Module 4 · Soil spectroscopy for digital soil mapping

Digital Soil Mapping
Using MIR spectra to predict soil properties: pre-processing, calibration models and their use in digital soil mapping.

Format: 4 parts · Level: Advanced · Runs in: SoilFER Learn lab (JupyterLab · RStudio · QGIS) · Material: SoilFER Training Manual + Training Resources

What you will learn

  • load and explore MIR spectral libraries
  • pre-process spectra (prospectr)
  • calibrate and validate spectral prediction models
  • use spectral predictions as input to mapping

Notebooks

Use the workspace your trainer picks. In a notebook, run the Setup cell first, then the cells in order.

  • JupyterLab opens the notebook in your SoilFER Learn lab, with the project, packages and data already there.
  • RStudio: the same exercises as the original R scripts. RRStudio opens the SoilFER-Training-Resources project; the scripts are in 02_scripts/module4.
Session Open in
Part 1 · Read and pre-process spectra

JJupyterLab.ipynb

Part 2 · Spectroscopy calibration models

JJupyterLab.ipynb

Part 3 · Digital soil mapping with spectral predictions

JJupyterLab.ipynb

Part 4 · Additional exercises

JJupyterLab.ipynb

Parts 2–4 continue from the previous part. If you restarted your lab or the notebook kernel, run the Fresh runtime? cell at the top of the notebook first.

TipSee your maps

The last cell of the mapping notebooks, Explore your results, plots your maps and packs them into soilfer_outputs.zip. Open them in QGIS in your Lab (QGIS desktop), or download the zip and drop it on the Map viewer.

First time here? Read Getting started.

Back to top