Graduation Term

Spring 2026

Degree Name

Master of Science (MS)

Department

Department of Geography-Geology: Hydrogeology

Committee Chair

Wondwosen Seyoum

Committee Member

Eric Peterson

Committee Member

Jonathan Thayn

Abstract

In agricultural landscapes, soil moisture regulates hydrologic partitioning, nutrient transport and water quality, land-atmosphere energy exchange that shapes local climate, and ecosystem resilience. However, traditional monitoring approaches, such as in-situ sensors and satellite imagery, often lack the spatial resolution required to capture fine-scale soil moisture variability. This study evaluated whether unmanned aerial system (UAS)-derived thermal, multispectral, and terrain variables can capture fine-scale spatial variability in volumetric water content (VWC) within an SRB in central Illinois.

High-resolution imagery was collected and paired with 50 field-measured VWC observations. Land surface temperature (LST), vegetation indices (NDVI and NDRE), spectral bands, and slope were extracted from UAS imagery and used as predictors in ordinary least squares (OLS), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) models. Model performance was evaluated using repeated 5-fold cross-validation to estimate predictive accuracy on unseen observations.

The models were trained on 80% of the data, and the remaining 20% was used for testing. The training error metrics indicated a strong fit with R² values of 0.531 for OLS, 0.924 for RF, and 0.999 for XGBoost. The testing result showed that the RF model achieved better predictive performance (R² ≈ 0.21; RMSE = 0.07 m³/m³), modestly outperforming OLS and XGBoost. The SHAP (SHapley Additive exPlanations) analysis showed that land surface temperature was the most influential predictor, accounting for approximately 60% of total model importance, with warmer surface conditions associated with lower soil moisture.

These results demonstrate that integrating thermal and multispectral UAS imagery can capture fine-scale variability in soil moisture. The approach provides a spatially detailed method for monitoring soil hydrologic conditions. It highlights the potential of UAS-based remote sensing to support improved landscape-scale water management and ecological monitoring.

Access Type

Thesis-Open Access

Download

Share

COinS