TransitionsInTimeseries.jl
TransitionsInTimeseries — ModuleTransitionsInTimeseries.jl
TransitionsInTimeseries.jl is a free and open-source software to easily analyse transitions within timeseries in a reproducible, performant, extensible and reliable way. In contrast to other existing software with similar target application, TransitionsInTimeseries.jl defines a generic interface for how to find transitions and how to test for significance. Within this interface, it is easy to expand the software in three orthogonal ways:
- Provide the analysis pipelines with new indicators, which can be either self-written or imported from other packages. In particular, the latter offers thousands of metrics that can indicate transitions right out of the box.
- Add new analysis pipelines for finding transitions.
- Add new ways for significance testing.
TransitionsInTimeseries is a registered Julia package and can be installed by running:
] add TransitionsInTimeseriesAll further information is provided in the documentation, which you can either find online or build locally by running the docs/make.jl file.
Alternative names for this package could have been: Early Warning Signals / Resilience Indicators / Regime-Shift Identifiers / Change-Point Detectors, or however else you want to call them!
If you have found this package useful, please consider starring it on GitHub. This gives us an accurate lower bound of the (satisfied) user count.
Content
Multi-stable systems can display abrupt transitions between two stability regimes. To predict such transitions in real-world systems solely based on data, mathematical tools have been developed in the last decades. Numerous terminologies have been used for them, such as early warning signals, resilience indicators, regime-shift identifiers, change-point detection and transition indicators. TransitionsInTimeseries.jl sticks to the latter terminology and provides an interface that:
- Allows a fast computation of common transition indicators with a couple of lines, as demonstrated in the example section.
- Makes the surrogate analysis to test for significance under the hub.
- Can be easily extended by any user without touching the source code.
- Reduces the programming overhead for any researcher willing to benchmark new methods.
- Eases the reproducibility thanks to a clear syntax, a simple installation and RNG-seeded surrogate generation.
- Increases trustworthiness thanks to a large test suite.
Approaches
Over the last decades, research on transition indicators has largely focused on Critical Slowing Down (CSD). CSD is observed when a system approaches a Hopf, a transcritical or a fold bifurcation and consists in a resilience loss of the system. For instance this can be diagnosed by an increase of the variance and the AR1-regression coefficient, as demonstrated in the example section. However, we emphasize that this is one out of many possible approaches for obtaining transition indicators. Recent work has explored new approaches relying on nonlinear dynamics or machine learning. TransitionsInTimeseries.jl is designed to allow these cutting-edge methods and foster the development of new ones.