Monitoring the Foliar Nutrients Status of Mango Using Spectroscopy-Based Spectral Indices and PLSR-Combined Machine Learning Models

Remote Sensing - Tập 13 Số 4 - Trang 641
Gopal Ramdas Mahajan1, Bappa Das1, Dayesh Murgaokar1, Ittai Herrmann2, Katja Berger3, R. N. Sahoo4, Kiran Patel1, Ashwini Desai1, Shaiesh Morajkar1, Rahul M. Kulkarni1
1Natural Resource Management, ICAR–Central Coastal Agricultural Research Institute, Old Goa, Goa 403402, India
2The Plant Sensing Laboratory, The Robert H. Smith Institute for Plant Sciences and Genetics in Agriculture, The Robert H. Smith Faculty of Agriculture, Food and Environment, The Hebrew University of Jerusalem, P.O. Box 12, Rehovot 7610001, Israel
3Department of Geography & Remote Sensing Ludwig-Maximilians-Universität München, 80333 Munich, Germany
4Division of Agricultural Physics, ICAR – Indian Agricultural Research Institute, New Delhi 110012, India

Tóm tắt

Conventional methods of plant nutrient estimation for nutrient management need a huge number of leaf or tissue samples and extensive chemical analysis, which is time-consuming and expensive. Remote sensing is a viable tool to estimate the plant’s nutritional status to determine the appropriate amounts of fertilizer inputs. The aim of the study was to use remote sensing to characterize the foliar nutrient status of mango through the development of spectral indices, multivariate analysis, chemometrics, and machine learning modeling of the spectral data. A spectral database within the 350–1050 nm wavelength range of the leaf samples and leaf nutrients were analyzed for the development of spectral indices and multivariate model development. The normalized difference and ratio spectral indices and multivariate models–partial least square regression (PLSR), principal component regression, and support vector regression (SVR) were ineffective in predicting any of the leaf nutrients. An approach of using PLSR-combined machine learning models was found to be the best to predict most of the nutrients. Based on the independent validation performance and summed ranks, the best performing models were cubist (R2 ≥ 0.91, the ratio of performance to deviation (RPD) ≥ 3.3, and the ratio of performance to interquartile distance (RPIQ) ≥ 3.71) for nitrogen, phosphorus, potassium, and zinc, SVR (R2 ≥ 0.88, RPD ≥ 2.73, RPIQ ≥ 3.31) for calcium, iron, copper, boron, and elastic net (R2 ≥ 0.95, RPD ≥ 4.47, RPIQ ≥ 6.11) for magnesium and sulfur. The results of the study revealed the potential of using hyperspectral remote sensing data for non-destructive estimation of mango leaf macro- and micro-nutrients. The developed approach is suggested to be employed within operational retrieval workflows for precision management of mango orchard nutrients.

Từ khóa


Tài liệu tham khảo

Herrmann, I., Vosberg, S.K., Townsend, P.A., and Conley, S.P. (2019). Spectral data collection by dual field-of-view system under changing atmospheric conditions—A case study of estimating early season soybean populations. Sensors, 19.

Weinstein, B.G., Marconi, S., Bohlman, S., Zare, A., and White, E. (2019). Individual tree-crown detection in RGB imagery using semi-supervised deep learning neural networks. Remote Sens., 11.

Osco, 2020, A convolutional neural network approach for counting and geolocating citrus-trees in UAV multispectral imagery, ISPRS J. Photogramm. Remote Sens., 160, 97, 10.1016/j.isprsjprs.2019.12.010

Hunt, 2019, High resolution wheat yield mapping using Sentinel-2, Remote Sens. Environ., 233, 111410, 10.1016/j.rse.2019.111410

Nevavuori, 2019, Crop yield prediction with deep convolutional neural networks, Comput. Electron. Agric., 163, 104859, 10.1016/j.compag.2019.104859

Pham, T.D., Yokoya, N., Bui, D.T., Yoshino, K., and Friess, D.A. (2019). Remote sensing approaches for monitoring mangrove species, structure, and biomass: Opportunities and challenges. Remote Sens., 11.

Zhang, K., Ge, X., Shen, P., Li, W., Liu, X., Cao, Q., Zhu, Y., Cao, W., and Tian, Y. (2019). Predicting rice grain yield based on dynamic changes in vegetation indexes during early to mid-growth stages. Remote Sens., 11.

Herrmann, 2020, Assessment of maize yield and phenology by drone-mounted superspectral camera, Precis. Agric., 21, 51, 10.1007/s11119-019-09659-5

Cui, B., Zhao, Q., Huang, W., Song, X., Ye, H., and Zhou, X. (2019). A new integrated vegetation index for the estimation of winter wheat leaf chlorophyll content. Remote Sens., 11.

Guo, 2019, Estimating leaf chlorophyll content in tobacco based on various canopy hyperspectral parameters, J. Ambient Intell. Humaniz. Comput., 10, 3239, 10.1007/s12652-018-1043-5

Peng, 2020, Estimation of leaf nutrition status in degraded vegetation based on field survey and hyperspectral data, Sci. Rep., 10, 1

Johnson, 2013, Identification of water stress in citrus leaves using sensing technologies, Agronomy, 3, 747, 10.3390/agronomy3040747

Das, 2017, Comparison of different uni-and multi-variate techniques for monitoring leaf water status as an indicator of water-deficit stress in wheat through spectroscopy, Biosyst. Eng., 160, 69, 10.1016/j.biosystemseng.2017.05.007

Gerhards, M., Schlerf, M., Rascher, U., Udelhoven, T., Juszczak, R., Alberti, G., Miglietta, F., and Inoue, Y. (2018). Analysis of airborne optical and thermal imagery for detection of water stress symptoms. Remote Sens., 10.

Loggenberg, K., Strever, A., Greyling, B., and Poona, N. (2018). Modelling water stress in a shiraz vineyard using hyperspectral imaging and machine learning. Remote Sens., 10.

Mahajan, 2014, Using hyperspectral remote sensing techniques to monitor nitrogen, phosphorus, sulphur and potassium in wheat (Triticum aestivum L.), Precis. Agric., 15, 499, 10.1007/s11119-014-9348-7

Mahajan, 2016, Monitoring nitrogen, phosphorus and sulphur in hybrid rice (Oryza sativa L.) using hyperspectral remote sensing, Precis. Agric., 18, 736, 10.1007/s11119-016-9485-2

Zheng, H., Li, W., Jiang, J., Liu, Y., Cheng, T., Tian, Y., Zhu, Y., Cao, W., Zhang, Y., and Yao, X. (2018). A comparative assessment of different modeling algorithms for estimating leaf nitrogen content in winter wheat using multispectral images from an unmanned aerial vehicle. Remote Sens., 10.

Li, F., Wang, L., Liu, J., Wang, Y., and Chang, Q. (2019). Evaluation of leaf N concentration in winter wheat based on discrete wavelet transform analysis. Remote Sens., 11.

Das, 2020, Spectroscopy based novel spectral indices, PCA-and PLSR-coupled machine learning models for salinity stress phenotyping of rice, Spectrochim. Acta Part A Mol. Biomol. Spectrosc., 229, 117983, 10.1016/j.saa.2019.117983

Osco, L.P., Ramos, A.P.M., Pinheiro, M.M.F., Moriya, É.A.S., Imai, N.N., Estrabis, N.V., Ianczyk, F., de Araújo, F.F., Liesenberg, V., and de Castro Jorge, L.A. (2020). Machine learning framework to predict nutrient content in Valencia-Orange leaf hyperspectral measurements. Remote Sens., 12.

Herrmann, I., Vosberg, S.K., Ravindran, P., Singh, A., Chang, H.-X., Chilvers, M.I., Conley, S.P., and Townsend, P.A. (2018). Leaf and canopy level detection of Fusarium virguliforme (sudden death syndrome) in soybean. Remote Sens., 10.

Abdulridha, J., Batuman, O., and Ampatzidis, Y. (2019). UAV-based remote sensing technique to detect citrus canker disease utilizing hyperspectral imaging and machine learning. Remote Sens., 11.

Yao, Z., Lei, Y., and He, D. (2019). Early visual detection of wheat stripe rust using visible/near-infrared hyperspectral imaging. Sensors, 19.

Gold, 2020, Investigating potato late blight physiological differences across potato cultivars with spectroscopy and machine learning, Plant Sci., 295, 110316, 10.1016/j.plantsci.2019.110316

Dibi, 2017, Use of fluorescence and reflectance spectra for predicting okra (Abelmoschus esculentus) yield and macronutrient contents of leaves, Open J. Appl. Sci., 7, 537

Verrelst, 2019, Quantifying vegetation biophysical variables from imaging spectroscopy data: A review on retrieval methods, Surv. Geophys., 40, 589, 10.1007/s10712-018-9478-y

Berger, 2020, Crop nitrogen monitoring: Recent progress and principal developments in the context of imaging spectroscopy missions, Remote Sens. Environ., 242, 111758, 10.1016/j.rse.2020.111758

Kawamura, 2011, Potential for spectral indices to remotely sense phosphorus and potassium content of legume-based pasture as a means of assessing soil phosphorus and potassium fertility status, Int. J. Remote Sens., 32, 103, 10.1080/01431160903439908

Mutanga, 2004, Integrating imaging spectroscopy and neural networks to map grass quality in the Kruger National Park, South Africa, Remote Sens. Environ., 90, 104, 10.1016/j.rse.2003.12.004

Darvishzadeh, 2008, LAI and chlorophyll estimation for a heterogeneous grassland using hyperspectral measurements, ISPRS J. Photogramm. Remote Sens., 63, 409, 10.1016/j.isprsjprs.2008.01.001

Ferwerda, 2005, Nitrogen detection with hyperspectral normalized ratio indices across multiple plant species, Int. J. Remote Sens., 26, 4083, 10.1080/01431160500181044

Ahmed, 2010, Estimation of sugarcane leaf nitrogen concentration using in situ spectroscopy, Int. J. Appl. Earth Obs. Geoinf., 12, S52

Herrmann, 2010, SWIR-based spectral indices for assessing nitrogen content in potato fields, Int. J. Remote Sens., 31, 5127, 10.1080/01431160903283892

Ramoelo, 2012, Regional estimation of savanna grass nitrogen using the red-edge band of the spaceborne RapidEye sensor, Int. J. Appl. Earth Obs. Geoinf., 19, 151

2014, Understanding the optical responses of leaf nitrogen in Mediterranean Holm oak (Quercus ilex) using field spectroscopy, Int. J. Appl. Earth Obs. Geoinf., 26, 105

Li, 2015, Diagnosis of N nutrition of rice using digital image processing technique, J. Plant Nutr. Fertil., 21, 259

Vanbrabant, Y., Tits, L., Delalieux, S., Pauly, K., Verjans, W., and Somers, B. (2019). Multitemporal chlorophyll mapping in pome fruit orchards from remotely piloted aircraft systems. Remote Sens., 11.

Pimstein, 2011, Exploring remotely sensed technologies for monitoring wheat potassium and phosphorus using field spectroscopy, Field Crop. Res., 121, 125, 10.1016/j.fcr.2010.12.001

Lu, 2019, Monitoring leaf potassium content using hyperspectral vegetation indices in rice leaves, Precis. Agric., 21, 324, 10.1007/s11119-019-09670-w

Santoso, 2018, Predicting oil palm leaf nutrient contents in kalimantan, indonesia by measuring reflectance with a spectroradiometer, Int. J. Remote Sens., 40, 7581, 10.1080/01431161.2018.1516323

Li, 2016, Comparison of four chemometric techniques for estimating leaf nitrogen concentrations in winter wheat (Triticum aestivum) based on hyperspectral features, J. Appl. Spectrosc., 83, 240, 10.1007/s10812-016-0276-3

Atzberger, C., Richter, K., Vuolo, F., Darvishzadeh, R., and Schlerf, M. (2011, January 19–21). Why confining to vegetation indices? Exploiting the potential of improved spectral observations using radiative transfer models. Proceedings of the Remote Sensing for Agriculture, Ecosystems, and Hydrology XIII.; International Society for Optics and Photonics, Prague, Czech Republic.

Godfray, 2010, Food security: The challenge of feeding 9 billion people, Science, 327, 812, 10.1126/science.1185383

Liu, 2011, Nondestructive determination of nutritional information in oilseed rape leaves using visible/near infrared spectroscopy and multivariate calibrations, Sci. China Inf. Sci., 54, 598, 10.1007/s11432-011-4198-7

Menesatti, 2010, Estimation of plant nutritional status by Vis–NIR spectrophotometric analysis on orange leaves [Citrus sinensis (L) Osbeck cv Tarocco], Biosyst. Eng., 105, 448, 10.1016/j.biosystemseng.2010.01.003

Axelsson, 2013, Hyperspectral analysis of mangrove foliar chemistry using PLSR and support vector regression, Int. J. Remote Sens., 34, 1724, 10.1080/01431161.2012.725958

Ye, 2020, Estimation and mapping of nitrogen content in apple trees at leaf and canopy levels using hyperspectral imaging, Precis. Agric., 21, 198, 10.1007/s11119-019-09661-x

Ling, 2019, Hyperspectral analysis of leaf pigments and nutritional elements in tallgrass prairie vegetation, Front. Plant Sci., 10, 142, 10.3389/fpls.2019.00142

Guo, 2018, A robust method to estimate foliar phosphorus of rubber trees with hyperspectral reflectance, Ind. Crops Prod., 126, 1, 10.1016/j.indcrop.2018.09.055

Pandey, 2017, High throughput in vivo analysis of plant leaf chemical properties using hyperspectral imaging, Front. Plant Sci., 8, 1348, 10.3389/fpls.2017.01348

Mitchell, T.M. (1997). Machine Learning, McGraw-Hill, Inc.. [1st ed.].

Ball, 2017, Comprehensive survey of deep learning in remote sensing: Theories, tools, and challenges for the community, J. Appl. Remote Sens., 11, 42609, 10.1117/1.JRS.11.042609

Mouazen, 2010, Comparison among principal component, partial least squares and back propagation neural network analyses for accuracy of measurement of selected soil properties with visible and near infrared spectroscopy, Geoderma, 158, 23, 10.1016/j.geoderma.2010.03.001

Tian, 2013, Laboratory assessment of three quantitative methods for estimating the organic matter content of soils in China based on visible/near-infrared reflectance spectra, Geoderma, 202, 161, 10.1016/j.geoderma.2013.03.018

Das, 2018, Evaluation of multiple linear, neural network and penalised regression models for prediction of rice yield based on weather parameters for west coast of India, Int. J. Biometeorol., 62, 1809, 10.1007/s00484-018-1583-6

Krishna, 2019, Comparison of various modelling approaches for water deficit stress monitoring in rice crop through hyperspectral remote sensing, Agric. Water Manag., 213, 231, 10.1016/j.agwat.2018.08.029

Pullanagari, 2016, Mapping of macro and micro nutrients of mixed pastures using airborne AisaFENIX hyperspectral imagery, ISPRS J. Photogram. Remote Sens., 117, 1, 10.1016/j.isprsjprs.2016.03.010

Mutanga, 2005, Estimating tropical pasture quality at canopy level using band depth analysis with continuum removal in the visible domain, Int. J. Remote Sens., 26, 1093, 10.1080/01431160512331326738

Ramoelo, 2011, Water-removed spectra increase the retrieval accuracy when estimating savanna grass nitrogen and phosphorus concentrations, ISPRS J. Photogram. Remote Sens., 66, 408, 10.1016/j.isprsjprs.2011.01.008

Bogrekci, 2005, Spectral phosphorus mapping using diffuse reflectance of soils and grass, Biosyst. Eng., 91, 305, 10.1016/j.biosystemseng.2005.04.015

Sanches, 2013, Seasonal prediction of in situ pasture macronutrients in New Zealand pastoral systems using hyperspectral data, Int. J. Remote Sens., 34, 276, 10.1080/01431161.2012.713528

Mutanga, 2007, Estimating and mapping grass phosphorus concentration in an African savanna using hyperspectral image data, Int. J. Remote Sens., 28, 4897, 10.1080/01431160701253253

Wang, 2015, Evaluating different methods for grass nutrient estimation from canopy hyperspectral reflectance, Remote Sens., 7, 5901, 10.3390/rs70505901

Knox, 2011, Dry season mapping of savanna forage quality, using the hyperspectral carnegie airborne observatory sensor, Remote Sens. Environ., 115, 1478, 10.1016/j.rse.2011.02.007

Zhang, 2013, Detecting macronutrients content and distribution in oilseed rape leaves based on hyperspectral imaging, Biosyst. Eng., 115, 56, 10.1016/j.biosystemseng.2013.02.007

Miphokasap, P., and Wannasiri, W. (2018). Estimations of nitrogen concentration in sugarcane using hyperspectral imagery. Sustainability, 10.

Das, 2019, Comparative analysis of index and chemometric techniques-based assessment of leaf area index (LAI) in wheat through field spectroradiometer, Landsat-8, Sentinel-2 and Hyperion bands, Geocarto Int., 35, 1

Rossel, 2010, Using data mining to model and interpret soil diffuse reflectance spectra, Geoderma, 158, 46, 10.1016/j.geoderma.2009.12.025

FAO (2017). FAO Statistical Programme of Work, FAO.

Ganeshamurthy, 2018, Enhancing mango productivity through sustainable resource management, J. Hortl. Sci., 13, 1, 10.24154/JHS.2018.v13i01.002

Barker, A.V., and Pilbeam, D.J. (2015). Handbook of Plant Nutrition, CRC Press.

Malmir, 2020, Prediction of macronutrients in plant leaves using chemometric analysis and wavelength selection, J. Soils Sediments, 20, 249, 10.1007/s11368-019-02418-z

Ramirez-Lopez, L., and Stevens, A. (2020, December 22). Prospectr: Miscellaneous Functions for Processing and Sample Selection of vis-NIR Diffuse Reflectance Data. Available online: https://github.com/l-ramirez-lopez/prospectr.

Jackson, M.L. (1973). Soil Chemical Analysis, Prentice Hall of India Private Limited Press.

Yoshida, S., Forno, D.A., Cock, J.H., and Gomez, K. (1976). Laboratory Manual for Physiological Studies of Rice, The International Rice Research Institute. [3rd ed.].

Tabatabai, 1970, A simple turbidimetric method of determining total sulfur in plant materials, Agron. J., 62, 805, 10.2134/agronj1970.00021962006200060038x

Friedman, 1991, Multivariate adaptation regression splines, Ann. Stat., 19, 1

Chen, T., and Guestrin, C. XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.

Quinlan, J.R. (1992, January 16–18). Learning with continuous classes. Proceedings of the 5th Australian Joint Conference on Artificial Intelligence, Hobart, Australia.

Kuhn, 2008, Building predictive models in r using the caret package, J. Stat. Softw., 28, 159, 10.18637/jss.v028.i05

R Core Team (2018). R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing.

Chang, 2001, Near-infrared reflectance spectroscopy–principal components regression analyses of soil properties, Soil Sci. Soc. Am. J., 65, 480, 10.2136/sssaj2001.652480x

Salazar, 2020, Emissivity of agricultural soil attributes in southeastern Brazil via terrestrial and satellite sensors, Geoderma, 361, 114038, 10.1016/j.geoderma.2019.114038

Zhang, 2014, Monitoring cotton (Gossypium hirsutum L.) leaf ion content and leaf water content in saline soil with hyperspectral reflectance, Eur. J. Remote Sens., 47, 593, 10.5721/EuJRS20144733

Jayaselan, 2018, Determination of the optimal pre-processing technique for spectral data of oil palm leaves with respect to nutrient, Pertanika J. Sci. Technol., 26, 1169

Mani, 2018, Estimating plant macronutrients using VNIR spectroradiometry, Pol. J. Environ. Stud., 28, 1831, 10.15244/pjoes/89585

Chemura, 2017, Separability of coffee leaf rust infection levels with machine learning methods at Sentinel-2 MSI spectral resolutions, Precis. Agric., 18, 859, 10.1007/s11119-016-9495-0

Baret, 2007, Quantification of plant stress using remote sensing observations and crop models: The case of nitrogen management, J. Exp. Bot., 58, 869, 10.1093/jxb/erl231

Xu, 2018, Monitoring ratio of carbon to nitrogen (C/N) in wheat and barley leaves by using spectral slope features with branch-and-bound algorithm, Sci. Rep., 8, 1

Shi, 2015, Estimating leaf nitrogen concentration in heterogeneous crop plants from hyperspectral reflectance, Int. J. Remote Sens., 36, 4652, 10.1080/01431161.2015.1088676

Wang, B.J., Chen, J.M., Ju, W., Qiu, F., Zhang, Q., Fang, M., and Chen, F. (2017). Limited effects of water absorption on reducing the accuracy of leaf nitrogen estimation. Remote Sens., 9.

Chemura, 2018, Mapping spatial variability of foliar nitrogen in coffee (Coffea arabica L.) plantations with multispectral Sentinel-2 MSI data, ISPRS J. Photogramm. Remote Sens., 138, 1, 10.1016/j.isprsjprs.2018.02.004

Loozen, 2019, Exploring the use of vegetation indices to sense canopy nitrogen to phosphorous ratio in grasses, Int. J. Appl. Earth Obs. Geoinf., 75, 1

Feret, 2008, PROSPECT-4 and 5: Advances in the leaf optical properties model separating photosynthetic pigments, Remote Sens. Environ., 112, 3030, 10.1016/j.rse.2008.02.012

Mutanga, 2004, Predicting in situ pasture quality in the Kruger National Park, South Africa, using continuum-removed absorption features, Remote Sens. Environ., 89, 393, 10.1016/j.rse.2003.11.001

Kumar, 1975, Multicollinearity in regression analysis, Rev. Econ. Stat., 57, 365, 10.2307/1923925

Hawkins, 2004, The problem of overfitting, J. Chem. Inf. Comput. Sci., 44, 1, 10.1021/ci0342472

Xue, 2014, Topdressing nitrogen recommendation for early rice with an active sensor in south China, Precis. Agric., 15, 95, 10.1007/s11119-013-9326-5

Yu, 2015, Estimate leaf chlorophyll of rice using reflectance indices and partial least squares, Photogramm. Fernerkundung Geoinf., 2015, 45, 10.1127/pfg/2015/0253

Ryan, 2016, Application of a partial least-squares regression model to retrieve chlorophyll-a concentrations in coastal waters using hyper-spectral data, Ocean Sci. J., 51, 209, 10.1007/s12601-016-0018-8

Baranowski, P., Jedryczka, M., Mazurek, W., Babula-Skowronska, D., and Siedliska, A. (2015). Hyperspectral and thermal imaging of oilseed rape (Brassica napus) response to fungal species of the Genus Alternaria. PLoS ONE, 10.

Singh, 2016, Machine learning for high-throughput stress phenotyping in plants, Trends Plant Sci., 21, 110, 10.1016/j.tplants.2015.10.015

Vasques, 2008, Comparison of multivariate methods for inferential modeling of soil carbon using visible/near-infrared spectra, Geoderma, 146, 14, 10.1016/j.geoderma.2008.04.007