177 lines
6.6 KiB
R
177 lines
6.6 KiB
R
# ============================================================================
|
||
# SCRIPT 30: Growth Model Interpolation (CI Time Series)
|
||
# ============================================================================
|
||
# PURPOSE:
|
||
# Interpolate Canopy Index (CI) values across time to create continuous
|
||
# growth curves. Fills gaps in measurement dates, applies smoothing via
|
||
# LOESS, and generates daily CI estimates and cumulative statistics for
|
||
# each field. Enables downstream yield prediction and trend analysis.
|
||
#
|
||
# INPUT DATA:
|
||
# - Source: laravel_app/storage/app/{project}/combined_CI/combined_CI_data.rds
|
||
# - Format: RDS (wide format: fields × dates with CI values)
|
||
# - Requirement: Field boundaries (pivot.geojson) and harvest data (harvest.xlsx)
|
||
#
|
||
# OUTPUT DATA:
|
||
# - Destination: laravel_app/storage/app/{project}/interpolated_ci/
|
||
# - Format: RDS files per field (daily CI estimates)
|
||
# - Also exports: Growth model curves as RDS (cumulative CI, daily values)
|
||
#
|
||
# USAGE:
|
||
# Rscript 30_interpolate_growth_model.R [project]
|
||
#
|
||
# Example (Windows PowerShell):
|
||
# & "C:\Program Files\R\R-4.4.3\bin\x64\Rscript.exe" r_app/30_interpolate_growth_model.R angata
|
||
#
|
||
# PARAMETERS:
|
||
# - project: Project name (character) - angata, chemba, xinavane, esa, simba
|
||
#
|
||
# CLIENT TYPES:
|
||
# - cane_supply (ANGATA): Yes - core growth monitoring
|
||
# - agronomic_support (AURA): Yes - field health trend analysis
|
||
#
|
||
# DEPENDENCIES:
|
||
# - Packages: tidyverse, lubridate
|
||
# - Utils files: parameters_project.R, 00_common_utils.R, 30_growth_model_utils.R
|
||
# - External data: Field boundaries (pivot.geojson), harvest data (harvest.xlsx)
|
||
# - Input data: combined_CI_data.rds from Script 20
|
||
# - Data directories: interpolated_ci/ (created if missing)
|
||
#
|
||
# NOTES:
|
||
# - Interpolation method: LOESS smoothing with span = 0.3 (sensitive to local trends)
|
||
# - Gap-filling: Assumes continuous growth between measurements; skips clouds
|
||
# - Cumulative CI: Sum of daily interpolated values from planting to current date
|
||
# - Used by: Script 80 (KPI trends) and Script 12 (yield forecasting)
|
||
# - Critical for 8-week CV trend calculation and 4-week growth categorization
|
||
#
|
||
# RELATED ISSUES:
|
||
# SC-112: Utilities restructuring
|
||
# SC-108: Core pipeline improvements
|
||
#
|
||
# ============================================================================
|
||
|
||
# 1. Load required packages
|
||
# -----------------------
|
||
suppressPackageStartupMessages({
|
||
# File path handling
|
||
library(here) # For relative path resolution (platform-independent file paths)
|
||
|
||
# Data manipulation
|
||
library(tidyverse) # For dplyr (data wrangling, grouping, mutating)
|
||
library(lubridate) # For date/time operations (date arithmetic, ISO week extraction)
|
||
library(readxl) # For reading harvest.xlsx (harvest dates for growth model phases)
|
||
})
|
||
|
||
# =============================================================================
|
||
# MAIN PROCESSING FUNCTION
|
||
# =============================================================================
|
||
|
||
main <- function() {
|
||
# STEP 1: Set working directory to project root (smartcane/)
|
||
# This ensures all relative paths resolve correctly
|
||
if (basename(getwd()) == "r_app") {
|
||
setwd("..")
|
||
}
|
||
|
||
# STEP 2: SOURCE ALL UTILITY SCRIPTS (before any operations)
|
||
# Parse command-line arguments FIRST
|
||
args <- commandArgs(trailingOnly = TRUE)
|
||
project_dir <- if (length(args) >= 1 && args[1] != "") args[1] else "angata"
|
||
|
||
# Make project_dir available globally for parameters_project.R
|
||
assign("project_dir", project_dir, envir = .GlobalEnv)
|
||
|
||
# Load parameters_project.R (provides setup_project_directories, etc.)
|
||
tryCatch({
|
||
source("r_app/parameters_project.R")
|
||
}, error = function(e) {
|
||
cat(sprintf("Error loading parameters_project.R: %s\n", e$message))
|
||
stop(e)
|
||
})
|
||
|
||
# Load growth model utilities
|
||
tryCatch({
|
||
source("r_app/30_growth_model_utils.R")
|
||
}, error = function(e) {
|
||
cat(sprintf("Error loading 30_growth_model_utils.R: %s\n", e$message))
|
||
stop(e)
|
||
})
|
||
|
||
# STEP 3: Now all utilities are loaded, proceed with script logic
|
||
safe_log(sprintf("=== Script 30: Growth Model Interpolation ==="))
|
||
safe_log(sprintf("Project: %s", project_dir))
|
||
|
||
# Set up directory paths from parameters
|
||
setup <- setup_project_directories(project_dir)
|
||
|
||
# For per-field architecture: read from daily_ci_vals_dir (Script 20 per-field output)
|
||
daily_vals_dir <- setup$daily_ci_vals_dir
|
||
safe_log(sprintf("Using per-field daily CI directory: %s", daily_vals_dir))
|
||
|
||
safe_log("Starting CI growth model interpolation")
|
||
|
||
# Load and process the data
|
||
tryCatch({
|
||
# Load the combined CI data (created by Script 20 per-field)
|
||
# Script 20 per-field outputs: daily_vals/{FIELD_NAME}/{YYYY-MM-DD}.rds
|
||
CI_data <- load_combined_ci_data(daily_vals_dir)
|
||
|
||
# Load harvesting data from harvest.xlsx for growth model phase assignment
|
||
# Use the centralized load_harvesting_data() function which handles NA season_end values
|
||
# by setting them to Sys.Date() (field is still in current growing season)
|
||
data_dir <- setup$data_dir
|
||
harvesting_data <- tryCatch({
|
||
load_harvesting_data(data_dir)
|
||
}, error = function(e) {
|
||
safe_log(paste("Error loading harvest data:", e$message), "WARNING")
|
||
NULL
|
||
})
|
||
|
||
# Validate harvesting data
|
||
if (is.null(harvesting_data) || nrow(harvesting_data) == 0) {
|
||
safe_log("No harvesting data available", "ERROR")
|
||
stop("No harvesting data available")
|
||
}
|
||
|
||
# Get the years from harvesting data
|
||
years <- harvesting_data %>%
|
||
filter(!is.na(season_start)) %>%
|
||
distinct(year) %>%
|
||
pull(year)
|
||
|
||
safe_log(paste("Processing data for years:", paste(years, collapse = ", ")))
|
||
|
||
# Generate interpolated CI data for each year and field
|
||
CI_all <- generate_interpolated_ci_data(years, harvesting_data, CI_data)
|
||
|
||
# CI_all <- CI_all %>%
|
||
# group_by(Date, field, season) %>%
|
||
# filter(!(field == "00F25" & season == 2023 & duplicated(DOY)))
|
||
|
||
# Calculate growth metrics and save the results
|
||
if (nrow(CI_all) > 0) {
|
||
# Add daily and cumulative metrics
|
||
CI_all_with_metrics <- calculate_growth_metrics(CI_all)
|
||
|
||
# Save the processed data to cumulative_vals directory
|
||
save_growth_model(
|
||
CI_all_with_metrics,
|
||
setup$cumulative_ci_vals_dir,
|
||
"All_pivots_Cumulative_CI_quadrant_year_v2.rds"
|
||
)
|
||
} else {
|
||
safe_log("No CI data was generated after interpolation", "WARNING")
|
||
}
|
||
|
||
safe_log("Growth model interpolation completed successfully")
|
||
|
||
}, error = function(e) {
|
||
safe_log(paste("Error in growth model interpolation:", e$message), "ERROR")
|
||
stop(e$message)
|
||
})
|
||
}
|
||
|
||
if (sys.nframe() == 0) {
|
||
main()
|
||
}
|