Abstract
High-throughput phenotyping using high spatial, spectral, and temporal resolution remote sensing (RS) data has become a critical part of the plant breeding chain focused on reducing the time and cost of the selection process for the “best” genotypes with respect to the trait(s) of interest. In this paper, the potential of accurate and reliable sorghum biomass prediction using visible and near infrared (VNIR) and short-wave infrared (SWIR) hyperspectral data as well as light detection and ranging (LiDAR) data acquired by sensors mounted on UAV platforms is investigated. Predictive models are developed using classical regression-based machine learning methods for nine experiments conducted during the 2017 and 2018 growing seasons at the Agronomy Center for Research and Education (ACRE) at Purdue University, Indiana, USA. The impact of the regression method, data source, timing of RS and field-based biomass reference data acquisition, and the number of samples on the prediction results are investigated. R2 values for end-of-season biomass ranged from 0.64 to 0.89 for different experiments when features from all the data sources were included. Geometry-based features derived from the LiDAR point cloud to characterize plant structure and chemistry-based features extracted from hyperspectral data provided the most accurate predictions. Evaluation of the impact of the time of data acquisition during the growing season on the prediction results indicated that although the most accurate and reliable predictions of final biomass were achieved using remotely sensed data from mid-season to end-of-season, predictions in mid-season provided adequate results to differentiate between promising varieties for selection. The analysis of variance (ANOVA) of the accuracies of the predictive models showed that both the data source and regression method are important factors for a reliable prediction; however, the data source was more important with 69% significance, versus 28% significance for the regression method.
Highlights
Biomass yield is an important trait of biofuel crops such as sorghum, as it is a key factor in determining the amount of biofuel that can be produced
Remote sensing via unmanned aerial vehicles (UAV) is currently being investigated as a means to close the gap because of its capability to acquire the high temporal and spatial resolution data required for high throughput phenotyping over relatively limited areas
They concluded that partial least squares regression (PLSR) can provide more accurate predictions using the normalized difference vegetation index (NDVI) calculated from field spectrometer measurements collected in July
Summary
Biomass yield is an important trait of biofuel crops such as sorghum, as it is a key factor in determining the amount of biofuel that can be produced. Remotely sensed biomass prediction of varieties of sorghum is investigated using the data acquired by RGB, hyperspectral and LiDAR sensors mounted on UAV platforms. Many studies focus on developing enhanced genotypes that can produce more energy-rich plant material (biomass) [26] It is important for these breeding studies to predict the end-of-season yield biomass of the planted varieties as soon as possible in the growing season to screen varieties, and reduce investment of expensive resources in monitoring for the whole season. A small number of field reference samples relative to the number of features (and thereby potentially the number of parameters to estimate) is a difficult issue for remote sensing-based phenotyping. The objective is to develop baseline predictive models for sorghum biomass yield based on classical machine learning methods using multi-date remote sensing and ground reference data.
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
