scholarly journals Dynamics-based data science in biology

2021 ◽  
Author(s):  
Jifan Shi ◽  
Kazuyuki Aihara ◽  
Luonan Chen
Keyword(s):  
Time Series ◽  
Data Science ◽  
Tipping Points ◽  
Biological Processes ◽  
Data Dynamics

With the increasingly accumulated bio-data, dynamics-based data-science has been progressing as an efficient way to reveal mechanisms of dynamical biological processes. We review three applications on detecting the tipping-points of diseases, quantifying cell's potency, and predicting time-series, to show the importance of dynamics-based data-science.

The Data Science of COVID-19 Spread: Some Troubling Current and Future Trends

2020 ◽  
Vol 26 (3) ◽  
Author(s):  
Rex W. Douglass ◽  
Thomas Leo Scherer ◽  
Erik Gartzke
Keyword(s):  
Time Series ◽  
Cross Section ◽  
Observational Studies ◽  
Data Science ◽  
Future Trends ◽  
Methodological Issues

AbstractOne of the main ways we try to understand the COVID-19 pandemic is through time series cross section counts of cases and deaths. Observational studies based on these kinds of data have concrete and well known methodological issues that suggest significant caution for both consumers and produces of COVID-19 knowledge. We briefly enumerate some of these issues in the areas of measurement, inference, and interpretation.

scholarly journals Evaluating the performance of multivariate indicators of resilience loss

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Els Weinans ◽  
Rick Quax ◽  
Egbert H. van Nes ◽  
Ingrid A. van de Leemput
Keyword(s):  
Time Series ◽  
Complex Systems ◽  
Multivariate Time Series ◽  
Tipping Points ◽  
Physical And Mental Health ◽  
One Dimensional ◽  
Slowing Down ◽  
The Past ◽  
Technological Developments ◽  
Resilience Indicators

AbstractVarious complex systems, such as the climate, ecosystems, and physical and mental health can show large shifts in response to small changes in their environment. These ‘tipping points’ are notoriously hard to predict based on trends. However, in the past 20 years several indicators pointing to a loss of resilience have been developed. These indicators use fluctuations in time series to detect critical slowing down preceding a tipping point. Most of the existing indicators are based on models of one-dimensional systems. However, complex systems generally consist of multiple interacting entities. Moreover, because of technological developments and wearables, multivariate time series are becoming increasingly available in different fields of science. In order to apply the framework of resilience indicators to multivariate time series, various extensions have been proposed. Not all multivariate indicators have been tested for the same types of systems and therefore a systematic comparison between the methods is lacking. Here, we evaluate the performance of the different multivariate indicators of resilience loss in different scenarios. We show that there is not one method outperforming the others. Instead, which method is best to use depends on the type of scenario the system is subject to. We propose a set of guidelines to help future users choose which multivariate indicator of resilience is best to use for their particular system.

TIME SERIES MODELLING OF EPIDEMICS: LEADING INDICATORS, CONTROL GROUPS AND POLICY ASSESSMENT

2021 ◽  
Vol 257 ◽  
pp. 83-100
Author(s):  
Andrew Harvey
Keyword(s):  
Time Series ◽  
Data Science ◽  
Leading Indicators ◽  
Control Groups ◽  
Balanced Growth ◽  
Time Series Modelling ◽  
Key Variables ◽  
The Uk ◽  
The Relationship

This article shows how new time series models can be used to track the progress of an epidemic, forecast key variables and evaluate the effects of policies. The univariate framework of Harvey and Kattuman (2020, Harvard Data Science Review, Special Issue 1—COVID-19, https://hdsr.mitpress.mit.edu/pub/ozgjx0yn) is extended to model the relationship between two or more series and the role of common trends is discussed. Data on daily deaths from COVID-19 in Italy and the UK provides an example of leading indicators when there is a balanced growth. When growth is not balanced, the model can be extended by including a non-stationary component in one of the series. The viability of this model is investigated by examining the relationship between new cases and deaths in the Florida second wave of summer 2020. The balanced growth framework is then used as the basis for policy evaluation by showing how some variables can serve as control groups for a target variable. This approach is used to investigate the consequences of Sweden’s soft lockdown coronavirus policy in the spring of 2020.

Preliminary results of the first assessment of 20 years of dust activity in the Patagonia desert (South America) with aerosol products from the MODIS sensors

2021 ◽  
Author(s):  
Santiago Gassó ◽  
Pawan Gupta ◽  
Paul Ginoux ◽  
Robert Levy
Keyword(s):  
Time Series ◽  
South America ◽  
Volcanic Eruptions ◽  
Transport Processes ◽  
Dust Storms ◽  
Biological Processes ◽  
Aerosol Transport ◽  
Deep Blue ◽  
Fire Activity ◽  
Analysis Of Time Series

<p>Aerosol transport processes in the Southern Hemisphere (SH) have been the center of renewed attention in the last two decades because of a number of major geophysical events such as volcanic eruptions (Chile and Argentina), biomass burning (Australia and Chile) and dust storms (Australia and Argentina).<br><br>While volcanic and fire activity in the SH have been the focus of several studies, there is a dearth of satellite assessments of dust activity. The lack of such analysis impairs the understanding of biological processes in the Southern Ocean and of the provenance of dust found in snow at the surface of East Antarctica.<br><br>This presentation will show an analysis of time series of Aerosol Optical Depths over the Patagonia desert in South America. Data from two aerosol algorithms (Dark Target and Deep Blue) will be jointly analyzed to establish a timeline of dust activity in the region. Also, dust proxies from both algorithms will be compared with ground-based observations of visibility at different airports in the area. Once an understanding of frequency and time evolution of the dust activity is achieved, first estimations of ocean-going dust fluxes will be derived.</p>

Phase Transitions and Resilience in Physical and Psychological Health

2020 ◽  
pp. 59-72
Author(s):  
Marcel G. M. Olde Rikkert ◽  
Noemi Schuurman ◽  
René J. F. Melis
Keyword(s):  
Time Series ◽  
Psychological Health ◽  
Wearable Devices ◽  
Complexity Science ◽  
Detailed Knowledge ◽  
Tipping Points ◽  
Mental Processes ◽  
Slowing Down ◽  
Physical And Psychological Health ◽  
Aging Societies

Complexity science methods offer new opportunities for prognosis and treatment in healthcare and clinical psychology because of the increasing need for integration of the detailed knowledge of physiological and psychological subsystems and the increasing prevalence of multiple disease conditions in our aging societies. This chapter explains how the frequently occurring acute transitions and related tipping points in physical and mental processes in these populations can be monitored with time series and dynamical indicators of resilience. The authors introduce slowing down of recovery, increase in variance and autocorrelation, and increasing cross-correlation between subsystem time series as valid predictors of the proximity of tipping points in diseases such as depression, heart failure and syncope. Using wearable devices, together with these complex systems analyses, yields new methods of forecasting and may improve resilience of individual persons and their mental or physical (organ) subsystems

Time Series Forecasting in Retail Sales Using LSTM and Prophet

2021 ◽  
pp. 241-262
Author(s):  
Clony Junior ◽  
Pedro Gusmão ◽  
José Moreira ◽  
Ana Maria M. Tome
Keyword(s):  
Time Series ◽  
Data Science ◽  
Short Term Memory ◽  
Special Kind ◽  
Time Series Forecasting ◽  
Short Term ◽  
Term Memory ◽  
Use Of Time

Data science highlights fields of study and research such as time series, which, although widely explored in the past, gain new perspectives in the context of this discipline. This chapter presents two approaches to time series forecasting, long short-term memory (LSTM), a special kind of recurrent neural network (RNN), and Prophet, an open-source library developed by Facebook for time series forecasting. With a focus on developing forecasting processes by data mining or machine learning experts, LSTM uses gating mechanisms to deal with long-term dependencies, reducing the short-term memory effect inherent to the traditional RNN. On the other hand, Prophet encapsulates statistical and computational complexity to allow broad use of time series forecasting, prioritizing the expert's business knowledge through exploration and experimentation. Both approaches were applied to a retail time series. This case study comprises daily and half-hourly forecasts, and the performance of both methods was measured using the standard metrics.

Recurrence Plot based entropies and their ability to detect transitions

2020 ◽  
Author(s):  
K. Hauke Kraemer ◽  
Norbert Marwan ◽  
Karoline Wiesner ◽  
Jürgen Kurths
Keyword(s):  
Time Series ◽  
Shannon Entropy ◽  
Recurrence Plot ◽  
Climate Dynamics ◽  
Value Distribution ◽  
Tipping Points ◽  
Recurrence Plots ◽  
The Past ◽  
Entropy Measures ◽  
Regime Transitions

<p>Many dynamical processes in Earth Sciences are the product of many interacting components and have often limited predictability, not least because they can exhibit regime transitions (e.g. tipping points).To quantify complexity, entropy measures such as the Shannon entropy of the value distribution are widely used. Amongst other more sophisticated ideas, a number of entropy measures based on recurrence plots have been suggested. Because different structures, e.g. diagonal lines, of the recurrence plot are used for the estimation of probabilities, these entropy measures represent different aspects of the analyzed system and, thus, behave differently. In the past, this fact has led to difficulties in interpreting and understanding those measures. We review the definitions, the motivation and interpretation of these entropy measures, compare their differences and discuss some of the pitfalls when using them.</p><p>Finally, we illustrate their potential in an application on paleoclimate time series. Using the presented entropy measures, changes and transitions in the climate dynamics in the past can be identified and interpreted.</p>

scholarly journals Change sign detection with differential MDL change statistics and its applications to COVID-19 pandemic analysis

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Kenji Yamanishi ◽  
Linchuan Xu ◽  
Ryo Yuki ◽  
Shintaro Fukushima ◽  
Chuan-hao Lin
Keyword(s):  
Time Series ◽  
Early Warning ◽  
Data Science ◽  
Minimum Description Length ◽  
Length Change ◽  
Warning Signals ◽  
Early Warning Signals ◽  
New Information ◽  
Long Time ◽  
Synthetic Datasets

AbstractWe are concerned with the issue of detecting changes and their signs from a data stream. For example, when given time series of COVID-19 cases in a region, we may raise early warning signals of an epidemic by detecting signs of changes in the data. We propose a novel methodology to address this issue. The key idea is to employ a new information-theoretic notion, which we call the differential minimum description length change statistics (D-MDL), for measuring the scores of change sign. We first give a fundamental theory for D-MDL. We then demonstrate its effectiveness using synthetic datasets. We apply it to detecting early warning signals of the COVID-19 epidemic using time series of the cases for individual countries. We empirically demonstrate that D-MDL is able to raise early warning signals of events such as significant increase/decrease of cases. Remarkably, for about $$64\%$$ 64 % of the events of significant increase of cases in studied countries, our method can detect warning signals as early as nearly six days on average before the events, buying considerably long time for making responses. We further relate the warning signals to the dynamics of the basic reproduction number R0 and the timing of social distancing. The results show that our method is a promising approach to the epidemic analysis from a data science viewpoint.

scholarly journals Forecasting at scale

2017 ◽  
Author(s):  
Sean J Taylor ◽  
Benjamin Letham
Keyword(s):  
Time Series ◽  
Performance Analysis ◽  
Goal Setting ◽  
Capacity Planning ◽  
Domain Knowledge ◽  
Data Science ◽  
Time Series Modeling ◽  
High Quality ◽  
Performance Analyses ◽  
Manual Review

Forecasting is a common data science task that helps organizations with capacity planning, goal setting, and anomaly detection. Despite its importance, there are serious challenges associated with producing reliable and high quality forecasts — especially when there are a variety of time series and analysts with expertise in time series modeling are relatively rare. To address these challenges, we describe a practical approach to forecasting “at scale” that combines configurable models with analyst-in-the-loop performance analysis. We propose a modular regression model with interpretable parameters that can be intuitively adjusted by analysts with domain knowledge about the time series. We describe performance analyses to compare and evaluate forecasting procedures, and automatically flag forecasts for manual review and adjustment. Tools that help analysts to use their expertise most effectively enable reliable, practical forecasting of business time series.

Sign in / Sign up

Export Citation Format

Share Document