Self-supervised learning predicts plant growth trajectories from multi-modal industrial greenhouse data

TL;DR

This paper introduces a self-supervised learning method that uses multi-modal data from robotic sensors to predict plant growth trajectories, aiding crop management and research.

Contribution

It presents a novel self-supervised approach that maps observed plant data to full growth trajectories using robotic sensing in a large-scale hydroponic system.

Findings

Accurately forecasts future plant height and harvest mass.

Demonstrates effectiveness of robotic sensing combined with machine learning.

Provides actionable insights for agronomic research and crop management.

Abstract

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.