Graph by Blas M. Benito
The package distantia allows to measure the dissimilarity between multivariate time-series. The package assumes that the target sequences are ordered along a given dimension, being depth and time the most common ones, but others such as latitude or elevation are also possible. Furthermore, the target time-series can be regular or irregular, and have their samples aligned (same age/time/depth) or unaligned (different age/time/depth). The only requirement is that the sequences must have at least two (but ideally more) columns with the same name and units representing different variables relevant to the dynamics of a system of interest.
The GitHub page of the project contains a thorough explanation of the statistics behind the method. The paper published in the Ecography journal describes the method, the package, and a couple of practical examples. The code and data used to develop the examples can be found in GitHub and Zenodo.
Please, if you find this package useful, please cite it as:
Benito, B.M. and Birks, H.J.B. (2020), distantia: an open‐source toolset to quantify dissimilarity between multivariate ecological time‐series. Ecography, 43: 660-667. https://doi.org/10.1111/ecog.04895
