Machine Learning for Plant Phenotyping in Wheat

Dear Colleagues,

In recent years, the integration of automation control and optical sensing technologies has led to the development of various high-throughput, non-destructive phenotyping platforms, including handheld, gantry, and drone-based systems for both indoor and outdoor applications. These advancements have established a multi-scale, comprehensive plant temporal phenotyping framework, spanning from above- to below-ground, from morphological to physiological, and from macroscopic to microscopic levels. These significantly improve data collection efficiency and precision, while also causing an explosion in phenotypic data.

As one of the most critical food crops, wheat’s precise phenotyping is crucial for genetic improvement and high-yield cultivation. Researchers have amassed vast wheat 2D images (visible light, multispectral/hyperspectral, thermal infrared, and chlorophyll fluorescence) and 3D point cloud data, which urgently require in-depth exploration. Machine learning (ML) and its subfield, deep learning (DL), have played pivotal roles in processing complex data, thereby providing powerful tools for efficient, accurate, and automated analysis of large-scale phenotypic datasets. Therefore, this Special Issue aims to explore and showcase the latest research progress, methodologies, and applications of ML in wheat phenotyping studies, focusing on advancements that improving wheat genetic breeding and high-efficiency production management. Topics include, but are not limited to, the application of ML and DL techniques in the following:

• Micro-scale phenotypic trait analysis: e.g., morphology of stomata, starch granules, and other physiological micro-indicators.
• Organ-scale phenotypic trait analysis: e.g., seed, root, stem, leaf, and spike.
• Individual-scale phenotypic trait analysis: e.g., plant architecture and phenological stages.
• Population-scale phenotypic trait analysis: e.g., uniformity and yield.
• Applications in analyzing other critical 2D and 3D wheat phenotypic traits.
• Development of predictive/estimation models for key wheat phenotypic traits.
• Genotype–phenotype associations: Integration of ML with genomic data to predict phenotypic outcomes, thereby supporting marker-assisted breeding and genomic selection.

We look forward to receiving your contributions.

Dr. Qing Li
Prof. Dr. Ping Liu
Guest Editors

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.

• machine learning
• deep learning
• multi-scale phenotype
• multi-data analysis
• modeling