TY  - JA
AU  - Victor,B.
AU  - Nibali,A.
AU  - Newman,S.J.
AU  - Coram,T.
AU  - Pinto Espinosa,F.
AU  - Reynolds,M.P.
AU  - Furbank,R.T.
AU  - Zhen He
TI  - High-throughput plot-level quantitative phenotyping using convolutional neural networks on very high-resolution satellite images
SN  - 2072-4292
PY  - 2024///
CY  - Basel (Switzerland)
PB  - MDPI, 
KW  - Agriculture
KW  - AGROVOC
KW  - Image analysis
KW  - Plant breeding
KW  - Remote sensing
KW  - Machine learning
N1  - Peer review; Open Access
N2  - To ensure global food security, crop breeders conduct extensive trials across various locations to discover new crop varieties that grow more robustly, have higher yields, and are resilient to local stress factors. These trials consist of thousands of plots, each containing a unique crop variety monitored at intervals during the growing season, requiring considerable manual effort. In this study, we combined satellite imagery and deep learning techniques to automatically collect plot-level phenotypes from plant breeding trials in South Australia and Sonora, Mexico. We implemented two novel methods, utilising state-of-the-art computer vision architectures, to predict plot-level phenotypes: flowering, canopy cover, greenness, height, biomass, and normalised difference vegetation index (NDVI). The first approach uses a classification model to predict for just the centred plot. The second approach predicts per-pixel and then aggregates predictions to determine a value per-plot. Using a modified ResNet18 model to predict the centred plot was found to be the most effective method. These results highlight the exciting potential for improving crop trials with remote sensing and machine learning
UR  - https://hdl.handle.net/10883/23043
DO  - https://doi.org/10.3390/rs16020282
T2  - Remote Sensing
ER  -