Estimating rice yield-related traits using machine learning models integrating hyperspectral and texture features.

Abstract

Background Rapidly estimating multiple trait indicators simultaneously, nondestructively, and with high precision is an important means of accurate diagnosis in modern phenomics. Increasing the accuracy of estimation models for rice yield-related trait indicators (leaf nitrogen concentration, LNC; leaf area index, LAI; aboveground biomass, AGB; and grain yield, GY) through a strategy of "spectral data + texture data + dimensionality reduction + machine learning" is highly important. Methods Between 2022 and 2023, hyperspectral canopy images, the LNC, LAI, AGB, and GY were collected synchronously. Then, dimensionality reduction was performed on the preprocessed spectral data using the Pearson correlation coefficient method, the successive projections algorithm (SPA), and competitive adaptive reweighted sampling (CARS) to select sensitive wavelengths. Estimation models were constructed using artificial neural networks (ANNs), support vector machine regression, one-dimensional convolutional neural networks, and long short-term memory networks. By extracting the texture features corresponding to sensitive wavelengths, high-precision estimation models were constructed using a "spectral data + texture data + dimensionality reduction + machine learning" method. Results SPA-ANN provided the best prediction for LNC (R 2 = 0.82, RMSE = 3.68 g/kg) and LAI (R 2 = 0.75, RMSE = 0.47), while CARS-ANN was optimal for AGB (R 2 = 0.90, RMSE = 79.05 g/m2) and GY (R 2 = 0.63, RMSE = 0.59 t/ha). Adding texture features increased R 2 by up to 9.9% and reduced RMSE by up to 27.2%. Conclusion The optimized method can significantly increase the accuracy of estimation models. The results provide a scientific basis and technical data for the precise diagnosis of rice yield-related traits.

Plant phenotyping relevance

水稲の収量関連形質を、ハイパースペクトル画像・テクスチャ特徴・次元削減・機械学習で非破壊推定する手法が研究の中心であり、植物フェノタイピング手法として明確に該当する。

Code and data availability

The supplied blocks describe rice hyperspectral/texture phenotyping and ML modeling but contain no public dataset, image, code, or model deposit. No data availability statement text or author-hosted repository URL appears; the only allowed URL is the article DOI itself, which is not a qualifying asset.

No evidence-backed public reproduction asset is currently recorded.