---
code_id: 169771
site_ownership_code: "CONTR"
open_source: true
repository_link: "https://github.com/pixelvar79/ESGAN-Flowering-Detection-paper"
project_type: "OS"
software_type: "S"
official_use_only: {}
developers:
- email: "sebavar79@gmail.com"
  orcid: ""
  first_name: "Sebastian"
  last_name: "Varela"
  middle_name: ""
  affiliations: []
- email: ""
  orcid: ""
  first_name: "Erik"
  last_name: "Sacks"
  middle_name: ""
  affiliations:
  - "Univ. of Illinois at Urbana-Champaign, IL (United States)"
- email: ""
  orcid: ""
  first_name: "Andrew"
  last_name: "Leakey"
  middle_name: ""
  affiliations:
  - "Univ. of Illinois at Urbana-Champaign, IL (United States)"
contributors: []
sponsoring_organizations:
- organization_name: "USDOE Office of Science (SC), Biological and Environmental Research\
    \ (BER)"
  funding_identifiers: []
  primary_award: "SC0018420"
  DOE: true
contributing_organizations: []
research_organizations:
- organization_name: "Center for Advanced Bioenergy and Bioproduct Innovation"
  DOE: true
related_identifiers: []
award_dois: []
release_date: "2025-04-23"
software_title: "pixelvar79/ESGAN-Flowering-Detection-paper"
acronym: "ESGAN-Flowering-Detection-paper"
doi: "https://doi.org/10.11578/dc.20251107.3"
description: "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."
programming_languages: []
country_of_origin: "United States"
project_keywords: []
licenses:
- "BSD 3-clause \"New\" or \"Revised\" License"
recipient_org: "CABBI"
date_record_added: "2025-11-07"
date_record_updated: "2025-11-07"
is_file_certified: false
last_editor: "krhodges@illinois.edu"
is_limited: false
links:
- rel: "citation"
  href: "https://www.osti.gov/doecode/biblio/169771"