High-throughput pollen germination phenotyping for assessing heat tolerance in soybean

Abstract

Abstract Heat stress causes ultrastructural damage in pollen grains, leading to reduced pollen germination, pollen size and shortened pollen tube length, ultimately lowering seed set and yield. This study presents a high-throughput phenotyping framework that integrates controlled-environment pollen germination assays with deep learning–based object detection for rapid, accurate, and scalable evaluation of reproductive heat tolerance in soybean breeding programs. Sixteen soybean genotypes were grown under controlled environments at optimal (28/18°C; day/night) and high temperature (38/28°C; day/night) regimes during flowering. In vitro pollen germination was quantified using six YOLO (You Only Look Once) object-detection architectures (YOLOv7–YOLOv12) to identify the best-performing model for automated analysis. Among the tested object-detection architectures, YOLOv9 achieved the best overall performance for detecting germinated and non-germinated pollen grains in complex images. High temperature significantly reduced mean pollen germination from an average of 40% under optimal conditions to an average of 21% under heat stress (P < 0.05), with a significant genotype × growth temperature interaction. Invitro incubation temperatures ranging from 10 °C to 45 °C produced a clear thermal response; however, no significant genotype × incubation temperature interaction was detected within either growth temperature regime. Although photosynthetic and physiological traits were measured exploring their relationship with pollen germination, their transient and complex response limited their reliability for predicting reproductive performance. The automated pipeline substantially reduced the time required to evaluate pollen germination. The pipeline processed nearly 5,000 images in approximately one hour, substantially increasing throughput and reducing reliance on manual counting. The findings demonstrate that pollen germination is a promising proxy trait for screening reproductive heat tolerance in soybean. Combining controlled environment phenotyping with YOLO-based object detection enabled efficient, accurate, and scalable pollen analysis, and represents the central methodological advance of this study. YOLOv9 performed best among the tested architectures, although discrepancies from manual counts in some images indicate that additional validation is needed. The weak associations with vegetative physiological traits further support the value of direct pollen-based phenotyping.

Plant phenotyping relevance

深層学習による花粉画像解析を中心に、花粉発芽という生殖形質を高速・自動測定するハイスループット表現型解析フレームワークを開発・比較・検証している。

Code and data availability

The authors state that all data supporting the study, including annotated pollen germination images, computational and statistical codes, and analysis tools, were deposited in Zenodo with a public DOI. This is a paper-specific, publicly actionable asset. LabelMe and Ultralytics YOLO are generic third-party tools, not作者