An open field phenomics resource for multimodal maize yield prediction across divergent environments
Year: 2026
Type: preprint
Abstract: 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.
Authors: 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, Nick Duffield, Jode Edwards, David Ertl, Sherry Flint-Garcia, Michael A. Gore, Candice N. Hirsch, James Holland, Shawn M. Kaeppler, Jarrod Miller, Maria Cinta Romay, James C. Schnable, Maninder P. Singh, Erin E. Sparks, Addie Thompson, Jacob D. Washburn, Teclemariam Weldekidan, Noah D. Winans, Natalia de Leon
Institutions: Texas A&M University, Purdue University West Lafayette, University of Wisconsin–Madison, Agricultural Research Service, Cornell University, New York State College of Agriculture & Life Sciences, University of Missouri, University of Minnesota, North Carolina State University, University of Delaware, University of Nebraska–Lincoln, Michigan State University, Donald Danforth Plant Science Center
Language: English
Subfield: Ecology
Field: Environmental Science
Domain: Physical Sciences
SDG: Zero hunger
Open Access status: green
OpenAlex ID: W7213609576