Aaron J. DeSalvio

This paper introduces a regression-based framework to predict flowering time from sparse UAV observations, reducing the need for repeated data collection.

Drone imagery from 356 flights in 19 Genomes to Fields maize environments; vegetation-index functional principal components complement genomic kernels, predicting yield of held-out hybrids at r up to 0.501.

This paper introduces distributional data analysis to plant phenomics, showing it captures novel heritable features in cotton and maize imagery that improve yield prediction and explain genetic variation.

This paper develops a CNN-based method for high-throughput maize tasseling phenotyping using UAS imagery across multiple environments, achieving high classification accuracy.

The paper uses drone-based multispectral imaging to study flood tolerance in maize hybrids, identifying spatial and genetic factors associated with post-flood survival.

This paper links functional data analysis with deep learning to analyze single-plant cotton senescence using temporally concatenated UAS images.