UAV- and Random-Forest-AdaBoost (RFA)-Based Estimation of Rice Plant Traits

• Main Authors: Farrah Melissa Muharam, Khairudin Nurulhuda, Zed Zulkafli, Mohamad Arif Tarmizi, Asniyani Nur Haidar Abdullah, Muhamad Faiz Che Hashim, Siti Najja Mohd Zad, Derraz Radhwane, Mohd Razi Ismail
• Format: Article
• Language: English
• Published: MDPI AG 2021-05-01
• Series: Agronomy
• Subjects: rice; phenotyping; multispectral images; machine learning; boosting algorithm
• Online Access: https://www.mdpi.com/2073-4395/11/5/915

Rapid, accurate and inexpensive methods are required to analyze plant traits throughout all crop growth stages for plant phenotyping. Few studies have comprehensively evaluated plant traits from multispectral cameras onboard UAV platforms. Additionally, machine learning algorithms tend to over- or underfit data and limited attention has been paid to optimizing their performance through an ensemble learning approach. This study aims to (1) comprehensively evaluate twelve rice plant traits estimated from aerial unmanned vehicle (UAV)-based multispectral images and (2) introduce Random Forest AdaBoost (RFA) algorithms as an optimization approach for estimating plant traits. The approach was tested based on a farmer’s field in Terengganu, Malaysia, for the off-season from February to June 2018, involving five rice cultivars and three nitrogen (N) rates. Four bands, thirteen indices and Random Forest-AdaBoost (RFA) regression models were evaluated against the twelve plant traits according to the growth stages. Among the plant traits, plant height, green leaf and storage organ biomass, and foliar nitrogen (N) content were estimated well, with a coefficient of determination (R²) above 0.80. In comparing the bands and indices, red, Normalized Difference Vegetation Index (NDVI), Ratio Vegetation Index (RVI), Red-Edge Wide Dynamic Range Vegetation Index (REWDRVI) and Red-Edge Soil Adjusted Vegetation Index (RESAVI) were remarkable in estimating all plant traits at tillering, booting and milking stages with R² values ranging from 0.80–0.99 and root mean square error (RMSE) values ranging from 0.04–0.22. Milking was found to be the best growth stage to conduct estimations of plant traits. In summary, our findings demonstrate that an ensemble learning approach can improve the accuracy as well as reduce under/overfitting in plant phenotyping algorithms.