No packages match

MBC - Multivariate Bias Correction of Climate Model Outputs

Calibrate and apply multivariate bias correction algorithms for climate model simulations of multiple climate variables. Three methods described by Cannon (2016) <doi:10.1175/JCLI-D-15-0679.1> and Cannon (2018) <doi:10.1007/s00382-017-3580-6> are implemented -- (i) MBC Pearson correlation (MBCp), (ii) MBC rank correlation (MBCr), and (iii) MBC N-dimensional PDF transform (MBCn) -- as is the Rank Resampling for Distributions and Dependences (R2D2) method. An additional multivariate rescaling method based on the linear Monge-Kantorovich map for Gaussian optimal transport of dependence structure is also included.

Last updated

4.49 score 11 stars 1 dependents 47 scripts 822 downloads

monmlp - Multi-Layer Perceptron Neural Network with Optional Monotonicity Constraints

Train and make predictions from a multi-layer perceptron neural network with optional partial monotonicity constraints.

Last updated

2.21 score 1 dependents 54 scripts 271 downloads

CaDENCE - Conditional Density Estimation Network Construction and Evaluation

Parameters of a user-specified probability distribution are modelled by a multi-layer perceptron artificial neural network. This framework can be used to implement probabilistic nonlinear models including mixture density networks, heteroscedastic regression models, zero-inflated models, etc. following Cannon (2012) <doi:10.1016/j.cageo.2011.08.023>.

Last updated

1.49 score 31 scripts 358 downloads

GEVcdn - GEV Conditional Density Estimation Network

Implements a flexible nonlinear modelling framework for nonstationary generalized extreme value analysis in hydroclimatology following Cannon (2010) <doi:10.1002/hyp.7506>.

Last updated

1.00 score 1 stars 5 scripts 201 downloads