Identification and selection of evaluation indices for soybean shade tolerance via high-throughput phenotyping platforms and machine learning

Abstract

• High-throughput phenotyping of 202 soybean accessions across two growth stages identified key shade tolerance indicators. • A two-stage framework assessed symbiotic shade tolerance, recovery ability, and overall performance. • Machine learning–based trait mining was validated across multiple environments. Intercropping is a promising cultivation strategy that enhances the sustainable use of water and land resources while contributing to national food and oil security. To improve the yield stability of soybeans in intercropping systems, there is an urgent need to develop a scientific and efficient framework for evaluating shade tolerance. In this study, we propose an integrated shade tolerance assessment method based on high-throughput phenotyping, multienvironment trials, and machine learning (ML) approaches. Utilizing multivariate analysis, we evaluated 202 soybean accessions and partitioned their performance under intercropping into two distinct capacities, namely, shade tolerance during the cogrowth stage and recovery ability during the independent growth stage, each of which was classified into five levels from weak to strong. Preliminary trait selection was performed through correlation analysis and broad-sense heritability estimation, followed by the application of six ML models to identify the key shade tolerance traits across different growth stages. The robustness and generalizability of the selected traits were validated in three environments—a field pot, an open field, and a greenhouse—using soybean varieties with known shade tolerance levels. The results revealed that three traits—the side canopy area (SCA), top canopy area at stage 3 (TCA3), and top-view mixed entropy (TME)—were strongly associated with shade-tolerant varieties. These traits presented two distinguishing features: significantly higher values under shaded conditions and greater increases during the recovery phase. The prediction models constructed with these three traits achieved strong performance, with coefficients of determination of R ²=0.776 for shade tolerance and R ²=0.959 for recovery ability. In summary, this study demonstrates the potential for integrating high-throughput phenotyping with ML to efficiently identify the key indicators of shade tolerance. By measuring only three indicators—SCA, TCA3, and TME—soybean shade tolerance at the seedling stage, recovery ability during later growth, and overall shade tolerance across the full growth period can be rapidly and accurately evaluated. This method offers a powerful and practical tool for implementing shade tolerance evaluations, gene discovery, and targeted breeding of soybean cultivars that are suitable for intercropping systems.

Plant phenotyping relevance

高スループット表現型解析と機械学習を統合し、画像由来の植物形質からダイズの遮陰耐性・回復能を評価する方法を提案・検証しており、表現型取得と抽出が研究の中心である。

Code and data availability

公開論文であることは確認できましたが、現在の公式API・許可済み取得経路では本文を自動取得できませんでした。

No evidence-backed public reproduction asset is currently recorded.