Soil Moisture

Comparing UAV hyperspectral and satellite multispectral approaches

This project provides a comprehensive comparison of UAV-based hyperspectral and satellite-based multispectral data for soil moisture estimation using machine learning techniques, offering insights into the optimal remote sensing approach for precision agriculture.

Overview

Soil moisture is a critical variable in agriculture, hydrology, and environmental monitoring. Accurate soil moisture estimation enables optimized irrigation management, improved crop yield predictions, and better understanding of hydrological processes. Remote sensing offers a non-destructive, spatially-explicit approach to soil moisture monitoring, but the choice between different platforms and sensors significantly impacts accuracy and operational feasibility.

Research Objectives

This study compares two distinct remote sensing approaches for soil moisture estimation:

UAV-Based Hyperspectral Imaging: High spatial resolution, detailed spectral information, but limited spatial coverage
Satellite-Based Multispectral Imaging: Large spatial coverage, lower spectral resolution, freely available data

The comparison aims to determine which approach provides superior soil moisture estimation accuracy and identify the optimal trade-offs between spatial resolution, spectral detail, and operational constraints.

Methodology

Data Acquisition Campaign

The study involved extensive field data collection campaigns conducted over 14 different dates from September 2021 to January 2023. This multi-temporal approach ensured capture of diverse soil moisture conditions across seasons and weather patterns.

Used Data

1. Satellite Multispectral Data:

Sentinel-2: 10-20 m spatial resolution
Landsat-8/9: 30 m spatial resolution

2. UAV Hyperspectral Data Acquisition:

The aerial data of the region were captured by mounting the CoSpectroCam sensor on a DJI Matrice 100 UAV. The CoSpectroCam is an advanced optical coaxial system that combines an RGB camera with a spectrometer, providing both high-resolution imagery and detailed spectral information.

CoSpectroCam Specifications:

RGB Camera: 700 × 800 pixels resolution
Spectrometer: High spectral resolution of 0.35 nm
Spectral Range: 339.6 nm to 1028.8 nm
Spectral Bands: 2048 bands covering UV to near-infrared

Key Advantages:

High spatial resolution imagery
Captures subtle variations in soil properties
Flexible acquisition timing
Detailed spectral information across 2048 bands

(a) DJI Matrice 100 UAV equipped with CoSpectroCam and RGB sensors, (b) CoSpectroCam sensor, and (c) RGB camera used for high-resolution imaging.

Modelling

We employed several machine learning algorithms to establish relationships between spectral signatures and soil moisture content:

Performance Comparison

The Taylor diagram below illustrates the comprehensive performance comparison of soil moisture estimation models developed using three different remote sensing data sources: Sentinel-2, Landsat-8/9, and UAV hyperspectral data.

Taylor diagram illustrating the performance of soil moisture estimation models developed using Sentinel-2, Landsat-8/9, and UAV hyperspectral data. The diagram shows correlation, standard deviation, and root-mean-square error for each approach.

Applications

Precision Agriculture

Hydrological Modeling

Environmental Monitoring

Research and Development

Future Directions

Integration of UAV and satellite data through multi-sensor fusion
Extension to other soil properties (organic matter, texture)

(Shokati et al., 2025)

(Shokati et al., 2024)

(Shokati et al., 2023)

References

2025

Water
Comparing UAV-Based Hyperspectral and Satellite-Based Multispectral Data for Soil Moisture Estimation Using Machine Learning

H. Shokati, M. Mashal, A. Noroozi, and 8 more authors

Water, 2025

Abs DOI Bib HTML

Accurate estimation of soil moisture content (SMC) is crucial for effective water management, enabling improved monitoring of water stress and a deeper understanding of hydrological processes. While satellite remote sensing provides broad coverage, its spatial resolution often limits its ability to capture small-scale variations in SMC, especially in landscapes with diverse land-cover types. Unmanned aerial vehicles (UAVs) equipped with hyperspectral sensors offer a promising solution to overcome this limitation. This study compares the effectiveness of Sentinel-2, Landsat-8/9 multispectral data and UAV hyperspectral data (from 339.6 nm to 1028.8 nm with spectral bands) in estimating SMC in a research farm consisting of bare soil, cropland and grassland. A DJI Matrice 100 UAV equipped with a hyperspectral spectrometer collected data on 14 field campaigns, synchronized with satellite overflights. Five machine-learning algorithms including extreme learning machines (ELMs), Gaussian process regression (GPR), partial least squares regression (PLSR), support vector regression (SVR) and artificial neural network (ANN) were used to estimate SMC, focusing on the influence of land cover on the accuracy of SMC estimation. The findings indicated that GPR outperformed the other models when using Landsat-8/9 and hyperspectral photography data, demonstrating a tight correlation with the observed SMC (R2 = 0.64 and 0.89, respectively). For Sentinel-2 data, ELM showed the highest correlation, with an R2 value of 0.46. In addition, a comparative analysis showed that the UAV hyperspectral data outperformed both satellite sources due to better spatial and spectral resolution. In addition, the Landsat-8/9 data outperformed the Sentinel-2 data in terms of SMC estimation accuracy. For the different land-cover types, all types of remote-sensing data showed the highest accuracy for bare soil compared to cropland and grassland. This research highlights the potential of integrating UAV-based spectroscopy and machine-learning techniques as complementary tools to satellite platforms for precise SMC monitoring. The findings contribute to the further development of remote-sensing methods and improve the understanding of SMC dynamics in heterogeneous landscapes, with significant implications for precision agriculture. By enhancing the SMC estimation accuracy at high spatial resolution, this approach can optimize irrigation practices, improve cropping strategies and contribute to sustainable agricultural practices, ultimately enabling better decision-making for farmers and land managers. However, its broader applicability depends on factors such as scalability and performance under different conditions.
@article{shokati2025soilmoisture, title = {Comparing UAV-Based Hyperspectral and Satellite-Based Multispectral Data for Soil Moisture Estimation Using Machine Learning}, author = {Shokati, H. and Mashal, M. and Noroozi, A. and Mirzaei, S. and Mohammadi-Doqozloo, Z. and Nabiollahi, K. and Taghizadeh-Mehrjardi, R. and Khosravani, P. and Adhikari, R. and Hu, L. and Scholten, T.}, journal = {Water}, volume = {17}, pages = {1715}, year = {2025}, publisher = {MDPI}, doi = {10.3390/w17111715}, }

2024

Rem. Sens.
Random Forest-Based Soil Moisture Estimation Using Sentinel-2, Landsat-8/9, and UAV-Based Hyperspectral Data

H. Shokati, M. Mashal, A. Noroozi, and 7 more authors

Remote Sensing, 2024

Abs DOI Bib HTML

Accurate spatiotemporal monitoring and modeling of soil moisture (SM) is of paramount importance for various applications ranging from food production to climate change adaptation. This study deals with modeling SM with the random forest (RF) algorithm using datasets comprising multispectral data from Sentinel-2, Landsat-8/9, and hyperspectral data from the CoSpectroCam sensor (CSC, licensed to AgriWatch BV, Enschede, The Netherlands) mounted on an unmanned aerial vehicle (UAV) in Iran. The model included nine bands from Landsat-8/9, 11 bands from Sentinel-2, and 1252 bands from the CSC (covering the wavelength range between 420 and 850 nm). The relative feature importance and band sensitivity to SM variations were analyzed. In addition, four indices, including the perpendicular index (PI), ratio index (RI), difference index (DI), and normalized difference index (NDI) were calculated from the different bands of the datasets, and their sensitivity to SM was evaluated. The results showed that the PI exhibited the highest sensitivity to SM changes in all datasets among the four indices considered. Comparisons of the performance of the datasets in SM estimation emphasized the superior performance of the UAV hyperspectral data (R2 = 0.87), while the Sentinel-2 and Landsat-8/9 data showed lower accuracy (R2 = 0.49 and 0.66, respectively). The robust performance of the CSC data is likely due to its superior spatial and spectral resolution as well as the application of preprocessing techniques such as noise reduction and smoothing filters. The lower accuracy of the multispectral data from Sentinel-2 and Landsat-8/9 can also be attributed to their relatively coarse spatial resolution compared to the CSC, which leads to pixel non-uniformities and impurities. Therefore, employing the CSC on a UAV proves to be a valuable technology, providing an effective link between satellite observations and ground measurements.
@article{shokati2024randomforest, title = {Random Forest-Based Soil Moisture Estimation Using Sentinel-2, Landsat-8/9, and UAV-Based Hyperspectral Data}, author = {Shokati, H. and Mashal, M. and Noroozi, A. and Abkar, A.A. and Mirzaei, S. and Mohammadi-Doqozloo, Z. and Taghizadeh, R. and Khosravani, P. and Nabiollahi, K. and Scholten, T.}, journal = {Remote Sensing}, volume = {16}, number = {11}, pages = {1962}, year = {2024}, publisher = {MDPI}, doi = {10.3390/rs16111962}, }

2023

RSASE
Assessing soil moisture levels using visible UAV imagery and machine learning models

H. Shokati, M. Mashal, A. Noroozi, and 2 more authors

Remote Sensing Applications: Society and Environment, 2023

Abs DOI Bib HTML

The estimation of soil moisture (SM) as an important variable in the hydrological cycle of nature is necessary for the optimal management of water and soil resources. One of the indirect methods to estimate SM is using visible imagery with unmanned aerial vehicles (UAVs). This study aims to evaluate the potential of visible UAV imagery for estimating SM in a bare soil field in Iran. In this study, M5 tree (M5P), random forest (RF), sequential minimal optimization regression (SMOreg), and multilayer perceptron (MLP) methods have been used for SM modeling from RGB (Red, Green and Blue) bands and brightness and intensity indices of aerial imagery. Three evaluation methods were used to assess the accuracy of the models, including the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). Four different indices, including difference index (DI), ratio index (RI), normalized difference index (NDI), and perpendicular index (PI), were used to estimate SM. The green and red bands pair were found to be the optimal bands for SM estimation. The findings showed that the PI index provided the most accurate SM estimates (R2 = 0.51). The RF model predicted SM most accurately among the machine learning models tested (R2 = 0.67). However, all models underestimated SM content in high-moisture areas and overestimated it in low-moisture areas, with the MLP model showing the most significant overestimation. All the indices were saturated beyond 25% SM. In general, this study highlighted the potential of aerial RGB imagery and associated indices for assessing SM levels within bare soil fields. However, it should be noted that the use of individual bands and indices alone is not sufficient to make an accurate estimate of SM.
@article{shokati2023uavimagery, title = {Assessing soil moisture levels using visible UAV imagery and machine learning models}, author = {Shokati, H. and Mashal, M. and Noroozi, A. and Mirzaei, S. and Mohammadi-Doqozloo, Z.}, journal = {Remote Sensing Applications: Society and Environment}, volume = {32}, pages = {101076}, year = {2023}, publisher = {Elsevier}, doi = {10.1016/j.rsase.2023.101076}, }