Linear Dynamical System Reconstruction
Reconstruction metrics
Call a reconstruction method
Pearson's correlation
Cross validate LDS model. This is a wrapper for LDS_reconstruction
Cross validation of PCR reconstruction.
Exponential confidence interval
Inverse Box-Cox transform
Implement Kalman smoothing
Kling-Gupta Efficiency
Learn LDS with L-BFGS-B
Learn LDS with L-BFGS-B
Learn LDS model
Learn LDS model with multiple initial conditions
Learn a linear dynamical system using Genetic Algorithm.
Learn LDS model.
Multiple LDS replicates
ldsr: Linear Dynamical System Reconstruction
Make initial values for parameters.
Make cross-validation folds.
Transform the estimates before calculating metrics
Maximizing expected likelihood using analytical solution
Calculates the negative log-likelihood
Normalized root-mean-square error
Nash-Sutcliffe Efficiency
One cross-validation run
One LDS replicate
One cross-validation run
Select the best reconstruction
Principal Component Regression Reconstruction
Penalized likelihood objective function
State propagation
Reduction of Error
Converts theta from a vector (as used in GA) to list (as used in Kalma...
Streamflow (and climate) reconstruction using Linear Dynamical Systems. The advantage of this method is the additional state trajectory which can reveal more information about the catchment or climate system. For details of the method please refer to Nguyen and Galelli (2018) <doi:10.1002/2017WR022114>.