Machine Learning Optimised Hyperspectral Remote Sensing Retrieves Cotton Nitrogen Status

Abstract

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 (B4; 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.

Dissection of Hyperspectral Reflectance to Estimate Photosynthetic Characteristics in Upland Cotton (Gossypium hirsutum L.) under Different Nitrogen Fertilizer Application Based on Machine Learning Algorithms

“…Research has indicated that the spectral characteristics of plant canopy reflections are closely related to several biochemical and biophysical properties, such as pigment concentrations [ 31 , 32 ], plant vigor [ 33 , 34 ], water status [ 35 , 36 ], and nutritional status [ 37 , 38 ]. Different nitrogen states in cotton cause reflectance changes in multiple bands of the spectrum, such as 550–700 nm [ 39 ], 705–715 nm [ 40 ], and 1325–1575 nm [ 41 ]. Hyperspectral remote sensing plays an important role in plant nitrogen nutrition monitoring as a cutting–edge technology.…”

Variation of Nitrogen, Phosphorus, and Potassium Contents in Drip-Irrigated Cotton at Different Yield Levels under Combined Effects of Nitrogen, Phosphorus and Potassium

“…Research has demonstrated that N, P, and K contents and accumulation could provide a reliable evaluation of the crop growth conditions and yield predictions [11,12]. Several studies have used unmanned aerial vehicles, satellite remote sensing [13][14][15], machine vision, and neural networks to monitor the nutritional status of crops [16,17]. However, the above studies mainly focused on the methods and platforms without considering that the different nutrient distribution leads to different cotton yields.…”

Canopy Nitrogen Estimation on Cotton Plant Using Satellite Imagery

“…Machine learning can be used to estimate nitrogen levels on crop leaves using satellite imagery by collecting data, extracting relevant features, training a machine learning model, and validating the model. Marang et al (2021) proposed hybrid random forest regression, DBSCAN, and PCA to predict N level on cotton crop using hyperspectral UAV and sentinel imagery. Huang et al (2015) estimated rice nitrogen status based on satellite imagery.…”