Machine Learning Optimised Hyperspectral Remote Sensing Retrieves Cotton Nitrogen Status
Machine Learning Optimised Hyperspectral Remote Sensing Retrieves Cotton Nitrogen Status
复制标题
DOI：
10.3390/rs13081428
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
I. Marang;P. Filippi;T. Weaver;B. Evans;B. Whelan;T. Bishop;Mohammed O. F. Murad;Dhahi Al-Shammari;G. Roth
中科院分区：
文献类型：
--
作者：
I. Marang;P. Filippi;T. Weaver;B. Evans;B. Whelan;T. Bishop;Mohammed O. F. Murad;Dhahi Al-Shammari;G. Roth
安装在无人机（UAV）上的高光谱成像光谱仪可以捕获高空间和光谱分辨率，为精准农业提供棉花作物氮状态。本研究的目的是探索机器学习在农业领域中高光谱数据立方体的使用。高光谱图像是在成熟的棉花作物上收集的，该作物在 475-925 nm 的光谱范围内具有高空间 (~5.2 cm) 和光谱 (5 nm) 分辨率，可以区分单个作物行和田间特征以及用于计算导数光谱的连续光谱范围。标称反射率及其导数清楚地突出了不同的处理块，并且与传统植被指数（例如 Vogelman 1，R2 = 0.8）和新颖的光谱组合（R2 = 0.85）中叶片和叶柄样品中的氮浓度密切相关。确定的关键高光谱波段位于红边拐点（695-715 nm）。通过测试 Sentinel MSI 使用 VIS-NIR 光谱区域中的波段预测氮浓度的能力，将卫星多光谱与无人机高光谱遥感的性能进行比较。 Sentinel 2A 绿带（B3；中点 559.8 nm）解释的 N 变化量与高光谱数据相同，并且比 Sentinel 红边点 1（B5；中点 704.9 nm）解释的变化更大，较低的 10 m 分辨率绿带报告 R2 = 0.85，而缩小比例的 Sentinel 红边点 1 在 5 m 处的 R2 = 0.78。其余哨兵带解释了低得多的变异（最大值为 NIR，R2 = 0.48）。对一阶导数中红边峰区域的研究显示出良好的前景，RIDAmid (R2 = 0.81) 是最佳指数。机器学习方法缩小了调查该试验地点植物状况所需的波段范围，大大缩短了处理时间并降低了处理复杂性。虽然 Sentinel 在此比较中表现良好，并且在大面积作物生产中很有用，但相对于感兴趣区域的像素边界以及粗略的空间和时间分辨率的影响会影响其在研究能力中的效用。
Hyperspectral imaging spectrometers mounted on unmanned aerial vehicle (UAV) can capture high spatial and spectral resolution to provide cotton crop nitrogen status for precision agriculture. The aim of this research was to explore machine learning use with hyperspectral datacubes over agricultural fields. Hyperspectral imagery was collected over a mature cotton crop, which had high spatial (~5.2 cm) and spectral (5 nm) resolution over the spectral range 475–925 nm that allowed discrimination of individual crop rows and field features as well as a continuous spectral range for calculating derivative spectra. The nominal reflectance and its derivatives clearly highlighted the different treatment blocks and were strongly related to N concentration in leaf and petiole samples, both in traditional vegetation indices (e.g., Vogelman 1, R2 = 0.8) and novel combinations of spectra (R2 = 0.85). The key hyperspectral bands identified were at the red-edge inflection point (695–715 nm). Satellite multispectral was compared against the UAV hyperspectral remote sensing’s performance by testing the ability of Sentinel MSI to predict N concentration using the bands in VIS-NIR spectral region. The Sentinel 2A Green band (B3; mid-point 559.8 nm) explained the same amount of variation in N as the hyperspectral data and more than the Sentinel Red Edge Point 1 (B5; mid-point 704.9 nm) with the lower 10 m resolution Green band reporting an R2 = 0.85, compared with the R2 = 0.78 of downscaled Sentinel Red Edge Point 1 at 5 m. The remaining Sentinel bands explained much lower variation (maximum was NIR at R2 = 0.48). Investigation of the red edge peak region in the first derivative showed strong promise with RIDAmid (R2 = 0.81) being the best index. The machine learning approach narrowed the range of bands required to investigate plant condition over this trial site, greatly improved processing time and reduced processing complexity. While Sentinel performed well in this comparison and would be useful in a broadacre crop production context, the impact of pixel boundaries relative to a region of interest and coarse spatial and temporal resolution impacts its utility in a research capacity.