RootNav 2.0: Deep learning for automatic navigation of complex plant root architectures
- Submitting institution
-
University of Nottingham, The
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 3747893
- Type
- D - Journal article
- DOI
-
10.1093/gigascience/giz123
- Title of journal
- GigaScience
- Article number
- giz123
- First page
- -
- Volume
- 8
- Issue
- 11
- ISSN
- 2047-217X
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
5
- Research group(s)
-
-
- Citation count
- 9
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Plant root system structures are commonly examined in order to identify crops that are e.g. drought tolerant in the face of global climate change. This paper offers a new deep-learning based approach to extracting root architectures from images. The work is unique in this field in that it uses modern deep learning in combination with traditional bottom-up path finding to extract root architectures. Unlike previous works, the approach offers high accuracy while remaining entirely automated. This enables large-scale genomic studies to be conducted, of high importance in modern plant science.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
