Utilizing Spectral, Structural and Textural Features for Estimating Oat Above-Ground Biomass Using UAV-Based Multispectral Data and Machine Learning

Rakshya Dhakal; Maitiniyazi Maimaitijiang; Jiyul Chang; Melanie Caffe

doi:10.3390/s23249708

Utilizing Spectral, Structural and Textural Features for Estimating Oat Above-Ground Biomass Using UAV-Based Multispectral Data and Machine Learning

Sensors (Basel). 2023 Dec 8;23(24):9708. doi: 10.3390/s23249708.

Authors

Rakshya Dhakal¹, Maitiniyazi Maimaitijiang², Jiyul Chang³, Melanie Caffe³

Affiliations

¹ Plant Breeding Graduate Program, University of Florida, Gainesville, FL 32608, USA.
² Department of Geography and Geospatial Sciences, South Dakota State University, Brookings, SD 57007, USA.
³ Department of Agronomy, Horticulture and Plant Science, South Dakota State University, Brookings, SD 57007, USA.

Abstract

Accurate and timely monitoring of biomass in breeding nurseries is essential for evaluating plant performance and selecting superior genotypes. Traditional methods for phenotyping above-ground biomass in field conditions requires significant time, cost, and labor. Unmanned Aerial Vehicles (UAVs) offer a rapid and non-destructive approach for phenotyping multiple field plots at a low cost. While Vegetation Indices (VIs) extracted from remote sensing imagery have been widely employed for biomass estimation, they mainly capture spectral information and disregard the 3D canopy structure and spatial pixel relationships. Addressing these limitations, this study, conducted in 2020 and 2021, aimed to explore the potential of integrating UAV multispectral imagery-derived canopy spectral, structural, and textural features with machine learning algorithms for accurate oat biomass estimation. Six oat genotypes planted at two seeding rates were evaluated in two South Dakota locations at multiple growth stages. Plot-level canopy spectral, structural, and textural features were extracted from the multispectral imagery and used as input variables for three machine learning models: Partial Least Squares Regression (PLSR), Support Vector Regression (SVR), and Random Forest Regression (RFR). The results showed that (1) in addition to canopy spectral features, canopy structural and textural features are also important indicators for oat biomass estimation; (2) combining spectral, structural, and textural features significantly improved biomass estimation accuracy over using a single feature type; (3) machine learning algorithms showed good predictive ability with slightly better estimation accuracy shown by RFR (R² = 0.926 and relative root mean square error (RMSE%) = 15.97%). This study demonstrated the benefits of UAV imagery-based multi-feature fusion using machine learning for above-ground biomass estimation in oat breeding nurseries, holding promise for enhancing the efficiency of oat breeding through UAV-based phenotyping and crop management practices.

Keywords: UAV; biomass; machine learning; multispectral imagery; oat; remote sensing.

MeSH terms

Avena*
Biomass
Machine Learning
Plant Breeding
Remote Sensing Technology* / methods

Grants and funding

This research was supported by South Dakota Crop Improvement Association, the South Dakota Agricultural Experiment Station, and the USDA NIFA under hatch project (project number SD00H529-14).