Version 1
: Received: 19 August 2024 / Approved: 19 August 2024 / Online: 20 August 2024 (11:00:45 CEST)
How to cite:
Beltrame, L.; Salzinger, J.; Fanta-Jende, P.; Koppensteiner, L. TriNet: Exploring More Affordable and Generalisable Remote Phenotyping with Explainable Deep Models. Preprints2024, 2024081411. https://doi.org/10.20944/preprints202408.1411.v1
Beltrame, L.; Salzinger, J.; Fanta-Jende, P.; Koppensteiner, L. TriNet: Exploring More Affordable and Generalisable Remote Phenotyping with Explainable Deep Models. Preprints 2024, 2024081411. https://doi.org/10.20944/preprints202408.1411.v1
Beltrame, L.; Salzinger, J.; Fanta-Jende, P.; Koppensteiner, L. TriNet: Exploring More Affordable and Generalisable Remote Phenotyping with Explainable Deep Models. Preprints2024, 2024081411. https://doi.org/10.20944/preprints202408.1411.v1
APA Style
Beltrame, L., Salzinger, J., Fanta-Jende, P., & Koppensteiner, L. (2024). TriNet: Exploring More Affordable and Generalisable Remote Phenotyping with Explainable Deep Models. Preprints. https://doi.org/10.20944/preprints202408.1411.v1
Chicago/Turabian Style
Beltrame, L., Phillipp Fanta-Jende and Lukas Koppensteiner. 2024 "TriNet: Exploring More Affordable and Generalisable Remote Phenotyping with Explainable Deep Models" Preprints. https://doi.org/10.20944/preprints202408.1411.v1
Abstract
In this study, we propose a scalable deep learning approach to automated phenotyping using UAV multispectral imagery, exemplified by yellow rust detection in winter wheat. We adopt a high granularity scoring method (1 to 9 scale) to align with international standards and plant breeders’ needs. Using a lower spatial resolution (60m flight height at 2.5cm GSD), we reduce the data volume by a factor of 3.4, making large-scale phenotyping faster and more cost-effective while obtaining results comparable to those of the state-of-the-art. Our model incorporates explainability components to optimise spectral bands and flight schedules, achieving top-3 accuracies of 0.87 for validation and 0.67 and 0.70 on two separate test sets. We demonstrate that a minimal set of bands (EVI, Red, and GNDVI) can achieve results comparable to more complex setups, highlighting the potential for cost-effective solutions. Additionally, we show that high performance can be maintained with fewer time steps, reducing operational complexity. Our interpretable model components improve performance through regularisation and provide actionable insights for agronomists and plant breeders. This scalable and explainable approach offers an efficient solution for yellow rust phenotyping and can be adapted for other phenotypes and species, with future work focusing on optimising the balance between spatial, spectral, and temporal resolutions.
Keywords
deep learning; yellow rust; wheat breeding; XAI; multispectral data; UAV; remote phenotyping; vegetation indices
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.