Geospatial Image Data for Sorghum Phenotyping

Abstract

There is an urgent need to accelerate energy crop development for the production of renewable transportation fuels from biomass. Greater knowledge of factors that influence crop growth and development is required to improve the breeding development pipeline for energy crops. Genomics tools have advanced and the pace of genotyping has accelerated exponentially while the cost of sequencing has dramatically decreased. The bottleneck has thus shifted emphasis from understanding the genotype to understanding the phenotype. Recent technological advancements in remote sensing have made it possible to extract massive volumes of morphological, physiological, and agronomic data from bioenergy crops, but complexities in data processing, feature extraction, and data analytics make predictions of crop performance from remote sensing data a challenge. Plant phenotyping pipelines for measuring and predicting plant productivity and performance from remotely sensed data are needed. These may include both ground-based and airborne sensor platforms for high-throughput phenotyping. High-throughput phenotyping data can be matched with genetic data through complex analytics to enable optimization of sorghum for biomass and energy yield for transportation fuel. The purpose of this project was to develop a disruptive technology system based on airborne and ground-based mobile sensor systems, confirmed by handheld sensors and agronomic performance data that enables phenotyping of sorghum for biomass and energy yield for transportation fuel. We achieved the goals of the project with key successes in (1) optimizing high-throughput remote-sensing technologies to acquire relevant data on sorghum plant phenotypes, (2) implementation of data analytics algorithms for segmentation and feature extraction, (3) developing predictive models for plant growth and performance, and (4) designing and implementing genetic analysis pipelines to identify genes controlling sorghum performance; and (5) designing a user-friendly system platform to enable breeders and other end users to interact with the needed data and analytics. This data set is a sampling of the data collected for the Purdue TERRA project and is presented for use by others for research purposes. This publication includes: <ul> <li>RGB image data at 1 cm spatial resolution for 3 dates in 2018 (6/4, 7/10, & 8/1)</li> <li>Hyperspectral data at 4 cm spatial resolution for 3 dates in 2018 (6/4, 7/11, & 8/2)</li> <li>Lidar digital surface model (dsm) data for 3 dates in 2018 (6/4, 7/10, 8/1) in las formatted files</li> <li>Documentation <ul> <li>txt and csv files documenting the biomass, plant height, leaf appearance, and leaf area for each of the plots</li> <li>Esri shape and geojson vector files describing spatial outline of the plots within the experiment</li> <li>Esri shape and geojson vector files describing spatial outline of each of the rows with the plots</li> <li>Incidence radiation graphs for the image data sets dates summarizing the illumination variations during the day</li> </ul> </li> </ul> The information, data, or work presented herein was funded in part by the Advanced Research Projects Agency-Energy (ARPA-E), U.S. Department of Energy, under Award Number DE-AR0000593. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.

Abstract from the paper’s OpenAlex record; open copy licensed public-domain. Read at the source ↗

The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.