MLFS (version 0.4.2)

height_prediction: height_prediction

Description

Height model

Usage

height_prediction(
  df_fit,
  df_predict,
  species_n_threshold = 100,
  height_model = "naslund",
  BRNN_neurons = 3,
  height_pred_level = 0,
  eval_model_height = TRUE,
  blocked_cv = TRUE,
  k = 10
)

Value

a list with four elements:

1. $data_height_predictions - a data frame with imputed tree heights

2. $data_height_eval - a data frame with predicted and observed tree heights, or a character string indicating that tree heights were not evaluated

3. $model_species - the output model for tree heights (species level)

4. $model_speciesGroups - the output model for tree heights (species group level)

Arguments

df_fit

data frame with tree heights and basal areas for individual trees

df_predict

data frame which will be used for predictions

species_n_threshold

a positive integer defining the minimum number of observations required to treat a species as an independent group

height_model

character string defining the model to be used for height prediction. If 'brnn', then ANN method with Bayesian Regularization is applied. In addition, all 2- and 3- parametric H-D models from lmfor R package are available.

BRNN_neurons

positive integer defining the number of neurons to be used in the brnn method.

height_pred_level

integer with value 0 or 1 defining the level of prediction for height-diameter (H-D) models. The value 1 defines a plot-level prediction, while the value 0 defines regional-level predictions. Default is 0. If using 1, make sure to have representative plot-level data for each species.

eval_model_height

logical, should the height model be evaluated and returned as the output

blocked_cv

logical, should the blocked cross-validation be used in the evaluation phase?

k

the number of folds to be used in the k fold cross-validation

Examples

library(MLFS)
data(data_tree_heights)
data(data_v2)

# A) Example with the BRNN method
h_predictions <- height_prediction(df_fit = data_tree_heights,
                                   df_predict = data_v2,
                                   species_n_threshold = 100,
                                   height_pred_level = 0,
                                   height_model = "brnn",
                                   BRNN_neurons = 3,
                                   eval_model_height = FALSE,
                                   blocked_cv = TRUE, k = 10
                                   )

predicted_df <- h_predictions$data_height_predictions # df with imputed heights
evaluation_df <- h_predictions$data_height_eval # df with evaluation results