Skip to main content
ARS Home » Plains Area » Lubbock, Texas » Cropping Systems Research Laboratory » Plant Stress and Germplasm Development Research » Research » Publications at this Location » Publication #388422

Research Project: Development of Economically Important Row Crops that Improve the Resilience of U.S. Agricultural Production to Present and Future Production Challenges

Location: Plant Stress and Germplasm Development Research

Title: Thresholding analysis and feature extraction from 3D ground penetrating radar data for noninvasive assessment of peanut yield

item DOBREVA, ILIYANA - Texas A&M University
item RUIZ-GUZMAN, HENRY - Texas A&M University
item BARRIOS-PEREZ, ILSE - Texas A&M University
item ADAMS, TYLER - Texas A&M University
item TEARE, BRODY - Texas A&M University
item Payton, Paxton
item EVERETT, MARK - Texas A&M University
item BUROW, MARK - Texas A&M University
item HAYES, DIRK - Texas A&M University

Submitted to: Remote Sensing
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/5/2021
Publication Date: 5/12/2021
Citation: Dobreva, I., Ruiz-Guzman, H., Barrios-Perez, I., Adams, T., Teare, B., Payton, P.R., Everett, M., Burow, M., Hayes, D. 2021. Thresholding analysis and feature extraction from 3D ground penetrating radar data for noninvasive assessment of peanut yield. Remote Sensing. 13(10).

Interpretive Summary: Peanut is an important oilseed, feed, and food crop grown in tropical, subtropical, and semi-arid regions. Peanut pods containing the seed and shell develop underground limiting peanut yield assessment to point sampling and post-harvest measurements. This means that only a limited number of plants are sampled to assess peanut yield in a trial that may consist of hundreds of plants, and that a peanut plant must be harvested in order to assess its yield. Remote sensing offers a suite of technologies for rapid observation of plant types over large areas, which is also referred to as high-throughput phenotyping. Scientists at Lubbock and College Station, Texas used a new technology call ground penetrating radar to quantify peanut development and yield prior to harvest. This work has established a method for non-invasive growth and development as well as pre-harvest yield analysis for peanut breeding plots in the field. The use of this technology can significantly enhance peanut breeding and may be applicable to other crops for examining below-ground processes that impact yield.

Technical Abstract: This study explores the efficacy of utilizing a novel ground penetrating radar (GPR) acquisition platform and data analysis methods to quantify peanut yield for breeding selection, agronomic research, and producer management and harvest applications. Sixty plots comprising different peanut market types were scanned with a multichannel, air-launched GPR antenna. Image thresholding analysis was performed on 3D GPR data from four of the channels to extract features that were correlated to peanut yield with the objective of developing a noninvasive high-throughput peanut phenotyping and yield-monitoring methodology. Plot-level GPR data were summarized using mean, standard deviation, sum, and the number of nonzero values (counts) below or above different percentile threshold values. Best results were obtained for data below the percentile threshold for mean, standard deviation and sum. Data both below and above the percentile threshold generated good correlations for count. Correlating individual GPR features to yield generated correlations of up to 39% explained variability, while combining GPR features in multiple linear regression models generated up to 51% explained variability. The correlations increased when regression models were developed separately for each peanut type. This research demonstrates that a systematic search of thresholding range, analysis window size, and data summary statistics is necessary for successful application of this type of analysis. The results also establish that thresholding analysis of GPR data is an appropriate methodology for noninvasive assessment of peanut yield, which could be further developed for high-throughput phenotyping and yield-monitoring, adding a new sensor and new capabilities to the growing set of digital agriculture technologies.