Rapid detection method of soybean seed germination potential based on the PLSR-MLP fusion model.

Abstract

In order to realize the rapid detection of soybean seed germination potential, this study designed a fusion model to solve the problem that the single model was insufficient in spectral feature analysis and the prediction performance was limited. The model combines the advantages of the Partial Least Squares Regression (PLSR) and the Multilayer Perceptron (MLP), and utilizing principal components extracted by PLSR as the input features for MLP to construct a soybean seed germination potential prediction model with both linear and nonlinear modeling capabilities. The PLSR module accurately extracts the linear features of the spectrum, and the MLP network further captures the nonlinear relationship between the spectral data and the target variable, which significantly improves the generalization ability of the model. The experimental results show that the prediction performance of the proposed PLSR-MLP fusion model (R p 2 = 0.9534, RMSEP = 7.3821) is significantly improved compared with the single PLSR model (R p 2 = 0.7284, RMSEP = 17.8154) and the single MLP model (R p 2 = 0.7935, RMSEP = 15.5335). In the prediction of soybean germination potential, the PLSR-MLP model also outperforms other single models (Support Vector Machine, SVM; Random Forest, RF) and other fusion models such as PLSR-SVM and PLSR-RF. The PLSR-MLP fusion model effectively addresses the limitations of a single model's performance enhancement potential and the susceptibility to overfitting. It provides a new method for the efficient evaluation of seed germination potential. It also has practical application value for precision seed selection in agriculture and offers a new idea for near-infrared spectrum modeling.

Plant phenotyping relevance

大豆種子の発芽能力という植物状態を近赤外スペクトルとPLSR-MLP融合モデルで推定する手法の開発・比較検証が研究の中心である。

Code and data availability

The supplied article blocks describe soybean seed NIR spectral data and a PLSR-MLP fusion model, but contain no data availability statement, no public dataset deposit, no author code repository, and no public URL for any paper-specific asset. The only implementation detail is that modeling was done in MATLAB R2021b, a

No evidence-backed public reproduction asset is currently recorded.