Soil Health

This project maps soil health and soil quality indicators to support sustainable management and restoration. We link soil measurements (e.g., SOC, pH, salinity/alkalinity indicators, carbonate status, texture-related attributes) with terrain, climate, land cover, and remote sensing covariates to predict soil condition across space. Machine learning models are validated with spatially structured evaluation to ensure realistic accuracy. Deliverables include indicator and/or index maps plus confidence layers for decision support.

Main focus

• Spatial prediction of soil health indicators and integrated soil quality indices.
• Identify hotspots of constraint and opportunity for targeted management.
• Provide confidence information to support monitoring and restoration.

Objectives

1. Define soil health indicators/indices and compile observation datasets.
2. Train ML models with spatial validation for realistic generalization.
3. Deliver soil health maps (and confidence) to guide management and monitoring.

Graphical abstract

:::: {.row .justify-content-sm-center} ::: {.col-sm-10 .mt-3 .mt-md-0}

::: ::::

::: caption Graphical abstract summarizing the workflow and key results. :::

Papers (selected)

Paper 1 — Soil Quality in Protected vs Degraded Semiarid Oak Forests

DOI

Paper 2 — Soil Quality Variability Within Management Zones

DOI

Paper 3 — Slope and Land Use Change Impacts on Soil Quality

DOI