EventsThe 10th International Electronic Conference on Water Sciences
Published
This submission belongs to the session S7. Remote Sensing, Artificial Intelligence, and New Technologies in Water Sciences of the event The 10th International Electronic Conference on Water Sciences
Published date
19 Nov, 2026
Academic Editor
author-avatarNikiforos Samarinas
Contribution&Funding
Conceptualization,
[Phathutshedzo Eugene Ratshiedana]
Methodology,
[Phathutshedzo Eugene Ratshiedana]
Software,
[Phathutshedzo Eugene Ratshiedana]
Validation,
[Phathutshedzo Eugene Ratshiedana]
Formal analysis,
[Phathutshedzo Eugene Ratshiedana]
Investigation,
[Phathutshedzo Eugene Ratshiedana]
Resources,
[Phathutshedzo Eugene Ratshiedana]
Data curation,
[Phathutshedzo Eugene Ratshiedana]
Writing - original draft,
[Phathutshedzo Eugene Ratshiedana]
Writing - review,
[editing] ; [Phathutshedzo Eugene Ratshiedana]
Visualization,
[Phathutshedzo Eugene Ratshiedana]
Supervision,
[Phathutshedzo Eugene Ratshiedana]
Project administration,
[Phathutshedzo Eugene Ratshiedana]
Funding acquisition,
[Phathutshedzo Eugene Ratshiedana]
Funding: --
Citation
Phathutshedzo Eugene Ratshiedana, High-resolution soil moisture variability detection using integrated unmanned aerial systems remote sensing and ground observations, in Proceedings of The 10th International Electronic Conference on Water Sciences, 24 November–27 November 2026, MDPI: Basel, Switzerland
Share
Email
Facebook
Twitter
LinkedIn

High-resolution soil moisture variability detection using integrated unmanned aerial systems remote sensing and ground observations

1. Geoinformation Sciences, Agricultural Research Council, Pretoria, 0083, South Africa
Abstract

Accurate and spatially representative soil‍ moisture information at high-resolution is important for environmental monitoring, wate⁠r resource management and⁠ sustainable agriculture in heterogeneous and water-scarcity areas. One of the biggest challenges in South African earth observation datasets is that existing satellite-based soil moisture products are limited by coarse‌ spatial resolution, while in situ measurements are costly and spatially scarce. This study presents a soil moisture retrieval framework that combines multispectral imagery with a stacked ensemble machine learning approach to‍ estimate field-scale surface so⁠il moisture in a smallholder irrigated maize farm. Unmanned Aerial⁠ Vehicle (UAV)‌ images were acquired across three‌ key crop phenological stages and a soil-line-based soil moisture⁠ index (SMI) derived from near-infrared an⁠d red reflectance was combined with spectral features to train multiple machine learning models. The models included linear regression, ridge regression, support vector machines, k-nearest neighbours, decision tree and random forest. A stacked ensemble model was developed to combine individual model capabilities and enhance predictive performance. Evaluation against in situ measurements‌ showed that the ensemble model outperformed other models with a coefficient of determination value (R²) of 0.93, Root Mean‍ Square Error (RMSE) of 0.96%, Mean Absolute Percentage Error (MAPE)⁠ of 1.90‍% and Explained Variance (EV) of 91.1⁠9%) compared to individual models and ND‍VI-based estimates⁠. The spatial distribution maps revealed persistent moisture gradients reflecting irrigation‌ patterns and⁠ field heterogeneity with highest so⁠il moisture at mid-development and lower levels at maturity due to canopy cover. This approach demonstrates the potential of UAV-based ensemble modelling‍ for precision water management and improved environmental monitoring in water-limited agricultural systems.

Keywords
soil moisture
NIR-red spectral space
unmanned aerial vehicle
remote sensing
machine learning
Streamflow estimation in ungauged basins through a morphometric and satellite-based approach 
SPIONs-laccase system: characterization and performance in the removal of endocrine disruptors from surface water