Collaborative inverse modeling of nitrogen and phosphorus content in rice based on WOA-ELM

Fenghua Yu, Shuang Xiang, Zhonghui Guo, Honggang Zhang, Juchi Bai, Tongyu Xu

Abstract


Abstract: Nitrogen and phosphorus play an important role in the growth and development of crops, and the accurate acquisition of information on crop nitrogen and phosphorus nutrient levels is of great significance in terms of accurate crop management and saving planting costs.  To address the problem that previous single-element monitoring has led to difficulties in synergy between inversion models, this paper proposes a method based on a whale algorithm with an extreme learning machine to achieve synergistic inversion of nitrogen and phosphorus content in rice, and demonstrates the feasibility of using spectral data to invert nitrogen and phosphorus simultaneously.  In this paper, an unmanned aircraft hyperspectral remote sensing platform was used to acquire hyperspectral remote sensing images of the canopy of japonica rice at key fertility stages, and agronomic information was sampled simultaneously on ground.  The hyperspectral data were downscaled by principal component analysis (PCA) and discrete wavelet multiscale decomposition (DWT), and the filtered feature vectors were used as input and the measured nitrogen and phosphorus content as output.  Two models, the limit learning machine and the limit learning machine based on the whale algorithm, were used to collaboratively estimate the nitrogen and phosphorus content of japonica rice at critical fertility stages, and the following conclusions were drawn: 1) The inversion accuracy of both models for nitrogen The R2 of the training set was above 0.64 and the R2 of the validation set was above 0.56.  2) The dimensionality reduction method using wavelet decomposition was more representative than that of principal component analysis in filtering feature vectors, and it was the best for phosphorus inversion.  3) Overall, the WOA-ELM model was better than the ELM model in estimation, with the R2 of nitrogen inversion reaching up to this model has greatly improved the efficiency of obtaining the nutrient content of rice leaves.

Keywords: rice, nitrogen, phosphorus, hyperspectral, whale algorithm, extreme learning machine

DOI: 10.33440/j.ijpaa.20220501.184

 

Citation: Yu F H, Xiang S, Guo Z H, Zhang H G, Bai J C, Xu T Y.  Collaborative inverse modeling of nitrogen and phosphorus content in rice based on WOA-ELM.  Int J Precis Agric Aviat, 2022; 5(1): 1–9.

Full Text:

PDF

References


Thomas J R , Oerther G F . Estimating Nitrogen Content Of Sweet Pepper Leaves by Reflectance Measurements. Agronomy journal, 1972, 64(1): 11–13. Doi: 10.2134/agronj1972.00021962006400010004x.

Kokaly R F. Investigating a Physical Basis for Spectroscopic Estimates of Leaf Nitrogen Concentration. Remote Sensing of Environment, 2001, 75(2): 153–161. Doi: 10.1016/S0034-4257(00)00163-2.

Osborne S L, Schepers J S, Francis D D , et al. Detection of Phosphorus and Nitrogen Deficiencies in Corn Using Spectral Radiance Measurements. Agronomy Journal, 2002, 94(6). Doi: 10.2134/agronj2002.1215.

Huang G B , Zhu Q Y , Siew C K. Extreme learning machine: Theory and applications. Neurocomputing, 2006, 70(1/3): 489–501. Doi: 10.1016/ j.neucom.2005.12.126.

Gupta R K, Vijayan D, Prasad T S. Comparative analysis of red-edge hyperspectral indices. Advances in Space Research, 2003, 32(11): 2217–2222. Doi: 10.1016/S0273-1177(03)90545-X.

Haboudane D. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture. Remote Sensing of Environment, 2004, 90. Doi: 10.1016/j.rse.2003.12.013.

Broge N H, Leblanc E. Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density. Remote Sensing of Environment, 2001, 76(2): 156–172. Doi: 10.1016/ S0034-4257(00)00197-8.

Chen P, Haboudane D, Tremblay N, et al. New spectral indicator assessing the efficiency of crop nitrogen treatment in corn and wheat. Remote Sensing of Environment, 2010, 114(9): 1987–1997. Doi: 10.1016/j.rse.2010.04.006.

Li B, Liew O W, Asundi A K. Pre-visual detection of iron and phosphorus deficiency by transformed reflectance spectra. Journal of Photochemistry & Photobiology B Biology, 2006, 85(2): 131–139. Doi: 10.1016/ j.jphotobiol.2006.06.005.

K Müller, Bttcher U, Meyer-Schatz F, et al. Analysis of vegetation indices derived from hyperspectral reflection measurements for estimating crop canopy parameters of oilseed rape (Brassica napus L.). Academic Press, 2008(2). Doi: 10.1016/J.BIOSYSTEMSENG.2008.07.004.

Fitzgerald G, Rodriguez D, Garry O. Measuring and predicting canopy nitrogen nutrition in wheat using a spectral index?The canopy chlorophyll content index (CCCI). Field Crops Research, 2010, 3(116): 318–324.

Burgos, X.P., Angela, R., Alberto, T., Gonzalo, P. Analysis of natural images processing for the extraction of agricultural elements. Image and Vision Computing, 2010, 28(1): 138–149. Doi: 10.1016/ j.imavis.2009.05.009.

Xu G L, Zhang F L, Shah, et al. Use of leaf color images to identify nitrogen and potassium deficient tomatoes. Pattern Recognition Letters, 2011, 32(11): 1584–1590. Doi: 10.1016/

j.patrec.2011.04.020.

Cai W S, Li Y K, Shao X G? A variable selection method based on uninformative variable elimination for multivariate calibration of near-infrared spectra?Chemometrics and Intelligent Laboratory Systems, 2008, 90(2): 188–194. Doi: 10.1016/j.chemolab.2007.10.001.

Osborne S L, Schepers J S, Francis D D, Schlemmer M R. Detection of phosphorus and nitrogen deficiencies in corn using spectral radiance measurements. Agronomy Journal, 2002, 94: 1215–1221. Doi: 10.2134/agronj2002.1215.

Menesatti P, Antonucci F, Pallottino F, Roccuzzo G, Allegra M, Stagno F, Intriglioio F. Estimation of plant nutritional status by Vis-NIR spectrophotometric analysis on orange leaves. Biosystems engineering, 2010, 105(4): 448–454. Doi: 10.1016/ j.biosystemseng.2010.01.003.

Bronson K F, Chua T T, Booker J D, et al.. In-season nitrogen status in irrigated cotton II leaf nitrogen and biomass. Soil Science Society of American Journal, 2003(07): 1439–1448.

Hamm J, Lee D. Separating pose and expression in face images: a manifold learning approach. Neural Information Processing-Letters and Reviews, 2007(04): 91–100.

Ma J F, Yamaji N, Mitani N, et al. Transporters of arsenitein rice and their role in arsenic accumulation in rice grain. Proceedings of the National Academy of Sciences ofthe United States of America, 2008, 105(29): 9931–9935. Doi: 10.1073/pnas.0802361105.

Asmhm Talukder, Ca Meisner, Mar Sarkar, et al. Effect ofwater management, arsenic and phosphorus levels on ricein a high -arsenic soil -water system: II. arsenic uptake .Ecotoxicology Environmental Safety, 2012, 80(80): 145–151. Doi: 10.1016/S1672-6308(13)60172-9.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.