Modeling of Biofuel Plants Phenotyping and Biomass

Dear Colleagues,

Several perennial and annual crops have been considered as leading candidates for bioenergy production. The favorable traits, such as high biomass production, wide adaptation, and low agronomic input requirements, are highly associated with a desirable bioenergy feedstock. Increased productivity and sustainability of plant feedstocks in bioenergy crops are key factors for biofuel production. Factors affecting plant quality and performance can be broadly attributed to plant genetics and the growing environment. However, phenotyping resources have created a bottleneck in biofuel crop improvement and breeding. Advances in developing high-throughput phenotyping tools and techniques are essential for characterizing aboveground and belowground phenes to achieve sustainable growth of biofuel crops. Moreover, novel high-throughput approaches are needed to better understand the association between genotypes and phenotypes and to accelerate plant breeding. Research on this topic is important to fight against climate/ecosystem changes, leading to climate-smart or eco-efficient agriculture. 

We encourage original research, methods, and review articles to address the broad range of topics from a data-driven approach, including, but not limited to:

• Perspectives of biofuel plant phenomics;
• Big data challenges for genomics and phenotyping data;
• High-throughput phenotyping: tools and techniques for assessment;
• Genomic selection in biofuel crops: Benefits of high throughput phenotyping;
• Precision agriculture association with high throughput biofuel plant phenotyping;
• Biomass quantity/quality assessment;
• Biotic/abiotic stress assessment;
• Sustainability trait assessment.

Dr. Yaping Xu
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Plants is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• biofuel
• bioenergy
• biomass
• phenotyping
• phenomics
• AI and machine learning
• image analysis

Title: Tiller Nitrogen Content Modeling of Field-Grown Switchgrass (Panicum virgatum) with UAV Muitispecrral Datasets and Machine Learning
Authors: Yaping Xu1,2,4, Reginald J. Millwood1,2, Vivek Shrestha1,2, Lance Hamilton1,2, Benjamin Wolfe1,2, Cristiano Piaseck1,2, Mitra Mazarei1,2,3, C. Neal Stewart Jr. 1,2
Affiliation: 1Department of Plant Sciences, University of Tennessee, Knoxville, Tennessee 37996; 2Center for Bioenergy Innovation, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37830; 3Center for Agricultural Synthetic Biology, University of Tennessee, Knoxville, Tennessee 37996; 4Deptment of Environmental and Geosciences, Sam Houston State University, Huntsville, Texas 77340
Abstract: High-throughput phenotyping is in high demand for field-grown crops due to time- and resource-savings offered over labor-intensive conventional phenotyping methods. Previously, we utilized a common garden switchgrass (Panicum virgatum L.) field experiment to demonstrate the feasibility of phenotyping with UAV-based multispectral sensors. However, challenges remain for high-throughput tiller nitrogen content modelin. Here, we outline an analytical approach that utilizes UAV-based multispectral data and artificial intelligence/machine learning for improved nitrogen estimation in switchgrass. High-resolution imagery were collected in the air, then processed with professional image processing software, and analyzed with R and Python packages to leverage the spectral information associated with tiller nitrogen content and rust disease from these datasets. As a result, we used random forests and Cubist model, two machine learning algorithms to successfully model nitrogen content in switchgrass. The modeling results show a five-fold increase in the accuracy as compared with conventioal regression-based models. We expect these analytical approaches to significantly improve data analysis for nitrogen content modeling in switchgrass as well as boost the application of UAV-collected data for precision agriculture.