Self-supervised learning predicts plant growth trajectories from multi-modal industrial greenhouse data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915378948472832 |
|---|---|
| author | Riesselman, Adam J Cofer, Evan M LaRue, Therese Meeussen, Wim |
| author_facet | Riesselman, Adam J Cofer, Evan M LaRue, Therese Meeussen, Wim |
| contents | Quantifying organism-level phenotypes, such as growth dynamics and biomass accumulation, is fundamental to understanding agronomic traits and optimizing crop production. However, quality growing data of plants at scale is difficult to generate. Here we use a mobile robotic platform to capture high-resolution environmental sensing and phenotyping measurements of a large-scale hydroponic leafy greens system. We describe a self-supervised modeling approach to build a map from observed growing data to the entire plant growth trajectory. We demonstrate our approach by forecasting future plant height and harvest mass of crops in this system. This approach represents a significant advance in combining robotic automation and machine learning, as well as providing actionable insights for agronomic research and operational efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_06336 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-supervised learning predicts plant growth trajectories from multi-modal industrial greenhouse data Riesselman, Adam J Cofer, Evan M LaRue, Therese Meeussen, Wim Quantitative Methods Machine Learning Robotics Quantifying organism-level phenotypes, such as growth dynamics and biomass accumulation, is fundamental to understanding agronomic traits and optimizing crop production. However, quality growing data of plants at scale is difficult to generate. Here we use a mobile robotic platform to capture high-resolution environmental sensing and phenotyping measurements of a large-scale hydroponic leafy greens system. We describe a self-supervised modeling approach to build a map from observed growing data to the entire plant growth trajectory. We demonstrate our approach by forecasting future plant height and harvest mass of crops in this system. This approach represents a significant advance in combining robotic automation and machine learning, as well as providing actionable insights for agronomic research and operational efficiency. |
| title | Self-supervised learning predicts plant growth trajectories from multi-modal industrial greenhouse data |
| topic | Quantitative Methods Machine Learning Robotics |
| url | https://arxiv.org/abs/2507.06336 |