文献类型：期刊文献

英文题名：Research Paper A novel framework for developing accurate and explainable leaf nitrogen content estimation model for aquilaria sinensis seedlings using canopy RGB imagery

作者：Chen, Zhulin[1,2] Wang, Xuefeng[1,2]

第一作者：Chen, Zhulin

通信作者：Wang, XF[1]

机构：[1]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing 100091, Peoples R China;[2]Natl Forestry & Grassland Adm, Key Lab Forest Management & Growth Modelling, Beijing 100091, Peoples R China

年份：2025

卷号：251

起止页码：128-144

外文期刊名：BIOSYSTEMS ENGINEERING

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001428714600001)】；

基金：This work was funded by the National Natural Science Foundation of China (Grant Numbers 32401581 and 32071761) . This research was also funded by the Special Funds for Fundamental Research Business Expenses of the Central Public Welfare Research Institution (CAFYBB2021ZB002) .

语种：英文

外文关键词：Colour indices; Texture features; Feature selection; RGB images; Deep learning; Variable contribution

摘要：Leaf nitrogen content (LNC) is crucial for the cultivation and health management of the endangered tree species Aquilaria sinensis. Although RGB imagery combined with machine learning has been effective for non-destructive LNC estimation, current models often neglect colour index texture features and face feature selection and interpretability challenges. This study introduces a framework to address these issues. Firstly, the canopy RGB imagery colour indices and the texture features of Aquilaria sinensis seedlings were collected as an initial feature set. Then, an improved hybrid feature selection algorithm combining SHapley Additive exPlanation (SHAP) with a dynamic ranking strategy was applied with a regression algorithm. This approach was tested using random forest (RF), support vector regression (SVR), and deep neural network (DNN) models. Optimal feature subsets were identified for each model, and performance comparisons determined the best LNC estimation model. Results show that texture features derived from colour indices significantly enhance LNC estimation accuracy. The dynamic SHAP ranking method outperformed RF and fixed SHAP rankings in feature selection. The optimal model, a DNN with an R2 of 0.946 and RMSE of 1.859 g kg-1 included two colour indices and five colour index texture features. While the normalised red colour index had the highest contribution, texture features contributed more overall to model accuracy. This method can be extended to other biophysical and biochemical parameter estimations.