ADAaron J. DeSalvio

Aaron J. DeSalvio

*This is an algorithmically generated author record based on publicly available information.

Aaron J. DeSalvio has a total of 61 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    An open field phenomics resource for multimodal maize yield prediction across divergent environments

    by Aaron J. DeSalvio, Peiman Mohseni, Alper Adak, Seth C. Murray, Mustafa A. Arik, Raymond K. W. Wong, Jinha Jung, Dayane C. Lima, Alejandro C. Aviles, Edward Buckler, et al.

    Temporal drone phenotyping captures crop development, but irregular flight schedules complicate comparisons across environments. We release curated imagery from 356 flights across 19 Genomes to Fields environments containing 1,180 maize ( Zea mays L.) hybrids. To evaluate its utility, we integrated functional principal components of vegetation index and weather trajectories with genomic information. Combinined genomic and phenomic kernels improved yield prediction, reaching correlations up to r = 0.501 for held-out hybrids in environments represented in training and 0.408 when environments were also withheld. Accumulated growing degree days offered no consistent predictive advantage over days after planting, and weather contributed modest, task-dependent gains. A transformer neural process learned directly from irregular observations, serving as a novel application of neural process models in agriculture. Mapping vegetation index functional principal components identified recurrent quantitative trait loci on chromosomes 3 and 7. This resource and its reproducible analyses guide the use of temporal spectral data for crop prediction and genetic discovery.


  • Open Access

    High‐throughput unmanned aerial vehicle phenomics and machine learning enables accurate early single‐plant biomass prediction in lettuce

    by Görkem Eren Özdemir, Ahmet Rıza Ağır, Burak Aktürk, Nida Selen Baysal, Adem Dogan, Aaron J. DeSalvio, Mustafa A. Arik, Yasin Topcu, Alper Adak

    Lettuce ( Lactuca sativa L.) exhibits pronounced genotype and environment‐dependent growth variation, making early, non‐destructive single‐plant biomass prediction critical for breeding. However, harvest‐based measurements fail to capture growth dynamics. In this study, we tested whether multi‐temporal unmanned aerial vehicle (UAV) phenomics could accurately predict lettuce fresh weight at the single‐plant level and how early reliable prediction was achievable under field conditions. Six UAV flights were conducted at 26, 34, 41, 48, 51, and 54 days after planting (DAP), from which single‐plant structural and spectral traits including canopy PixelCount and 17 vegetation indices were extracted from high‐resolution red, green, blue, and multispectral imagery. Temporal canopy development was characterized using generalized additive models (GAMs), and fresh weight was predicted using Ridge Regression, Least Absolute Shrinkage and Selection Operator, Elastic Net, and Random Forest algorithms within a stringent genotype‐pair cross‐validation framework (420 train–test splits), ensuring prediction of completely unseen genotypes. Canopy PixelCount emerged as the dominant predictor of biomass across all growth stages, showing consistently strong correlations from early development through harvest (e.g., peak r = 0.89 at 54 DAP). Spectral indices such as green normalized difference vegetation index exhibited promising but stage‐dependent associations (e.g., peak r = 0.78 at 41 DAP). Biomass quartiles became clearly separable from mid‐season onward, with strongest discrimination observed at DAP 48–54 (often p < 0.0001). GAMs captured nonlinear canopy expansion accurately ( R 2 = 0.84–0.87; root mean square error = 114.8–145.2 pixels), revealing distinct growth trajectories between low‐ and high‐biomass plants. Importantly, meaningful biomass prediction was already achievable at the earliest flight (DAP 26; test r = 0.30–0.66) and improved consistently as additional flights were incorporated, reaching high accuracy when all six flights were used ( r = 0.85–0.89). Ridge regression provided the most stable performance across genotypes, although alternative models occasionally showed slight early‐stage advantages in specific genetic backgrounds. Overall, these results demonstrate that single‐plant, multi‐temporal UAV phenomics enables accurate early biomass prediction in lettuce, while the large‐scale, temporally resolved single‐plant dataset generated in this study provides a valuable resource for future phenomic research.

  • Open Access

    Phenomics-derived temporal maize health and environmental index enhance physiology-informed genomic prediction of yield across environments

    by Alper Adak, Aaron J DeSalvio, Seth C Murray, James B Holland, Natalia De Leon, Martin O Bohn, Jode Edwards, David Ertl, Candice Hirsch, Shawn Kaeppler, et al.

    Integrating multi-omics data, including phenomic, genomic, and environmental inputs, offers a powerful approach for enhancing maize performance and predicting grain yield. In this study, crop health was quantified using temporal NGRDI (Normalized Green Red Difference Index) trajectories collected from 16 unoccupied (unmanned) aerial vehicle or system (UAV or UAS, drones and sensors) flights (from 19 to 117 d after planting) in maize trials conducted in Texas. Crop health indices (CHIs) were calculated through area under the curve (CHIAUC) and functional principal component analysis (CHIFPCA), capturing dynamic plant health responses throughout the growing season. Heritability estimates of NGRDI fluctuated between 0.3 and 0.7, averaging 0.51 ± 0.02, reflecting consistent genetic contributions to growth dynamics. CHIs derived from a favorable (irrigated) trial in Texas effectively separated high- and low-yielding hybrids across 41 environment-tester combinations, achieving significant differentiation in 27 (CHIAUC) and 28 (CHIFPCA1) environments. In comparison, only 21 environments were differentiated when using grain yield alone. Genomic mapping of temporal NGRDI revealed key quantitative trait loci (QTLs) linked to maize growth, containing candidate genes including br2, phyC1, wus1, mads69, cct1, rap2, miR172, and gl15, associated with canopy development, flowering regulation, and drought adaptation. Integrating multi-omics data into phenomic- and environment-informed genomic prediction models improved yield prediction accuracy by approximately 18.5%, particularly for untested genotypes in both tested and untested environments. These findings demonstrate that multi-omics integration provides a scalable framework for enhancing maize performance and advancing grain yield prediction across diverse agricultural systems.


  • Open Access

    Distributional Data Analysis Uncovers Hundreds of Novel and Heritable Phenomic Features from Temporal Cotton and Maize Drone Imagery

    by Aaron J. DeSalvio, Marcos Matabuena, Alper Adak, Mustafa A. Arik, Serina M. DeSalvio, Seth C. Murray, Raymond K.W. Wong, Jode Edwards, Natalia de Leon, Shawn M. Kaeppler, et al.

    Genomic and phenomic analyses suggest additional heritable phenomic features can improve modeling of important end traits like senescence or yield. Field phenotyping generally uses trait values averaged across individual experimental units (plants or numerous plants within plots), ignoring the full distributional pattern of collected measures. Images of plants or plots, as captured by drones (unoccupied aerial vehicles / UAVs / drones), can be viewed as individual distribution functions that capture biological information. This study introduces and validates distributional data analysis in two crops and experiment types – cotton ( Gossypium hirsutum L.) single plant vegetation index (VI) analysis and maize ( Zea mays L.) plot-level yield predictions. In both crops, the concept of within-day variance decomposition was demonstrated. In cotton, genotypes exerted significant influences on temporal quantile functions of VIs. Maize yield prediction using distributional data with elastic-net regression indicated improvements in yield prediction between 12.7%-21.6% with quantiles outside the conventionally used median responsible for added predictive power. A novel data visualization method for per-pixel heritability allowed distributional features to be explainable and interpretable. These results have implications for future plant phenomic studies, indicating that distributional data analysis applied across temporal imagery captures novel, heritable, and interpretable biological signal that is lost when working with conventional measures of central tendency such as mean or median summary values of experimental units. Significance: Repeated aerial imaging of agricultural experiments produces image data sets that capture plant development in high spatial and temporal resolutions. Frequently, images are summarized by measures of central tendency, such as mean or median values. Here, functional data distributional methods were applied to cotton ( Gossypium hirsutum L.) and maize ( Zea mays L.) image data, capturing more information than standard approaches. Cotton genotypes significantly impacted distributional spectral data while in maize, distributional data enabled more accurate predictions of grain yield versus models trained with median data alone. Distributional data were more explainable by genetics, with novel data visualization techniques able to shine light on specific parts of plant imagery with high and low genetic variance.

  • Open Access

    Deep learning‐based high‐throughput detection of flowered maize ( Zea mays L.) plots from UAS imagery across environments

    by Nicholas R. Shepard, Aaron J. DeSalvio, Mustafa Arik, Alper Adak, Seth C. Murray, Jose Ignacio Varela

    Flowering time is a critical phenological trait in maize ( Zea mays L.) breeding programs. Traditional measurements for assessing flowering time involve semi‐subjective and labor‐intensive manual observation, limiting the scale and efficiency of genetics and breeding improvement. Leveraging unoccupied aerial system (UAS, also known as unoccupied aerial vehicles or drones) technology coupled with convolutional neural networks (CNNs) presents a promising approach for high‐throughput detection of flowered plots in maize. Most CNN image analysis is overly complicated for simple tasks relevant to plant scientists. Here, a methodology for extracting tasseling from UAS red/green/blue imagery using a CNN‐based approach was applied to 220 hybrids and 30 test lines grown in eight diverse environments (Wisconsin and Texas) and then validated through an unrelated set of hybrids. Overall accuracies of 0.946, 0.911, 0.985, and 0.988 were obtained for classifying maize images with or without tassels from College Station, TX, in 2020; College Station, TX, in 2021; Arlington, WI, in 2021; and Madison, WI, in 2021, respectively. By employing deep learning techniques, larger volumes of phenotypic data can be processed enabling high‐throughput phenotyping in breeding programs. Although large datasets are required to train CNN models, the proposed methodology prioritizes simplicity in computational architecture while maintaining effectiveness in identifying flowered maize across diverse genotypes and environments.


  • Open Access

    Drone-Based Identification of Flood-Tolerant Maize via Multispectral Imaging: A Real-World Case Study

    by Madison N Mitchell, Grace Sidberry, Morgan Mathison, Aaron J. DeSalvio, Daniel R Kick, Jacob D. Washburn

    Excess moisture (flooding, water logging, etc.) is a major source of crop damage causing catastrophic monetary losses to farmers around the world. Losses from excess water are often more common and costly than those from too little water (i.e., drought). Extreme weather patterns are predicted to increase, increasing the expected frequency of excess moisture events to farmers across the Midwest. Despite its importance, studying the impacts of flooding in the field is challenging due to unpredictability of flooding and fields being rendered inaccessible during flooding. Here, we took advantage of a natural flood experiment to examine the responses, damage, and recovery of diverse maize hybrids. Using drones, we monitored the hybrids before, during, and after flooding and examined the spatial and genetic components associated with post-flood survival.

  • Open Access

    High temporal resolution unoccupied aerial systems phenotyping provides unique information between flight dates

    by Jacob D. Washburn, Alper Adak, Aaron J. DeSalvio, Mustafa A. Arik, Seth C. Murray

    Unoccupied aerial systems (UAS, unoccupied aerial vehicle, and drone) are high‐throughput phenotyping tools that can provide transformational insights into biological and agricultural research, but practical and scientific questions remain. The utility of dense versus sparse temporal collections (e.g., daily, weekly, and monthly flights) has important implications for experimental design, resource allocation, and the scope of scientific questions investigated through UAS. UAS‐derived image data were collected on over 1500 maize hybrid yield trial plots with a temporal (longitudinal, 4D) sampling density of 2.8 days on average between 43 flights throughout the growing season. Correlations of vegetation index (VI) phenomic features between flight dates were generally high between flights separated by only 1 or 2 days but dropped when 3, 4, or more days separated the flights. These varied depending on specific dates and the VI used. Correlations between flights were lower around flowering time than during other parts of the season indicating the phenotypic uniqueness of this developmental period. The cross‐validation accuracy of end of season yields prediction models on untested genotypes from the UAS data (0.59 and 0.62) far exceeded genomic prediction accuracy (0.24) for the same test set hybrids regardless of whether all flight dates were used for prediction or only dates before flowering. Phenomic prediction accuracy marginally increased as additional flight dates were added throughout the season.


  • Open Access

    Temporal Image Sandwiches Enable Link between Functional Data Analysis and Deep Learning for Single-Plant Cotton Senescence

    by Aaron J. DeSalvio, Alper Adak, Mustafa A. Arik, Nicholas R. Shepard, Serina M. DeSalvio, Seth C. Murray, Oriana García-Ramos, Himabindhu Badavath, David M. Stelly

    Summary: Senescence is a highly ordered degenerative biological process that affects yield and quality in annuals and perennials. Images from 14 unoccupied aerial system (UAS, UAV, drone) flights captured the senescence window across two experiments while functional principal component analysis (FPCA) effectively reduced the dimensionality of temporal visual senescence ratings (VSRs) and two vegetation indices: RCC and TNDGR. Convolutional neural networks (CNNs) trained on temporally concatenated, or “sandwiched,” UAS images of individual cotton plants ( Gossypium hirsutum L.), allowed single-plant analysis (SPA). The first functional principal component scores (FPC1) served as the regression target across six CNN models (M1-M6). Model performance was strongest for FPC1 scores from VSR (R 2 = 0.857 and 0.886 for M1 and M4), strong for TNDGR (R 2 = 0.743 and 0.745 for M3 and M6), and strong-to- moderate for RCC (R 2 = 0.619 and 0.435 for M2 and M5), with deep learning attention of each model confirmed by activation of plant pixels within saliency maps. Single-plant UAS image analysis across time enabled translatable implementations of high-throughput phenotyping by linking deep learning with functional data analysis (FDA). This has applications for fundamental plant biology, monitoring orchards or other spaced plantings, plant breeding, and genetic research.


  • Open Access

    Temporal image sandwiches enable link between functional data analysis and deep learning for single-plant cotton senescence

    by Aaron J DeSalvio, Alper Adak, Mustafa A Arik, Nicholas R Shepard, Serina M DeSalvio, Seth C Murray, Oriana García-Ramos, Himabindhu Badavath, David M Stelly

    Senescence is a highly ordered biological process involving resource redistribution away from aging tissues that affects yield and quality in annuals and perennials. Images from 14 unmanned / unoccupied / uncrewed aerial system (UAS, UAV, drone) flights captured the senescence window across two experiments while functional principal component analysis (FPCA) effectively reduced the dimensionality of temporal visual senescence ratings (VSRs) and two vegetation indices: the red chromatic coordinate index (RCC) and transformed normalized difference green and red index (TNDGR). Convolutional neural networks (CNNs) trained on temporally concatenated, or “sandwiched,” UAS images of individual cotton plants (Gossypium hirsutum L.), allowed single-plant analysis (SPA). The first functional principal component scores (FPC1) served as the regression target across six CNN models (M1-M6). Model performance was strongest for FPC1 scores from VSRs (R2 = 0.857 and 0.886 for M1 and M4), strong for TNDGR (R2 = 0.743 and 0.745 for M3 and M6), and strong-to-moderate for RCC (R2 = 0.619 and 0.435 for M2 and M5), with deep learning attention of each model confirmed by activation of plant pixels within saliency maps. Single-plant UAS image analysis across time enabled translatable implementations of high-throughput phenotyping by linking deep learning with functional data analysis (FDA). This has applications for fundamental plant biology, monitoring orchards or other spaced plantings, plant breeding, and genetic research.


  • Open Access

    Deep Learning-Based High-Throughput Phenotyping Of Maize ( Zea mays L.) Tasseling From Uas Imagery Across Environments

    by Nicholas R. Shepard, Aaron J. DeSalvio, Mustafa Arik, Alper Adak, Seth C. Murray, Jose Ignacio Varela, Natalia de Leon

    A bstract: Flowering time is a critical phenological trait in maize ( Zea mays L.) breeding programs. Traditional measurements for assessing flowering time involve semi-subjective and labor-intensive manual observation, limiting the scale and efficiency of genetics and breeding improvement. Leveraging unoccupied aerial system (UAS, also known as UAVs or drones) technology coupled with convolutional neural networks (CNNs) presents a promising approach for high-throughput phenotyping of tasseling in maize. Most CNN image analysis is overly complicated for simple tasks relevant to plant scientists. Here a methodology for extracting tasseling from RGB imagery using a CNN-based approach was applied to 220 hybrids and 30 test lines grown in eight diverse environments (Wisconsin and Texas, U.S.A.) then validated through an unrelated set of hybrids. Overall accuracies of .946, .911, .985, and .988 were obtained for classifying maize images with or without tassels from College Station, TX in 2020; College Station, TX in 2021; Arlington, WI in 2021; and Madison, WI in 2021 respectively. By employing deep learning techniques, larger volumes of phenotypic data can be processed enabling high-throughput phenotyping in breeding programs. Although large datasets are required to train CNN models, the proposed methodology prioritizes simplicity in computational architecture while maintaining effectiveness in identifying flowered maize across diverse genotypes and environments.