loading page

EWSmethods: an R package to forecast tipping points at the community level using early warning signals and machine learning models
  • +3
  • Duncan O'Brien,
  • Smita Deb,
  • Sahil Sidheekh,
  • Narayanan Krishnan,
  • Partha S. Dutta,
  • Christopher clements
Duncan O'Brien
University of Bristol

Corresponding Author:[email protected]

Author Profile
Smita Deb
IIT Ropar
Author Profile
Sahil Sidheekh
The University of Texas at Dallas
Author Profile
Narayanan Krishnan
IIT Palakkad
Author Profile
Partha S. Dutta
Department of Mathematics, Indian Institute of Technology Ropar, Rupnagar
Author Profile
Christopher clements
University of Bristol
Author Profile

Abstract

Early warning signals (EWSs) represent a potentially universal tool for identifying whether a system is approaching a tipping point, and have been applied in fields including ecology, epidemiology, economics, and physics. This potential universality has led to the development of a suite of computational approaches aimed at improving the reliability of these methods. Classic methods based on univariate data have a long history of use, but recent theoretical advances have expanded EWSs to multivariate datasets, particularly relevant given advancements in remote sensing. More recently, novel machine learning approaches have been developed but have not been made accessible in the R environment. Here, we present EWSmethods – an R package that provides a unified syntax and interpretation of the most popular and cutting edge EWSs methods applicable to both univariate and multivariate time series. EWSmethods provides two primary functions for univariate and multivariate systems respectively, with two forms of calculation available for each: classical rolling window time series analysis, and the more robust expanding window. It also provides an interface to the Python machine learning model EWSNet which predicts the probability of a sudden tipping point or a smooth transition, the first of its form available to R users. This note details the rationale for this open-source package and delivers an introduction to its functionality for assessing resilience. We have also provided vignettes and an external website to act as further tutorials and FAQs.
09 Nov 2022Submitted to Ecography
09 Nov 2022Submission Checks Completed
09 Nov 2022Assigned to Editor
09 Nov 2022Review(s) Completed, Editorial Evaluation Pending
15 Nov 2022Reviewer(s) Assigned
11 Apr 2023Editorial Decision: Revise Major
27 Apr 20231st Revision Received
27 Apr 2023Submission Checks Completed
27 Apr 2023Assigned to Editor
27 Apr 2023Review(s) Completed, Editorial Evaluation Pending
28 Apr 2023Reviewer(s) Assigned
31 May 2023Editorial Decision: Revise Minor
01 Jun 20232nd Revision Received
01 Jun 2023Submission Checks Completed
01 Jun 2023Assigned to Editor
01 Jun 2023Review(s) Completed, Editorial Evaluation Pending
01 Jun 2023Editorial Decision: Accept