Abstract
Machine learning (ML) can accelerate biological research. However, the adoption of such tools to facilitate phenotyping based on sensor data has been limited by (i) the need for a large amount of human-annotated training data for each context in which the tool is used and (ii) phenotypes varying across contexts defined in terms of genetics and environment. This is a major bottleneck because acquiring training data is generally costly and time-consuming. This study demonstrates how a ML approach can address these challenges by minimizing the amount of human supervision needed for tool building. A case study was performed to compare ML approaches that examine images collected by an uncrewed aerial vehicle to determine the presence/absence of panicles (i.e. “heading”) across thousands of field plots containing genetically diverse breeding populations of 2 Miscanthus species. Automated analysis of aerial imagery enabled the identification of heading approximately 9 times faster than in-field visual inspection by humans. Leveraging an Efficiently Supervised Generative Adversarial Network (ESGAN) learning strategy reduced the requirement for human-annotated data by 1 to 2 orders of magnitude compared to traditional, fully supervised learning approaches. The ESGAN model learned the salient features of the data set by using thousands of unlabeled images
More>>
- Developers:
-
Varela, Sebastian ; Sacks, Erik [1] ; Leakey, Andrew [1]
- Univ. of Illinois at Urbana-Champaign, IL (United States)
- Release Date:
- 2025-04-23
- Project Type:
- Open Source, Publicly Available Repository
- Software Type:
- Scientific
- Licenses:
-
BSD 3-clause "New" or "Revised" License
- Sponsoring Org.:
-
USDOE Office of Science (SC), Biological and Environmental Research (BER)Primary Award/Contract Number:SC0018420
- Code ID:
- 169771
- Research Org.:
- Center for Advanced Bioenergy and Bioproduct Innovation
- Country of Origin:
- United States
Citation Formats
Varela, Sebastian, Sacks, Erik, and Leakey, Andrew.
pixelvar79/ESGAN-Flowering-Detection-paper.
Computer Software.
https://github.com/pixelvar79/ESGAN-Flowering-Detection-paper.
USDOE Office of Science (SC), Biological and Environmental Research (BER).
23 Apr. 2025.
Web.
doi:10.11578/dc.20251107.3.
Varela, Sebastian, Sacks, Erik, & Leakey, Andrew.
(2025, April 23).
pixelvar79/ESGAN-Flowering-Detection-paper.
[Computer software].
https://github.com/pixelvar79/ESGAN-Flowering-Detection-paper.
https://doi.org/10.11578/dc.20251107.3.
Varela, Sebastian, Sacks, Erik, and Leakey, Andrew.
"pixelvar79/ESGAN-Flowering-Detection-paper." Computer software.
April 23, 2025.
https://github.com/pixelvar79/ESGAN-Flowering-Detection-paper.
https://doi.org/10.11578/dc.20251107.3.
@misc{
doecode_169771,
title = {pixelvar79/ESGAN-Flowering-Detection-paper},
author = {Varela, Sebastian and Sacks, Erik and Leakey, Andrew},
abstractNote = {Machine learning (ML) can accelerate biological research. However, the adoption of such tools to facilitate phenotyping based on sensor data has been limited by (i) the need for a large amount of human-annotated training data for each context in which the tool is used and (ii) phenotypes varying across contexts defined in terms of genetics and environment. This is a major bottleneck because acquiring training data is generally costly and time-consuming. This study demonstrates how a ML approach can address these challenges by minimizing the amount of human supervision needed for tool building. A case study was performed to compare ML approaches that examine images collected by an uncrewed aerial vehicle to determine the presence/absence of panicles (i.e. “heading”) across thousands of field plots containing genetically diverse breeding populations of 2 Miscanthus species. Automated analysis of aerial imagery enabled the identification of heading approximately 9 times faster than in-field visual inspection by humans. Leveraging an Efficiently Supervised Generative Adversarial Network (ESGAN) learning strategy reduced the requirement for human-annotated data by 1 to 2 orders of magnitude compared to traditional, fully supervised learning approaches. The ESGAN model learned the salient features of the data set by using thousands of unlabeled images to inform the discriminative ability of a classifier so that it required minimal human-labeled training data. This method can accelerate the phenotyping of heading date as a measure of flowering time in Miscanthus across diverse contexts (e.g. in multistate trials) and opens avenues to promote the broad adoption of ML tools.},
doi = {10.11578/dc.20251107.3},
url = {https://doi.org/10.11578/dc.20251107.3},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20251107.3}},
year = {2025},
month = {apr}
}