivier Roux ◽  
Katsumi Inoue
Keyword(s):  
Time Delays ◽  
Regulatory Networks ◽  
Time Series Data ◽  
Series Data ◽  
Learning Approach ◽  
Direct Integration ◽  
Biological Models ◽  
High Throughput Data ◽  
Biological Regulatory Networks ◽  
Manual Analysis

Models of Biological Regulatory Networks are generally based on prior knowledge, either derived from literature and/or the manual analysis of biological observations. With the development of high-throughput data, there is a growing need for methods that automatically generate admissible models. To have a better understanding of the dynamical phenomena at stake in the influences between biological components, it would be necessary to include delayed influences in the model. The main purpose of this work is to have a resulting network as consistent as possible with the observed datasets regarding the conflicts and the simultaneity between transitions. The originality of our work is threefold: (i) the identification the sign of the interactions, (ii) the direct integration of quantitative time delays in the learning approach and (iii) the identification of the qualitative discrete levels that lead to the systems dynamics.In this work the precision of our automatic approach is discussed by applying it on dynamical biological models coming from the DREAM4 Challenge datasets.

Measurement of Chaotic Behavior of Operator Stabilizing an Inverted Pendulum and Its Fuzzy Identification from Time Series Data

2001 ◽  
Vol 13 (1) ◽  
pp. 23-29 ◽  
Author(s):  
Yoshihiko Kawazoe ◽  
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Fuzzy Inference ◽  
Fuzzy Controller ◽  
Chaotic Behavior ◽  
Series Data ◽  
Experimental Time ◽  
Experimental Time Series ◽  
Simulated Time ◽  
Simulated Time Series

This paper investigates the identification of the chaotic characteristics of human operation with individual difference and the skill difference from the experimental time series data by utilizing fuzzy inference. It shows how to construct rules automatically for a fuzzy controller from experimental time series data of each trial of each operator to identify a controller from human-generated decision-making data. The characteristics of each operator trial were identified fairly well from experimental time series data by utilizing fuzzy reasoning. It was shown that the estimated maximum Lyapunov exponents of simulated time series data using an identified fuzzy controller were positive against embedding dimensions, which means a chaotic phenomenon. It was also recognized that the simulated human behavior have a large amount of disorder according to the result of estimated entropy from the simulated time, series data.

CHAOTIC DYNAMICS OF A NONLINEAR ELECTRONIC CONVERTER

2008 ◽  
Vol 18 (10) ◽  
pp. 2981-3000
Author(s):  
E. CAMPOS-CANTÓN ◽  
J. S. MURGUÍA ◽  
H. C. ROSU
Keyword(s):  
Time Series Data ◽  
Chaotic Behavior ◽  
Series Data ◽  
Chaotic Oscillator ◽  
Quantitative Results ◽  
Wavelet Transform Analysis ◽  
Experimental Values ◽  
The Mathematical Model ◽  
Nonlinear Converter ◽  
Good Agreement

The nonlinear electronic converter used by Rulkov and collaborators [Rulkov et al., 2001], which is the core of their chaotic oscillator, is modeled and simulated numerically by means of an appropriate direct relationship between the experimental values of the electronic components of the system and the mathematical model. This relationship allows us to analyze the chaotic behavior of the model in terms of a particular bifurcation parameter k. Varying the parameter k, quantitative results of the dynamics of the numerical system are presented, which are found to be in good agreement with the experimental measurements that we performed as well. Moreover, we show that this nonlinear converter belongs to a class of 3-D systems that can be mapped to the unfolded Chua's circuit. We also report a wavelet transform analysis of the experimental and numerical chaotic time series data of this chaotic system. The wavelet analysis provides us with information on such systems in terms of the concentration of energy which is the standard electromagnetic interpretation of the L2 norm of a given signal.

Chaotic Characteristics of Workface Gas Emission Time-Series Data

2013 ◽  
Vol 340 ◽  
pp. 456-460 ◽  
Author(s):  
Mei Ying Qiao ◽  
Jian Yi Lan
Keyword(s):  
Time Series ◽  
Time Series Data ◽  
Chaotic Behavior ◽  
Chaotic Time Series ◽  
Point Of View ◽  
Series Data ◽  
Embedding Dimension ◽  
Minimum Entropy ◽  
Gas Emission ◽  
Emission Time

The chaotic time series phase space reconstruction theory based in this paper. First, the appropriate embedding dimension and delay time are selected by minimum entropy rate. Followed the chaotic behavior are analyzed by the use of the Poincare section map and Power spectrum of time series from the qualitative point of view. Based on NLSR LLE the quantitative study of the chaotic time series characteristics indicators is proposed. Finally, the gas emission workface of Hebi 10th Mine Coal is studied. The several analytical results of the above methods show that: the gas emission time-series data of this workface has chaotic characteristics.

scholarly journals Evaluation of classification and forecasting methods on time series gene expression data

PLoS ONE ◽  
2020 ◽  
Vol 15 (11) ◽  
pp. e0241686
Author(s):  
Nafis Irtiza Tripto ◽  
Mohimenul Kabir ◽  
Md. Shamsuzzoha Bayzid ◽  
Atif Rahman
Keyword(s):  
Gene Expression ◽  
Time Series ◽  
Deep Learning ◽  
Gene Expression Data ◽  
Time Series Data ◽  
Weather Prediction ◽  
Supervised Machine Learning ◽  
Series Data ◽  
Expression Data ◽  
Time Series Gene Expression

Time series gene expression data is widely used to study different dynamic biological processes. Although gene expression datasets share many of the characteristics of time series data from other domains, most of the analyses in this field do not fully leverage the time-ordered nature of the data and focus on clustering the genes based on their expression values. Other domains, such as financial stock and weather prediction, utilize time series data for forecasting purposes. Moreover, many studies have been conducted to classify generic time series data based on trend, seasonality, and other patterns. Therefore, an assessment of these approaches on gene expression data would be of great interest to evaluate their adequacy in this domain. Here, we perform a comprehensive evaluation of different traditional unsupervised and supervised machine learning approaches as well as deep learning based techniques for time series gene expression classification and forecasting on five real datasets. In addition, we propose deep learning based methods for both classification and forecasting, and compare their performances with the state-of-the-art methods. We find that deep learning based methods generally outperform traditional approaches for time series classification. Experiments also suggest that supervised classification on gene expression is more effective than clustering when labels are available. In time series gene expression forecasting, we observe that an autoregressive statistical approach has the best performance for short term forecasting, whereas deep learning based methods are better suited for long term forecasting.

Sign in / Sign up

Export Citation Format

Share Document