Courses
Digital Soil Mapping track
Follow the modules in order. Each one opens your personal RStudio in the SoilFER Lab with the exercise files ready.
| Module | Description | Duration | Level |
|---|---|---|---|
| Module 0 · Welcome and the SoilFER Lab | Check that your Lab works, find the training project and data, and open QGIS in the browser. | 30 min | Beginner |
| 01 · R essentials for soil data | Data frames, the tidyverse and spatial objects (sf, terra) applied to soil observations. | 2 h | Beginner |
| Module 1 · Introduction to R, spatial data and soil data preparation | R and RStudio basics, spatial data with terra and sf, quality control and harmonisation of the KSSL soil dataset, and building the covariate stack. | 4 sessions | Beginner |
| Module 2 · Soil sampling design | A three-stage probabilistic sampling design (PSU/SSU/TSU) using covariate space coverage, land-use strata and climate (Newhall) regimes. | 3 sessions | Intermediate |
| 02 · Soil data preparation and harmonisation | Quality control, depth harmonisation with splines, and preparing profile and topsoil data for mapping. | 3 h | Intermediate |
| 03 · Environmental covariates with Google Earth Engine | Building the covariate stack (terrain, climate, vegetation, parent material) in Google Earth Engine and R. | 3 h | Intermediate |
| Module 3 · Digital soil mapping | Modelling and mapping soil properties with Quantile Regression Forest: covariate selection (Boruta), training, accuracy assessment and tiled prediction with uncertainty. | 2 sessions | Intermediate |
| 04 · Digital soil mapping with machine learning | Regression-matrix, covariate selection and models (random forest, quantile regression forest, Cubist). | 4 h | Intermediate |
| Module 4 · Soil spectroscopy for digital soil mapping | Using MIR spectra to predict soil properties: pre-processing, calibration models and their use in digital soil mapping. | 4 sessions | Advanced |
| Module 5 · Soil data standardisation, sharing and dissemination | Standards, metadata and services for sharing soil data and maps through national soil information systems. | 1 session | Intermediate |
| 05 · Uncertainty and validation | Cross-validation, spatial cross-validation, prediction intervals and area of applicability. | 3 h | Advanced |
| 06 · Soil nutrient and nutrient budget maps | Producing N, P, K and SOC maps and nutrient budgets following the SoilFER / GSP technical specifications. | 4 h | Advanced |
No matching items