A Measurement-Driven Digital Twin Architecture for Plant-Level Biomass Estimation and Growth Forecasting in Hydroponic Systems

2026-06-01

AI Summary

This study addresses the challenges of real-time, accurate biomass estimation and unreliable growth trend prediction for individual plants in hydroponic systems. To this end, the authors propose a data-driven digital twin framework that uniquely integrates a custom-designed neural network with a dynamic plant growth model. Leveraging RGB-D image inputs, the approach enables non-invasive, continuous estimation of individual lettuce fresh weight through a novel neural network, while an online-updatable digital twin model facilitates short-term yield forecasting. Experimental results demonstrate that, after training on 1,300 images, the neural network achieves mass estimation errors below 1.5 grams. Furthermore, the integrated system predicts yields 1–4 days in advance with an average error of approximately 2 grams, significantly enhancing the accuracy and timeliness of monitoring and management in hydroponic crop production.

Abstract

Alternatives to soil-based horticulture, such as hydroponics, have been developed to respond to food distribution concerns for dense urban centers. A new system was developed to track an individual lettuce plant's growth in a hydroponic environment, utilizing streams of measured information and available models to continuously update the growth trajectory estimates for a plant. These "digital twin" models were integrated into an operating hydroponic greenhouse, with custom horticultural and sensor hardware to grow and measure relevant information. To aid in updating model parameters, plant yield was continuously measured with a custom neural network, using RGB-D images of the plants as an input. The network, trained on a collected dataset of 1300 images, was able to estimate mass within 1.5 g of the ground-truth value. After integration into the custom system, digital twin growth projections could approximate future yield between one and four days in the future, maintaining around a 2 g forecasting error.

Problem

• digital twin
• biomass estimation
• growth forecasting
• hydroponic systems
• plant-level monitoring

Innovation

• digital twin
• hydroponics
• RGB-D imaging
• neural network
• growth forecasting