Machine learning approaches for predicting soybean disorders under climate change and assessing adaptation measures

Abstract

Soybean production in Japan is increasingly affected by climate change, with rising temperatures and changing soil moisture conditions contributing to green stem disorder (GSD), seed coat cracking (SCC), and seed coat wrinkling (SCW). These disorders reduce seed yield, lower seed quality, and complicate harvesting. To better understand and predict their occurrence (score), we developed random forest (RF) regression models using historical cultivar data and environmental factors from four major soybean breeding sites in Japan. The RF models outperformed traditional regression methods, achieving moderate prediction accuracy for GSD, SCC, and SCW scores (R² > 0.5). Analysis of the partial dependence plot suggested that increased GSD and SCC scores were associated with high temperatures during reproductive stages, while the SCW score showed a stronger link to cultivar traits. Future projections, derived from predictive models and future climate scenarios, suggested that GSD and SCC scores could increase at all sites, whereas the SCW score might rise at specific sites. Adaptation strategies such as late sowing and use of late-maturing cultivars showed potential for reducing risks, but their effectiveness varied by site and disorder type. These findings underscore the importance of considering region-specific strategies to address climate-related challenges in soybean production. By integrating machine learning with historical cultivar data, this study offers insights into developing targeted adaptation measures that could support sustainable soybean cultivation in a changing climate.

Plant phenotyping relevance

大豆の障害スコアという植物状態を対象に、RF回帰モデルを開発・比較評価し、予測性能も検証しているため、計算的な表現型推定が中心的です。

Code and data availability

公開状態または取得可能な本文経路を確認できませんでした。

No evidence-backed public reproduction asset is currently recorded.