Harnessing the power of topological data analysis to detect change points
We introduce a novel geometry‐oriented methodology, based on the emerging tools of topological data analysis, into the change‐point detection framework. The key rationale is that change points are likely to be associated with changes in geometry behind the data‐generating process. While the applicat...
Published in: | Environmetrics |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Subjects: | |
Online Access: | https://doi.org/10.1002/env.2612 |
id |
ftrepec:oai:RePEc:wly:envmet:v:31:y:2020:i:1:n:e2612 |
---|---|
record_format |
openpolar |
spelling |
ftrepec:oai:RePEc:wly:envmet:v:31:y:2020:i:1:n:e2612 2023-05-15T17:32:53+02:00 Harnessing the power of topological data analysis to detect change points Umar Islambekov Monisha Yuvaraj Yulia R. Gel https://doi.org/10.1002/env.2612 unknown https://doi.org/10.1002/env.2612 article ftrepec https://doi.org/10.1002/env.2612 2020-12-04T13:31:20Z We introduce a novel geometry‐oriented methodology, based on the emerging tools of topological data analysis, into the change‐point detection framework. The key rationale is that change points are likely to be associated with changes in geometry behind the data‐generating process. While the applications of topological data analysis to change‐point detection are potentially very broad, in this paper, we primarily focus on integrating topological concepts with the existing nonparametric methods for change‐point detection. In particular, the proposed new geometry‐oriented approach aims to enhance detection accuracy of distributional regime shift locations. Our simulation studies suggest that integration of topological data analysis with some existing algorithms for change‐point detection leads to consistently more accurate detection results. We illustrate our new methodology in application to the two closely related environmental time series data sets—ice phenology of the Lake Baikal and the North Atlantic Oscillation indices, in a research query for a possible association between their estimated regime shift locations. Article in Journal/Newspaper North Atlantic North Atlantic oscillation RePEc (Research Papers in Economics) Environmetrics 31 1 |
institution |
Open Polar |
collection |
RePEc (Research Papers in Economics) |
op_collection_id |
ftrepec |
language |
unknown |
description |
We introduce a novel geometry‐oriented methodology, based on the emerging tools of topological data analysis, into the change‐point detection framework. The key rationale is that change points are likely to be associated with changes in geometry behind the data‐generating process. While the applications of topological data analysis to change‐point detection are potentially very broad, in this paper, we primarily focus on integrating topological concepts with the existing nonparametric methods for change‐point detection. In particular, the proposed new geometry‐oriented approach aims to enhance detection accuracy of distributional regime shift locations. Our simulation studies suggest that integration of topological data analysis with some existing algorithms for change‐point detection leads to consistently more accurate detection results. We illustrate our new methodology in application to the two closely related environmental time series data sets—ice phenology of the Lake Baikal and the North Atlantic Oscillation indices, in a research query for a possible association between their estimated regime shift locations. |
format |
Article in Journal/Newspaper |
author |
Umar Islambekov Monisha Yuvaraj Yulia R. Gel |
spellingShingle |
Umar Islambekov Monisha Yuvaraj Yulia R. Gel Harnessing the power of topological data analysis to detect change points |
author_facet |
Umar Islambekov Monisha Yuvaraj Yulia R. Gel |
author_sort |
Umar Islambekov |
title |
Harnessing the power of topological data analysis to detect change points |
title_short |
Harnessing the power of topological data analysis to detect change points |
title_full |
Harnessing the power of topological data analysis to detect change points |
title_fullStr |
Harnessing the power of topological data analysis to detect change points |
title_full_unstemmed |
Harnessing the power of topological data analysis to detect change points |
title_sort |
harnessing the power of topological data analysis to detect change points |
url |
https://doi.org/10.1002/env.2612 |
genre |
North Atlantic North Atlantic oscillation |
genre_facet |
North Atlantic North Atlantic oscillation |
op_relation |
https://doi.org/10.1002/env.2612 |
op_doi |
https://doi.org/10.1002/env.2612 |
container_title |
Environmetrics |
container_volume |
31 |
container_issue |
1 |
_version_ |
1766131184450928640 |