Physics-Informed Neural Networks for Soil Water Retention Curves

---

Documentation for package ‘soilFlux’ version 0.1.5

• DESCRIPTION file
• User guides, package vignettes and other documentation
• Package README

Help Pages

add_texture	Add texture classification column to a data frame
apply_minmax	Apply a fitted min-max scaler to a data frame
build_residual_sets	Build physics residual point sets (S1 – S4)
build_swrc_model	Build the CNN1D monotone-integral SWRC model
classify_texture	Classify soil texture according to the USDA system
data_prep	Data preparation for CNN1D SWRC modelling
evaluate_swrc	Compute metrics from a swrc_fit on new data
fit_minmax	Fit a min-max scaler from a training data frame
fit_swrc	Fit a physics-informed CNN1D SWRC model
fix_bd_units	Detect and correct bulk-density units
head_from_pf	Convert pF to matric head (cm)
head_normalize	Normalise matric head (cm) to the pF domain
invert_minmax	Invert a min-max scaling transformation
io	Save and load fitted SWRC models
load_swrc_model	Load a previously saved SWRC model from disk
metrics	Performance metrics for SWRC models
model	CNN1D monotone-integral model architecture
norouzi_lambdas	Return default Norouzi et al. (2025) loss weights (lambdas)
parse_depth	Parse a soil depth string into midpoint and label
parse_depth_column	Parse depth column in a data frame
pf_from_head	Convert matric head (cm) to pF
pf_normalize	Normalise pF values to [0, 1]
physics	Physics-informed constraints for SWRC modelling
plots	Publication-quality plots for SWRC analysis
plot_pred_obs	Plot predicted vs. observed water content
plot_swrc	Plot soil water retention curves (SWRC)
plot_swrc_metrics	Plot model performance metric comparison
plot_training_history	Plot training loss history
predict	Prediction from fitted SWRC models
predict.swrc_fit	Predict method for swrc_fit
predict_swrc	Predict water content at specific pF or matric-head values
predict_swrc_dense	Predict dense SWRC curves for a set of soil profiles
predict_theta_s	Extract saturated water content (theta_s) from covariates
prepare_swrc_data	Prepare a soil data frame for SWRC modelling
print.swrc_fit	Print method for swrc_fit
save_swrc_model	Save a fitted SWRC model to disk
scale	Min-max feature scaling
summary.swrc_fit	Summary method for swrc_fit
swrc_example	Example soil water retention dataset
swrc_metrics	Compute regression metrics for SWRC predictions
swrc_metrics_by_group	Compute regression metrics by group
swrc_model_exists	Check whether a model directory contains a valid saved model
texture	USDA soil texture classification
texture_triangle	Plot a soil texture triangle (ternary diagram)
theta_unit_factor	Detect theta unit scale factor
train	Training the CNN1D SWRC model
utils	Utility functions for soilFlux