Machine learning methods for crop chlorophyll variable retrieval

Fenghua Yu, Tongyu Xu, Chunling Chen, Wen Du, Shuai Feng

Abstract


Abstract: Hyperspectral remote sensing technology improves the retrieval ability of chlorophyll content in crops.  The machine learning method has been developed and applied to crop phenotyping information inversion.  This study combined radiative transfer model (PROSPECT-4) and Gauss Process Regression algorithm (GPR) to retrieval crop leaf chlorophyll content.  The test was conducted in the eastern city of Shenyang, Liaoning Province, China with a japonica rice.  This paper describes (1) The PROSPECT-4 model was analyzed by GSA tool, and the sensitivity band range of crop chlorophyll was at 400-750 nm.  (2) The chlorophyll content model was established with great accuracy (R2=0.8638) that can predict the crop leaf chlorophyll content; (3) Theresults demonstrated that crop chlorophyll is inversion by PROSPECT model and machine learning algorithm.  Therefore,crop chlorophyll content can be estimated by hyperspectral datathat may be used for cropgrowth management.  This research can provide an efficient method to detect crop leaf chlorophyll content at the RTMS in the future.

Keywords: Gaussian Processes Regression, hyperspectral remote sensing, leaf chlorophyll, machine learning, PROSPECT

DOI: 10.33440/j.ijpaa.20180101.0006

Citation:Yu F H, Xu T Y, Chen C L, Du W, Feng S A.  Machine learning methods for crop chlorophyll variable retrieval.  Int J Precis Agric Aviat, 2018; 1(1): 32–36.


Full Text:

PDF Word

References


Habib, A., Han, Y., Xiong, W., He, F., Zhang, Z., & Crawford, M. Automated Ortho-Rectification of UAV-Based Hyperspectral Data over an Agricultural Field Using Frame RGB Imagery. Remote Sensing, 2016; 8(10): 1–22.

Fenghua, Y, Tongyu, X, Yingli, C, Guijun, Y, Wen, D, & Shu, W. Models for estimating the leaf NDVI of japonica rice on a canopy scale by combining canopy NDVI and multisource environmental data in Northeast China. International Journal of Agricultural and Biological Engineering, 2016; 9(5): 132–141.

Homolova, L, Malenovský, Z, Clevers, J. G, García-Santos, G., & Schaepman, M. E. Review of optical-based remote sensing for plant trait mapping. Ecological Complexity, 2013; 15, 1–16.

Khodadadzadeh, M., Li, J., Prasad, S., & Plaza, A. Fusion of hyperspectral and LiDAR remote sensing data using multiple feature learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2015; 8(6): 2971–2983.

Verrelst, J., Rivera, J. P., Tol, C. V. D., Magnani, F., Mohammed, G., & Moreno, J. Global sensitivity analysis of the scope model: what drives simulated canopy-leaving sun-induced fluorescence. Remote Sensing of Environment, 2015; 166, 8–21.

Yang, H. L, Crawford, M. M. Spectral and spatial proximity-based manifold alignment for multitemporal hyperspectral image classification. IEEE Transactions on Geoscience & Remote Sensing, 2016; 54(1): 51–64.

Barry Haack, Ann Rafter. Regression estimation techniques with remote sensing: a review and case study. Geocarto International, 2009; 25(1): 71–82.

Yu F H, Xu T Y, Cao Y L, Yang G J, Du W, Wang S. Models for estimating the leaf NDVI of japonica rice on a canopy scale by combining canopy NDVI and multisource environmental data in Northeast China. Int J Agric & Biol Eng,2016; 09(05): 132-142.

Kira, O., Dubowski, Y., & Linker, R. Reconstruction of passive open-path ftir ambient spectra using meteorological measurements and its application for detection of aerosol cloud drift. Optics Express, 2015; 23(15): 916–29.

Boegh, E., Soegaard, H., Thomsen, A., & Hansen, S. Multi-scale remote sensing based estimation of leaf area index and nitrogen concentration for photosynthesis modelling. Geoscience and Remote Sensing Symposium, 2003. IGARSS '03. Proceedings. 2003 IEEE International (Vol.4, pp.2847–2849 vol.4). IEEE.

Chappelle, E. W., Kim, M. S., & Jeiii, M. M. Ratio analysis of reflectance spectra (rars): an algorithm for the remote estimation of the concentrations of chlorophyll a, chlorophyll b, and carotenoids in soybean leaves. Remote Sensing of Environment, 1992; 39(3): 239–247.

Filella, I., Serrano, L., Serra, J., & Penuelas, J. Evaluating wheat nitrogen status with canopy reflectance indices and discriminant analysis. Crop Science, 1995; 35(5): 1400–1405.

Blackburn, G. A. Quantifying chlorophylls and caroteniods at leaf and canopy scales: an evaluation of some hyperspectral approaches. Remote Sensing of Environment, 1998; 66(3): 273–285.

Baret, F., Buis, S. Estimating Canopy Characteristics from Remote Sensing Observations: Review of Methods and Associated Problems. Advances in Land Remote Sensing. Springer Netherlands. 2008.

Darvishzadeh, R., Skidmore, A., Schlerf, M., & Atzberger, C. Inversion of a radiative transfer model for estimating vegetation lai and chlorophyll in a heterogeneous grassland. Remote Sensing of Environment, 2008; 112(5): 2592–2604.

Verrelst, J., Rivera, J. P., Leoneko, G., Alonso, L., Moreno, J. Optimizing LUT-based RTM Inversion for Semiautomatic Mapping of Crop Biophysical Parameters from Sentinel-2 and -3 data: Role of Cost Functions. IEEE Transactions on Geoscience and Remote Sensing, 2014; 52(1): 257–269.

Rivera, J.P., Verrelst, J., Gómez-Dans, J., Muñoz-Marí, J., Moreno, J., Camps-Valls, G. An Emulator Toolbox to Approximate Radiative Transfer Models with Statistical Learning. Remote Sensing, 2015; p. 7, 9347–9370.

Hosgood, B., Jacquemoud, S., Andreoli, G., Verdebout, J., Pedrini, G., & Schmuck, G. Leaf optical properties experiment 93 (lopex93). 1994.

Jacquemoud, S., & Baret, F. Prospect: a model of leaf optical properties spectra. Remote Sensing of Environment, 1990; 34(2): 75–91.

Feret, J. B., François, C., Asner, G. P., Gitelson, A. A., Martin, R. E., & Bidel, L. P. R., et al. Prospect-4 and 5: advances in the leaf optical properties model separating photosynthetic pigments. Remote Sensing of Environment, 2008; 112(6): 3030–3043.

Jacquemoud, S., Ustin, S. L., Verdebout, J., Schmuck, G., Andreoli, G., & Hosgood, B. Estimating leaf biochemistry using the prospect leaf optical properties model. Remote Sensing of Environment, 1996; 56(3): 194–202.

Laurent, E. J., Shi, H., Gatziolis, D., Lebouton, J. P., Walters, M. B., & Liu, J. Using the spatial and spectral precision of satellite imagery to predict wildlife occurrence patterns. Remote Sensing of Environment, 2005; 97(97): 249–262.

Mousivand, A., Menenti, M., Gorte, B., & Verhoef, W. Global sensitivity analysis of the spectral radiance of a soil–vegetation system. Remote Sensing of Environment, 2014; 145(5): 131–144.

Verrelst, J., Rivera, J.P., Moreno, J. ARTMO's global sensitivity analysis (GSA) toolbox to quantify driving variables of leaf and canopy radiative transfer models. EARSeL eProceedings, Speical Issue 2: 9th EARSeL Imaging Spectroscopy Workshop, 2015; 1–11

Sobol', I. M. On sensitivity estimation for nonlinear mathematical models. Keldysh Applied Mathematics Institute, 1990; 2(1): 112–118.

Verrelst, J., Rivera, J.P., Moreno, J. ARTMO's global sensitivity analysis (GSA) toolbox to quantify driving variables of leaf and canopy radiative transfer models. In: 9th EARSEL SIG Imaging Spectroscopy Workshop, 14-16 April, Luxembourg, 2015.

Williams, Christopher, K. I., Rasmussen, & Edward, C. Gaussian Processes For Machine Learning. Gaussian processes for machine learning /. MIT Press. 2006.

Verrelst, J., Rivera, J. P., Gitelson, A., Delegido, J., Moreno, J., & Camps-Valls, G. Spectral band selection for vegetation properties retrieval using gaussian processes regression. International Journal of Applied Earth Observation & Geoinformation, 2016; 52, 554–567.

Rasmussen, J., Sommerlarsen, J., Pedersen, K., Toft, S., Benson, A., & Bower, R. G., et al. Investigating hot gas in the halos of two massive spirals: observations and cosmological simulations, 2006.

Verrelst, J., Rivera, J.P., Moreno, J. From model simulations towards vegetation properties mapping: automating, optimizing & simplifying. In: ISSI Workshop on Exploring the Earth’s Ecostystems on a Global Scale: Requirements, Capabilities and Directions in Spaceborne Imaging Spectroscopy, 21-25 November, Bern, Switzerland. 2016.


Refbacks

  • There are currently no refbacks.