Sugarcane nitrogen nutrition estimation with digital images and machine learning methods

Abstract

The color and texture characteristics of crops can reflect their nitrogen (N) nutrient status and help optimize N fertilizer management. This study conducted a one-year field experiment to collect sugarcane leaf images at tillering and elongation stages using a commercial digital camera and extract leaf image color feature (CF) and texture feature (TF) parameters using digital image processing techniques. By analyzing the correlation between leaf N content and feature parameters, feature dimensionality reduction was performed using principal component analysis (PCA), and three regression methods (multiple linear regression; MLR, random forest regression; RF, stacking fusion model; SFM) were used to construct N content estimation models based on different image feature parameters. All models were built using five-fold cross-validation and grid search to verify the model performance and stability. The results showed that the models based on color-texture integrated principal component features (C-T-PCA) outperformed the single-feature models based on CF or TF. Among them, SFM had the highest accuracy for the validation dataset with the model coefficient of determination (R 2 ) of 0.9264 for the tillering stage and 0.9111 for the elongation stage, with the maximum improvement of 9.85% and 8.91%, respectively, compared with the other tested models. In conclusion, the SFM framework based on C-T-PCA combines the advantages of multiple models to enhance the model performance while enhancing the anti-interference and generalization capabilities. Combining digital image processing techniques and machine learning facilitates fast and nondestructive estimation of crop N-substance nutrition.

Plant phenotyping relevance

デジタル画像から葉の色・テクスチャ特徴を抽出し、機械学習でサトウキビ葉の窒素状態を推定する手法を構築・交差検証しており、表現型取得・推定が研究の中心である。

Code and data availability

The supplied article blocks describe sugarcane leaf image collection, feature extraction (color/texture/PCA), and ML models (MLR/RF/SFM), but contain no data availability statement, no public dataset or image deposit, and no author code/model release with a URL. All URLs in the text are citations to prior work or the (

No evidence-backed public reproduction asset is currently recorded.