Integrating data from unmanned aerial vehicles and Sentinel-2 with PROSAIL-5D-driven machine learning for fuel moisture content estimation in agroecosystems
1
Issued Date
2025-11-01
Resource Type
ISSN
15749541
Scopus ID
2-s2.0-105013567849
Journal Title
Ecological Informatics
Volume
91
Rights Holder(s)
SCOPUS
Bibliographic Citation
Ecological Informatics Vol.91 (2025)
Suggested Citation
Liu J., Jin J., Huang J., Wu M., Hao S., Jia H., Qin T., Huang Y., Chen D., Pumijumnong N. Integrating data from unmanned aerial vehicles and Sentinel-2 with PROSAIL-5D-driven machine learning for fuel moisture content estimation in agroecosystems. Ecological Informatics Vol.91 (2025). doi:10.1016/j.ecoinf.2025.103389 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/111825
Title
Integrating data from unmanned aerial vehicles and Sentinel-2 with PROSAIL-5D-driven machine learning for fuel moisture content estimation in agroecosystems
Corresponding Author(s)
Other Contributor(s)
Abstract
Fuel moisture content (FMC) is a critical ecological indicator for evaluating vegetation water status and ecosystem resilience, particularly in agricultural ecosystems. This study presents an advanced framework integrating multi-source remote sensing data fusion, physically based modeling, and machine learning to enable high-resolution and high-precision FMC estimation. An additive wavelet transform (AWT) was employed to fuse unmanned aerial vehicle (UAV) multispectral imagery with Sentinel-2 data, generating enhanced spatial-spectral reflectance composites while retaining key shortwave infrared bands essential for moisture analysis. To address the challenge of sparse ground observations, a calibrated PROSAIL-5D radiative transfer model was used to simulate diverse spectral responses, augmenting the training dataset. A genetic algorithm-optimized backpropagation neural network was then applied to assess the effectiveness of the fused remote sensing data and PROSAIL-5D simulation in improving FMC retrieval accuracy. The results indicate: (1) The AWT fusion method effectively integrates UAV and Sentinel-2 data, improving spatial and spectral consistency with field measurements. (2) Calibration of the PROSAIL-5D model significantly improves the retrieval accuracy of equivalent water thickness (Cw, R<sup>2</sup> = 0.847) and dry matter content (Cm, R<sup>2</sup> = 0.735), both key parameters for FMC calculation. (3) Incorporating 70 % of the measured spectral data (UAV and fused Sentinel-2) into the PROSAIL-5D simulated dataset enhanced FMC estimation accuracy (R<sup>2</sup> = 0.765), representing a 133.94 % improvement compared with using UAV data alone. This study demonstrates the potential of data fusion and physically based modeling for enhancing vegetation moisture monitoring in agroecosystems. This approach contributes to ecological informatics by offering a scalable, transferable solution for remote sensing-based analysis of ecosystem water status.