From images to canopy cover growth predictions informed by short-term weather data using transformers and non-linear modeling in soybean breeding lines

Abstract

Selecting soybean lines that thrive under increasingly extreme weather conditions requires a deep understanding of genotype by environmental interaction (GxE) interactions. While controlled experiments offer valuable insights, they rarely capture the complexity of real field conditions. Here, we combine high-resolution, 8-year field imagery with weather data to model soybean canopy growth using automatically labeled deep learning for soybean-weed segmentation and one-stage nonlinear mixed-effects modeling. The models revealed distinct genotypic growth patterns, allowing to pinpoint environmental covariates, specifically photothermal product and precipitation, as drivers of canopy development. Two breeding lines, ‘Everest’ and ‘Kalinka’ recently released as varieties, show stable performance across contrasting weather scenarios with minimal GxE interaction. Genotypic model coefficients predicted key agronomic traits such as maturity timing and protein yield. This demonstrates that growth models can reveal genotypic resilience to environmental variation, even from single-environment measurements, offering valuable insights for breeding and climate adaptation.

Plant phenotyping relevance

画像からの雑草分割とキャノピー成長モデルにより、ダイズのキャノピー成長という植物形質を抽出・予測する手法が研究の中心である。

Code and data availability

公開本文の所在を確認できませんでした。非公開または購読が必要な可能性があります。

No evidence-backed public reproduction asset is currently recorded.