Let's do the time warp again: non‐linear time series matching as a tool for sequentially structured data in ecology

Abstract

Ecological patterns are often fundamentally chronological. However, generalization of data is necessarily accompanied by a loss of detail or resolution. Temporal data in particular contain information not only in data values but in the temporal structure, which is lost when these values are aggregated to provide point estimates. Dynamic time warping (DTW) is a time series comparison method that is capable of efficiently comparing series despite temporal offsets that confound other methods. The DTW method is both efficient and remarkably flexible, capable of efficiently matching not only time series but also any sequentially structured data set, which has made it a popular technique in machine learning, artificial intelligence, and big data analytical tasks. DTW is rarely used in ecology despite the ubiquity of temporally structured data. As technological advances have increased the richness of small-scale ecological data, DTW may be an attractive analysis technique because it is able to utilize the additional information contained in the temporal structure of many ecological data sets. In this study, we use an example data set of highresolution fish movement records obtained from otolith microchemistry to compare traditional analysis techniques with DTW clustering. Our results suggest that DTW is capable of detecting subtle behavioral patterns within otolith data sets which traditional data aggregation techniques cannot. These results provide evidence that the DTW method may be useful across many of the temporal data types commonly collected in ecology, as well other sequentially ordered "pseudo time series" data such as classification of species by shape.

A user‐friendly guide to using distance measures to compare time series in ecology

“…While the Euclidean distance is faster, better known, and still widely used in some fields, an extensive body of research has shown DTW to be more accurate (Dau et al, 2019 ; Paparrizos et al, 2020 ; Zhu et al, 2012 ), and it is considered the de facto standard for accuracy in classification (note that it is still important to consider the properties of DTW in relation to the data, as it does not perform well in every case). Despite this, it is rarely used in ecology (Hegg & Kennedy, 2021 ). Note, however, that DTW is computationally expensive and therefore can be slow for large datasets (for discussion on ways to speed up DTW, see Appendix E ).…”

A User-Friendly Guide to Using Distance Measures to Compare Time Series in Ecology

“…While the Euclidean Distance is faster, better known, and still widely used in some fields, an extensive body of research has shown DTW to be more accurate (Zhu et al ., 2012; Dau et al ., 2019; Paparrizos et al ., 2020) and it is considered the de facto standard for accuracy in classification (note that it is still important to consider the properties of DTW in relation to the data, as it does not perform well in every case). Despite this, it is rarely used in ecology (Hegg and Kennedy, 2021). Note, however, that DTW is computationally expensive and therefore can be slow for large datasets (for discussion on ways to speed up DTW, see supplementary materials S11).…”

Time series methods for the analysis of soundscapes and other cyclical ecological data

“…Dynamic time warping (DTW) is a technique that seeks to minimize the distance between two time series by expanding or contracting the temporal axis to find the closest fit between the two time series (Hegg & Kennedy, 2021). More generally, it can be used to cluster multiple time series into similar groups.…”