In jonasbhend/biascorrection: Bias Correct Ensemble Forecasts

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "README-"
)

biascorrection

Introduction

Collection of functions to calibrate daily ensemble forecasts. This package includes a wrapper for performing bias correction in in-sample, cross-validation, moving blocks cross-validation and forward modes and also includes a variety of calibration functions (regression-based, quantile mapping). The focus is on ease-of-use rather than performance when applied to large datasets. Consequently, specific functions will have to be implemented separately to be applicable in an operational setting.

Marginal support is provided to apply calibration functions to large datasets. Function debiasApply automates calibration with collections of forecasts and calibrating observations.

The bias correction options include:

library(biascorrection)
list_methods()

Getting started

First, install the package and vignettes.

devtools::install_github("MeteoSwiss/biascorrection", build_vignettes=TRUE)

Next, check out the examples provided in the vignette or the help and examples of individual functions in biascorrection.

vignette('biascorrection')

jonasbhend/biascorrection documentation built on Nov. 11, 2023, 1:16 a.m.