Soil Moisture

Estimates soil moisture/VWC using UAV and satellite features, delivering field-scale maps for variable-rate irrigation.

This project estimates soil moisture and volumetric water content (VWC) using UAV imagery and complementary satellite observations. We link field measurements with remote-sensing features (multispectral/hyperspectral, time series, and where relevant radar) and terrain context to map within-field moisture variability. Machine learning models provide high-resolution moisture surfaces useful for variable-rate irrigation and water-use efficiency. Outputs can include confidence information to support operational decision-making.

Main focus

  • Field-scale soil moisture/VWC mapping using UAV + satellite information.
  • Support precision irrigation through spatially explicit moisture insights.
  • Build reliable prediction workflows validated across dates and conditions.

Objectives

  1. Integrate in-situ moisture data with UAV/satellite-derived features.
  2. Train ML models to estimate moisture patterns across space (and depth when available).
  3. Produce moisture maps (and confidence layers) for variable-rate irrigation planning.

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 Moisture Retrieval from Sentinel-1

DOI




Paper 2 — Mapping of Multi-Depth Soil Water Content Using UAV

DOI




Paper 3 — Random Forest Soil Moisture Estimation

DOI



References