Department of Agricultural and Biological Engineering, Mississippi State University, Starkville, MS, USA.
College of Mechanical and Electrical Engineering, Nanjing Forestry University, Nanjing, China.
J Exp Bot. 2023 Aug 3;74(14):4050-4062. doi: 10.1093/jxb/erad129.
Leaf-level hyperspectral reflectance has become an effective tool for high-throughput phenotyping of plant leaf traits due to its rapid, low-cost, multi-sensing, and non-destructive nature. However, collecting samples for model calibration can still be expensive, and models show poor transferability among different datasets. This study had three specific objectives: first, to assemble a large library of leaf hyperspectral data (n=2460) from maize and sorghum; second, to evaluate two machine-learning approaches to estimate nine leaf properties (chlorophyll, thickness, water content, nitrogen, phosphorus, potassium, calcium, magnesium, and sulfur); and third, to investigate the usefulness of this spectral library for predicting external datasets (n=445) including soybean and camelina using extra-weighted spiking. Internal cross-validation showed satisfactory performance of the spectral library to estimate all nine traits (mean R2=0.688), with partial least-squares regression outperforming deep neural network models. Models calibrated solely using the spectral library showed degraded performance on external datasets (mean R2=0.159 for camelina, 0.337 for soybean). Models improved significantly when a small portion of external samples (n=20) was added to the library via extra-weighted spiking (mean R2=0.574 for camelina, 0.536 for soybean). The leaf-level spectral library greatly benefits plant physiological and biochemical phenotyping, whilst extra-weight spiking improves model transferability and extends its utility.
叶片水平高光谱反射率因其快速、低成本、多传感和非破坏性的特点，已成为高通量植物叶片特性表型分析的有效工具。然而，用于模型校准的样本采集仍然可能很昂贵，而且模型在不同数据集之间的可转移性较差。本研究有三个具体目标：首先，从玉米和高粱中收集大量叶片高光谱数据（n=2460）；其次，评估两种机器学习方法来估计九个叶片属性（叶绿素、厚度、含水量、氮、磷、钾、钙、镁和硫）；最后，通过额外加权 spikes 方法，研究这个光谱库对预测大豆和荠蓝等外部数据集（n=445）的有用性。内部交叉验证表明，该光谱库可以很好地估计所有九个特征（平均 R2=0.688），偏最小二乘回归模型的表现优于深度神经网络模型。仅使用光谱库校准的模型在外部数据集上的性能有所下降（荠蓝的平均 R2=0.159，大豆的平均 R2=0.337）。当通过额外加权 spikes 将一小部分外部样本（n=20）添加到库中时，模型的性能显著提高（荠蓝的平均 R2=0.574，大豆的平均 R2=0.536）。叶片水平的光谱库极大地促进了植物生理生化表型分析，而额外加权 spikes 则提高了模型的可转移性并扩展了其应用范围。
