Inversion of Nitrogen Concentration in Apple Canopy Based on UAV Hyperspectral Images

As the major nutrient affecting crop growth, accurate assessing of nitrogen (N) is crucial to precise agricultural management. Although improvements based on ground and satellite data nitrogen in monitoring crops have been made, the application of these technologies is limited by expensive costs, covering small spatial scales and low spatiotemporal resolution. This study strived to explore an effective approach for inversing and mapping the distributions of the canopy nitrogen concentration (CNC) based on Unmanned Aerial Vehicle (UAV) hyperspectral image data in a typical apple orchard area of China. A Cubert UHD185 imaging spectrometer mounted on a UAV was used to obtain the hyperspectral images of the apple canopy. The range of the apple canopy was determined by the threshold method to eliminate the effect of the background spectrum from bare soil and shadow. We analyzed and screened out the spectral parameters sensitive to CNC, including vegetation indices (VIs), random two-band spectral indices, and red-edge parameters. The partial least squares regression (PLSR) and backpropagation neural network (BPNN) were constructed to inverse CNC based on a single spectral parameter or a combination of multiple spectral parameters. The results show that when the thresholds of normalized difference vegetation index (NDVI) and normalized difference canopy shadow index (NDCSI) were set to 0.65 and 0.45, respectively, the canopy’s CNC range could be effectively identified and extracted, which was more refined than random forest classifier (RFC); the correlation between random two-band spectral indices and nitrogen concentration was stronger than that of other spectral parameters; and the BPNN model based on the combination of random two-band spectral indices and red-edge parameters was the optimal model for accurately retrieving CNC. Its modeling determination coefficient (R2) and root mean square error (RMSE) were 0.77 and 0.16, respectively; and the validation R2 and residual predictive deviation (RPD) were 0.75 and 1.92. The findings of this study can provide a theoretical basis and technical support for the large-scale, rapid, and non-destructive monitoring of apple nutritional status.

[1]  A. Aquino,et al.  A Methodology for the Automated Delineation of Crop Tree Crowns from UAV-Based Aerial Imagery by Means of Morphological Image Analysis , 2021, Agronomy.

[2]  F. Marinello,et al.  Economic Comparison of Satellite, Plane and UAV-Acquired NDVI Images for Site-Specific Nitrogen Application: Observations from Italy , 2021, Agronomy.

[3]  Guijun Yang,et al.  Inversion reflectance by apple tree canopy ground and unmanned aerial vehicle integrated remote sensing data , 2021, Journal of Plant Research.

[4]  Takuya Togawa,et al.  Remotely sensed tree canopy cover-based indicators for monitoring global sustainability and environmental initiatives , 2021, Environmental Research Letters.

[5]  Scott A. Shearer,et al.  Remote Sensing in Agriculture - Accomplishments, Limitations, and Opportunities , 2020, Remote. Sens..

[6]  Rui Wang,et al.  Estimation of the vertically integrated leaf nitrogen content in maize using canopy hyperspectral red edge parameters , 2020 .

[7]  Guijun Yang,et al.  Estimation of Nitrogen Content on Apple Tree Canopy through Red-Edge Parameters from Fractional-Order Differential Operators using Hyperspectral Reflectance , 2020, Journal of the Indian Society of Remote Sensing.

[8]  Thomas Lagkas,et al.  A compilation of UAV applications for precision agriculture , 2020, Comput. Networks.

[9]  Xiaodong Yang,et al.  Estimation of Crop Growth Parameters Using UAV-Based Hyperspectral Remote Sensing Data , 2020, Sensors.

[10]  Chong Wang,et al.  Correlation of production constraints with the yield gap of apple cropping systems in Luochuan County, China , 2019, Journal of Integrative Agriculture.

[11]  Jia Tian,et al.  Analysis of Vegetation Red Edge with Different Illuminated/Shaded Canopy Proportions and to Construct Normalized Difference Canopy Shadow Index , 2019, Remote. Sens..

[12]  Xujun Ye,et al.  Estimation and mapping of nitrogen content in apple trees at leaf and canopy levels using hyperspectral imaging , 2019, Precision Agriculture.

[13]  P. Miphokasap,et al.  Estimations of Nitrogen Concentration in Sugarcane Using Hyperspectral Imagery , 2018 .

[14]  F. Maupas,et al.  Retrieving LAI, chlorophyll and nitrogen contents in sugar beet crops from multi-angular optical remote sensing: Comparison of vegetation indices and PROSAIL inversion for field phenotyping , 2017 .

[15]  Yanjie Wang,et al.  Estimation of Winter Wheat Above-Ground Biomass Using Unmanned Aerial Vehicle-Based Snapshot Hyperspectral Sensor and Crop Height Improved Models , 2017, Remote. Sens..

[16]  Baofeng Su,et al.  Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications , 2017, J. Sensors.

[17]  Mairaj Din,et al.  Evaluating Hyperspectral Vegetation Indices for Leaf Area Index Estimation of Oryza sativa L. at Diverse Phenological Stages , 2017, Front. Plant Sci..

[18]  Rebecca L. Whetton,et al.  Machine learning based prediction of soil total nitrogen, organic carbon and moisture content by using VIS-NIR spectroscopy , 2016 .

[19]  Ronghua Ma,et al.  Estimating the Total Nitrogen Concentration of Reed Canopy with Hyperspectral Measurements Considering a Non-Uniform Vertical Nitrogen Distribution , 2016, Remote. Sens..

[20]  Marco Heurich,et al.  Vegetation Indices for Mapping Canopy Foliar Nitrogen in a Mixed Temperate Forest , 2016, Remote. Sens..

[21]  Jan G. P. W. Clevers,et al.  Optical remote sensing and the retrieval of terrestrial vegetation bio-geophysical properties - A review , 2015 .

[22]  Lixin Zhang,et al.  15NITROGEN STUDY ON ABSORPTION, DISTRIBUTION AND UTILIZATION OF NITROGEN APPLIED IN EARLY SUMMER IN RED FUJI APPLE , 2012 .

[23]  X. Yao,et al.  Assessing newly developed and published vegetation indices for estimating rice leaf nitrogen concentration with ground- and space-based hyperspectral reflectance , 2011 .

[24]  P. Reich,et al.  Leaf physiological versus morphological acclimation to high-light exposure at different stages of foliar development in oak. , 2008, Tree physiology.

[25]  M. Cho,et al.  A new technique for extracting the red edge position from hyperspectral data: The linear extrapolation method , 2006 .

[26]  Haidong Zhang,et al.  A Review of Unmanned Aerial Vehicle Low-Altitude Remote Sensing (UAV-LARS) Use in Agricultural Monitoring in China , 2021, Remote. Sens..

[27]  Lin Gao,et al.  Research on multispectral-image-based NDVI shadow-effect-eliminating model , 2020, National Remote Sensing Bulletin.

[28]  H. Xie,et al.  Modeling grassland above-ground biomass based on artificial neural network and remote sensing in the Three-River Headwaters Region , 2018 .

[29]  Qiang Zhang,et al.  [Multivariate analysis of relationship between soil nutrient factors and fruit quality characte-ristic of 'Fuji' apple in two dominant production regions of China]. , 2017, Ying yong sheng tai xue bao = The journal of applied ecology.