Journal
REMOTE SENSING
Volume 13, Issue 19, Pages -Publisher
MDPI
DOI: 10.3390/rs13193976
Keywords
machine learning; crop breeding; multimodal learning; Zea mays; high-throughput phenotyping; computer vision; vegetation indices; explainable artificial intelligence; uncrewed aerial vehicles
Categories
Funding
- Australian Government through the Australian Research Council [DP210100296, DP200100762]
- Australian Government through the Grains Research and Development Corporation [9177539, 9177591]
- Forrest Research Foundation
- Research Training Program scholarship
Ask authors/readers for more resources
The study presents a multimodal deep learning model for early prediction of maize performance using multispectral data and vegetation indices. The model accurately predicted yield and identified high-yielding varieties, outperforming previous models. Inclusion of vegetation indices improved model performance, providing a decision support tool for identifying promising lines early in the field trial.
Assessing crop production in the field often requires breeders to wait until the end of the season to collect yield-related measurements, limiting the pace of the breeding cycle. Early prediction of crop performance can reduce this constraint by allowing breeders more time to focus on the highest-performing varieties. Here, we present a multimodal deep learning model for predicting the performance of maize (Zea mays) at an early developmental stage, offering the potential to accelerate crop breeding. We employed multispectral images and eight vegetation indices, collected by an uncrewed aerial vehicle approximately 60 days after sowing, over three consecutive growing cycles (2017, 2018 and 2019). The multimodal deep learning approach was used to integrate field management and genotype information with the multispectral data, providing context to the conditions that the plants experienced during the trial. Model performance was assessed using holdout data, in which the model accurately predicted the yield (RMSE 1.07 t/ha, a relative RMSE of 7.60% of 16 t/ha, and R-2 score 0.73) and identified the majority of high-yielding varieties, outperforming previously published models for early yield prediction. The inclusion of vegetation indices was important for model performance, with a normalized difference vegetation index and green with normalized difference vegetation index contributing the most to model performance. The model provides a decision support tool, identifying promising lines early in the field trial.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available