Search for: All records

Soybean yield prediction is a challenging problem in plant breeding that is often affected by many different factors simultaneously. Hyperspectral reflectance data from plants and soil data provide breeders with useful information about soybean plant health and using these different types of data to predict yield is an active area of research. Furthermore, breeding programs encounter challenges such as data imbalance and external factors like genotype variability across different environments, which present significant hurdles in the development of yield prediction models for large-scale breeding programs. In this work, we perform a comprehensive study of predicting yield using both hyperspectral reflectance and soil data to understand what scenario's offer the best chances of predicting yield with high accuracy. We demonstrate a cluster based ensemble approach for yield prediction using hyperspectral reflectance data that can perform well for large scale breeding programs by efficiently harnessing useful information from data through an unsupervised approach. 

The drive to increase seed yield in soybean (L.) Merr.] has traditionally overshadowed the exploration of biomass partitioning and the compositional characteristics of plant residue traits such as leaves, petioles, stems, and pods. The exploration of biomass partitioning and the compositional characteristics of plant residue traits in soybean provide insights into plant nutrient allocation strategies that can be utilized to increase crop productivity and improve management practices for maximizing yields and sustainability. Recognizing this gap, our study aimed to investigate the variability in these traits across 32 genetically diverse soybean genotypes cultivated over 2 years in central Iowa. Through detailed collection and analysis of vegetative parts at critical growth stages (R1, R4, and R8), we assessed both biomass traits and their chemical compositional characteristics, focusing on soybean residue traits to enhance soil health and their importance in soybean cropping systems. We present broad sense heritability estimates for accumulated (R8) organ biomass (0.61–0.87) and residue carbon nitrogen composition (0.74) in soybeans. The large variation and high heritability suggest breeding strategies to optimize variety development via biomass and residue traits. Utilizing the Agriculture Production Systems sIMulator, we conducted a sensitivity analysis to evaluate the impact of soybean residue quality on soil nutrient cycling and its effects on the subsequent maize [Zea maysL.] crop. The study underscores the importance of soybean residue management, emphasizing the need for integrated approaches in breeding and agricultural practices that utilize the genetic diversity of these traits.