氮素是蛋白质和叶绿素等物质的组成元素，对植物生长发育起着关键作用，氮素含量指示着植物营养状况及长势变化。利用高光谱技术无损、高效地估算植物生理生化指标，可以为植物生长发育过程中养分和健康状况评估提供可靠的数据收集方法。本文以薄壳山核桃（长林和建德系列）为研究对象，室外随机采集53株薄壳山核桃350~2500 nm范围的冠层高光谱，首先运用分数阶微分(FOD)进行光谱预处理，进一步联合两种两波段光谱指数探明薄壳山核桃叶片氮素含量(LNC)与光谱的响应关系，最后利用变量组合集群分析算法(VCPA)筛选建模变量，分别构建冠层FOD单波段及FOD联合两波段光谱指数的极端梯度提升算法(XGBoost)估算模型，得到基于本试验条件下LNC适宜的估算模型。结果表明，与原始光谱相比，FOD预处理后的冠层光谱与薄壳山核桃LNC的相关性提升效果较好，提高了0.152；FOD结合两波段光谱指数（归一化和差值光谱指数）比单波段在提高光谱特征与目标成分的相关性效果更佳，分别提高了0.250和0.277；VCPA变量选择方法最终筛选的光谱变量组合子集中同时包含强弱信息变量，对提升估算模型精度具有重要的作用；最优氮素估算模型是1.5阶微分结合两波段差值光谱指数(DSI)模型，模型预测集R2 P = 0.75，RMSEP = 1.32 g?kg。本文一方面证实了高光谱快速无损估算薄壳山核桃LNC的可行性；另一方面，分数阶微分结合两波段光谱指数可以显著提高光谱特征与目标变量的响应关系，丰富了高光谱数据处理方法，为植物养分监测开拓一种新的思路。

[Objective] Nitrogen is not only a component element of protein and chlorophyll, but also plays a key role in plant growth and development. Obtaining and analyzing the nitrogen content in plants can reveal their nutritional status and growth changes. Non-destructive and efficient estimation of plant physiological and biochemical indicators using hyperspectral technology can provide a reliable data collection method for the evaluation of nutrient levels and health status during plant growth and development. [Methods] In this study, Carya illinoensis (Jiande and Changlin series) was taken as research object. The spectral data of 53 plants were collected randomly, covering a wavelength range of 350~2500 nm. Firstly, fractional order derivative (FOD) was used for spectral preprocessing. Secondly, the spectral response relationship between LNC and spectral reflectance combining two-band spectral indices (normalized difference spectral index, NDSI; difference spectral index, DSI). The variable combination population analysis (VCPA) strategy was used to screen modeling variables. The extreme gradient boosting algorithm (XGBoost) estimation models of canopy FOD single-band and FOD combined with two-band spectral indices were constructed respectively. Finally, a suitable estimation model of LNC based on the experimental conditions was obtained. [Results] The results showed that the correlation between canopy spectrum after FOD treatment and LNC was improved by 0.152, compared with the raw spectrum. FOD combined with two-band spectral indices (NDSI, DSI) was better than single-band in improving the correlation between spectral characteristics and target components, which was increased by 0.25 and 0.277, respectively. The final selected subset of spectral variable combinations included both strong and weak information variables, playing a crucial role in improving the accuracy of the estimation models. The optimal LNC model is the 1.5th-order derivative transformation combined with two-band spectral index (difference spectral index, DSI), with R2 P = 0.75, and RMSEP = 1.32 g/kg. [Conclusions] This study confirms the feasibility of rapid and non-destructive LNC estimation of Carya illinoensis using hyperspectral technology. On the other hand, FOD combined with two-band spectral indices can significantly improve the response relationship between spectral characteristics and target variables, enrich hyperspectral data processing methods, and open up a new idea for plant nutrient monitoring.