Abstract
Traditional methods to measure spatio-temporal variations in biomass rely on a labor-intensive destructive sampling of the crop. In this paper, we present a high-throughput phenotyping approach for the estimation of Above-Ground Biomass Dynamics (AGBD) using an unmanned aerial system. Multispectral imagery was acquired and processed by using the proposed segmentation method called GFKuts, that optimally labels the plot canopy based on a Gaussian mixture model, a Montecarlo based K-means, and a guided image filtering. Accurate plot segmentation results enabled the extraction of several canopy features associated with biomass yield. Machine learning algorithms were trained to estimate the AGBD according to the growth stages of the crop and the physiological response of two rice genotypes under lowland and upland production systems. Results report AGBD estimation correlations with an average of r = 0.95 and R2 = 0.91 according to the experimental data. We compared our segmentation method against a traditional technique based on clustering. A comprehensive improvement of 13% in the biomass correlation was obtained thanks to the segmentation method proposed herein.
Highlights
Accurate and precise high-throughput phenotyping platforms are necessary to enable highresolution linkage mapping for training genomic selection models in plant improvement [1, 2]
These metrics are compared against traditional image segmentation methods such as Thresholding [41] and K-means [42], and against the original GrabCut method [33]
We used Artificial Neural Networks (ANN) with one hidden layer composed by 15 neurons and the Levenberg-Marquardt non-linear training function. This configuration was selected according to the findings previously reported in [29], where strong non-linear dependencies between the vegetation indices with the biomass variations were found through the phenological cycle, concretely, when the rice plants began to senesce, making the yellow color of the plants predominant
Summary
Accurate and precise high-throughput phenotyping platforms are necessary to enable highresolution linkage mapping for training genomic selection models in plant improvement [1, 2]. Several morphological and physiological characteristics require spatio-temporal precise measurement for that purpose. Biomass is a key variable for quantifying grain yield and assessing crop health status. To overcome the limitations of traditional destructive methods for biomass sampling, above-ground methods to capture several canopy traits have gained traction.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
