SDA Downscale Function — SDA_downscale • PEcAnAssimSequential

This function uses either Random Forest or Convolutional Neural Network model based on the model_type parameter.

Usage

SDA_downscale(
  preprocessed,
  date,
  carbon_pool,
  covariates,
  model_type = "rf",
  seed = NULL
)

preprocessed: List. Preprocessed data returned as an output from the SDA_downscale_preprocess function.
date: Date. If SDA site run, format is yyyy/mm/dd; if NEON, yyyy-mm-dd. Restricted to years within file supplied to 'preprocessed' from the 'data_path'.
carbon_pool: Character. Carbon pool of interest. Name must match carbon pool name found within file supplied to 'preprocessed' from the 'data_path'.
covariates: SpatRaster stack. Used as predictors in downscaling. Layers within stack should be named. Recommended that this stack be generated using 'covariates' instructions in assim.sequential/inst folder
model_type: Character. Either "rf" for Random Forest or "cnn" for Convolutional Neural Network. Default is Random Forest.
seed: Numeric or NULL. Optional seed for random number generation. Default is NULL.

A list containing the training and testing data sets, models, predicted maps for each ensemble member, and predictions for testing data.

This function will downscale forecast data to unmodeled locations using covariates and site locations

Joshua Ploshay, Sambhav Dixit