convergent cross mapping

In the event one has access to system variables as time series observations, Takens' embedding theorem can be applied. Takens' theorem generically proves that the state space of a dynamical system can be reconstructed from a single observed time series of the system, $X$. This reconstructed or shadow manifold $M\_X$ is diffeomorphic to the true manifold, $M$, preserving instrinsic state space properties of $M$ in $M\_X$.

Convergent Cross Mapping (CCM) leverages a corollary to the Generalized Takens Theorem{{cite journal | doi=10.1371/journal.pone.0018295 | doi-access=free | title=Generalized Theorems for Nonlinear State Space Reconstruction | year=2011 | last1=Deyle | first1=Ethan R. | last2=Sugihara | first2=George | journal=PLOS ONE | volume=6 | issue=3 | pages=e18295 | pmid=21483839 | pmc=3069082 | bibcode=2011PLoSO...618295D }} that it should be possible to cross predict or cross map between variables observed from the same system. Suppose that in some dynamical system involving variables $X$ and $Y$, $X$ causes $Y$. Since $X$ and $Y$ belong to the same dynamical system, their reconstructions via embeddings $M\_\{X\}$ and $M\_\{Y\}$, also map to the same system.

The causal variable $X$ leaves a signature on the affected variable $Y$, and consequently, the reconstructed states based on $Y$ can be used to cross predict values of $X$. CCM leverages this property to infer causality by predicting $X$ using the $M\_\{Y\}$ library of points (or vice-versa for the other direction of causality), while assessing improvements in cross map predictability as larger and larger random samplings of $M\_\{Y\}$ are used. If the prediction skill of $X$ increases and saturates as the entire $M\_\{Y\}$ is used, this provides evidence that $X$ is causally influencing $Y$.

Cross mapping is generally asymmetric. If $X$ forces $Y$ unidirectionally, variable $Y$ will contain information about $X$, but not vice versa. Consequently, the state of $X$ can be predicted from $M\_Y$, but $Y$ will not be predictable from $M\_X$.

The basic steps of convergent cross mapping for a variable $X$ of length $N$ against variable $Y$ are:

1. If needed, create the state space manifold $M\_Y$ from $Y$
2. Define a sequence of library subset sizes $L$ ranging from a small fraction of $N$ to close to $N$.
3. Define a number of ensembles $N\_E$ to evaluate at each library size.
4. At each library subset size $L\_i$:
5. For $N\_E$ ensembles:
6. Randomly select $L\_i$ state space vectors from $M\_Y$
7. Estimate $\backslash hat\{X\}$ from the random subset of $M\_Y$ using the Simplex state space prediction
8. Compute the correlation $\backslash rho$ between $\backslash hat\{X\}$ and $X$
9. Compute the mean correlation $\backslash bar\{\backslash rho\}$ over the $N\_E$ ensembles at $L\_i$
10. The spectrum of $\backslash bar\{\backslash rho\}$ versus $L$ must exhibit convergence.
11. Assess significance. One technique is to compare $\backslash bar\{\backslash rho\}$ to $\backslash bar\{\backslash rho\_S\}$ computed from $S$ random realizations (surrogates) of $X$.

CCM is used to detect if two variables belong to the same dynamical system, for example, can past ocean surface temperatures be estimated from the population data over time of sardines or if there is a causal relationship between cosmic rays and global temperatures. As for the latter it was hypothesised that cosmic rays may impact cloud formation, therefore cloudiness, therefore global temperatures. {{Citation |last=Tsonis |first=Anastasios A. |title=Convergent Cross Mapping: Theory and an Example |date=2018 |url=https://doi.org/10.1007/978-3-319-58895-7_27 |work=Advances in Nonlinear Geosciences |pages=587–600 |editor-last=Tsonis |editor-first=Anastasios A. |access-date=2023-10-19 |place=Cham |publisher=Springer International Publishing |language=en |doi=10.1007/978-3-319-58895-7_27 |isbn=978-3-319-58895-7 |last2=Deyle |first2=Ethan R. |last3=Ye |first3=Hao |last4=Sugihara |first4=George|url-access=subscription }}

Extensions to CCM include:

• Extended Convergent Cross Mapping{{cite journal | doi=10.1038/srep14750 | title=Distinguishing time-delayed causal interactions using convergent cross mapping | year=2015 | last1=Ye | first1=Hao | last2=Deyle | first2=Ethan R. | last3=Gilarranz | first3=Luis J. | last4=Sugihara | first4=George | journal=Scientific Reports | volume=5 | page=14750 | pmid=26435402 | pmc=4592974 | bibcode=2015NatSR...514750Y }}
• Convergent Cross Sorting{{cite journal | url=https://doi.org/10.1038/s41598-021-98864-2 | doi=10.1038/s41598-021-98864-2 | title=Convergent cross sorting for estimating dynamic coupling | year=2021 | last1=Breston | first1=Leo | last2=Leonardis | first2=Eric J. | last3=Quinn | first3=Laleh K. | last4=Tolston | first4=Michael | last5=Wiles | first5=Janet | last6=Chiba | first6=Andrea A. | journal=Scientific Reports | volume=11 | issue=1 | page=20374 | pmid=34645847 | pmc=8514556 | bibcode=2021NatSR..1120374B | s2cid=238859361 }}

• Empirical dynamic modeling
• System dynamics
• Complex dynamics

{{Reflist}}

• {{cite journal

|journal = Ecol Res

|year = 2017

|title = Empirical dynamic modeling for beginners

|pages = 785–796

|author = Chang, CW., Ushio, M. & Hsieh, Ch.

|volume = 32

|issue = 6

|doi = 10.1007/s11284-017-1469-9

|doi-access = free

|hdl = 2433/235326

|hdl-access = free

}}

• {{cite journal

|journal = ICES Journal of Marine Science

|year = 2020

|title = Frequently asked questions about nonlinear dynamics and empirical dynamic modelling

|pages = 1463–1479

|author = Stephan B Munch, Antoine Brias, George Sugihara, Tanya L Rogers

|volume = 77

|doi = 10.1093/icesjms/fsz209

|issue = 4

|url = https://doi.org/10.1093/icesjms/fsz209

|url-access = subscription

}}

Animations:

• {{YouTube|fevurdpiRYg|State Space Reconstruction: Time Series and Dynamic Systems}}
• {{YouTube|QQwtrWBwxQg|State Space Reconstruction: Takens' Theorem and Shadow Manifolds}}
• {{YouTube|NrFdIz-D2yM|State Space Reconstruction: Convergent Cross Mapping}}

{{Authority control}}

Category:Nonlinear systems

Category:Predictive analytics

Category:Nonlinear time series analysis

Category:Time series statistical tests