DIRTNet: Enabling Root Phenotyping with Fiber Bragg Grating Sensors
- 1University of Arizona
Abstract
Non-destructive methods for real-time phenotyping of root growth and development are essential to accelerate the breeding of climate-resilient crops. We present DIRTNet (Digital Investigations of Root Traits Net), a hybrid deep learning model that interprets in-soil signals collected by Fiber Bragg Grating (FBG) sensors. We first evaluated DIRTNet in a controlled simulation study in which metal rods of varying diameters were inserted into soil to emulate root growth. Using augmented training data with an 80:20 train-test split, DIRTNet surpassed baseline models, achieving 0.97 accuracy for root depth prediction and 0.94 for root diameter prediction. We then applied the best-performing models to maize (Zea mays) roots monitored by six FBG sensors placed at different soil location and depths. A control trial and a drought-stress trial yielded 192 samples, split 80:20 into training and holdout sets; the hold-out portion was divided equally into validation and test sets. Augmentation was applied only to the training data. On real maize root data, DIRTNet achieved 0.92 accuracy for both root depth and root width prediction across variable growth periods, covering root mass lengths up to 20 cm and diameters up to 10 cm. The prediction accuracy is independent of the soil moisture and drought condition. In a fixed-interval analysis, accuracy reached 0.97 for days 25-42 after planting and 0.93 for days 25-48, demonstrating robust performance as root complexity increased.
Related
- Population dimensionality and timescale organization in mouse V1 under grating and natural movie stimulation
- Tube-in-tube oxygen saturator enabling precise and dynamic control of liquid-phase oxygen concentrations for human cell culture applications
- Enabling climate action: A nexus approach for delivering co-benefits across biodiversity, water, food, and health
- Integrated phenotyping reveals coordinated physiological responses to cold, freezing, and recovery in Ramonda resurrection plants
- Vision Transformers Enable Advanced Plant Phenotyping in Controlled Environments
BibTeX
@misc{hossain2026dirtnet,
title = {{DIRTNet: Enabling Root Phenotyping with Fiber Bragg Grating Sensors}},
author = {K. Hossain and S. Binder and M. Fok and A. Bucksch},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.22.753535},
url = {https://www.biorxiv.org/content/10.64898/2026.09.22.753535v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - DIRTNet: Enabling Root Phenotyping with Fiber Bragg Grating Sensors
AU - K. Hossain
AU - S. Binder
AU - M. Fok
AU - A. Bucksch
PY - 2026
DA - 2026/09/22
PB - bioRxiv
DO - 10.64898/2026.09.22.753535
UR - https://www.biorxiv.org/content/10.64898/2026.09.22.753535v1
AB - Non-destructive methods for real-time phenotyping of root growth and development are essential to accelerate the breeding of climate-resilient crops. We present DIRTNet (Digital Investigations of Root Traits Net), a hybrid deep learning model that interprets in-soil signals collected by Fiber Bragg Grating (FBG) sensors. We first evaluated DIRTNet in a controlled simulation study in which metal rods of varying diameters were inserted into soil to emulate root growth. Using augmented training data with an 80:20 train-test split, DIRTNet surpassed baseline models, achieving 0.97 accuracy for root depth prediction and 0.94 for root diameter prediction. We then applied the best-performing models to maize (Zea mays) roots monitored by six FBG sensors placed at different soil location and depths. A control trial and a drought-stress trial yielded 192 samples, split 80:20 into training and holdout sets; the hold-out portion was divided equally into validation and test sets. Augmentation was applied only to the training data. On real maize root data, DIRTNet achieved 0.92 accuracy for both root depth and root width prediction across variable growth periods, covering root mass lengths up to 20 cm and diameters up to 10 cm. The prediction accuracy is independent of the soil moisture and drought condition. In a fixed-interval analysis, accuracy reached 0.97 for days 25-42 after planting and 0.93 for days 25-48, demonstrating robust performance as root complexity increased.
ER -