Hyperspectral Inversion of Phragmites Communis Carbon, Nitrogen, and Phosphorus Stoichiometry Using Three Models

Studying the stoichiometric characteristics of plant C, N, and P is an effective way of understanding plant survival and adaptation strategies. In this study, 60 fixed plots and 120 random plots were set up in a reed-swamp wetland, and the canopy spectral data were collected in order to analyze the stoichiometric characteristics of C, N, and P across all four seasons. Three machine models (random forest, RF; support vector machine, SVM; and back propagation neural network, BPNN) were used to study the stoichiometric characteristics of these elements via hyperspectral inversion. The results showed significant differences in these characteristics across seasons. The RF model had the highest prediction accuracy concerning the stoichiometric properties of C, N, and P. The R2 of the four-season models was greater than 0.88, 0.95, 0.97, and 0.92, respectively. According to the root mean square error (RMSE) results, the model error of total C (TC) inversion is the smallest, and that of C/N inversion is the largest. The SVM yielded poor predictive results for the stoichiometric properties of C, N, and P. The R2 of the four-season models was greater than 0.82, 0.81, 0.81, and 0.70, respectively. According to RMSE results, the model error of TC inversion is the smallest, and that of C/P inversion is the largest. The BPNN yielded high stoichiometric prediction accuracy. The R2 of the four-season models was greater than 0.87, 0.96, 0.84, and 0.90, respectively. According to RMSE results, the model error of TC inversion is the smallest, and that of C/P inversion is the largest. The accuracy and stability of the results were verified by comprehensive analysis. The RF model showed the greatest prediction stability, followed by the BPNN and then the SVM models. The results indicate that the accuracy and stability of the RF model were the highest. Hyperspectral data can be used to accurately invert the stoichiometric characteristics of C, N, and P in wetland plants. It provides a scientific basis for the long-term dynamic monitoring of plant stoichiometry through hyperspectral data in the future.

[1]  Peter Reichert,et al.  A generic framework for deriving process stoichiometry in environmental models , 2010, Environ. Model. Softw..

[2]  Monica Beltrami,et al.  A grid-quadtree model selection method for support vector machines , 2020, Expert Syst. Appl..

[3]  J. Elser,et al.  Ecological Stoichiometry: The Biology of Elements from Molecules to the Biosphere , 2002 .

[4]  Liang Tang,et al.  Non-destructive Assessment of Plant Nitrogen Parameters Using Leaf Chlorophyll Measurements in Rice , 2016, Front. Plant Sci..

[5]  Mark G. Tjoelker,et al.  Universal scaling of respiratory metabolism, size and nitrogen in plants , 2006, Nature.

[6]  F. Chapin,et al.  Principles of Terrestrial Ecosystem Ecology , 2002, Springer New York.

[7]  Liu,et al.  Random forest algorithm and regional applications of spectral inversion model for estimating canopy nitrogen concentration in rice , 2014, National Remote Sensing Bulletin.

[8]  Junjie Wang,et al.  A Wavelet-Based Area Parameter for Indirectly Estimating Copper Concentration in Carex Leaves from Canopy Reflectance , 2015, Remote. Sens..

[9]  Wei Li,et al.  Suitability of hyperspectral data for monitoring nitrogen and phosphorus content in constructed wetlands , 2020 .

[10]  J. Schjoerring,et al.  Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression , 2003 .

[11]  Karl J. Niklas,et al.  Nitrogen/phosphorus leaf stoichiometry and the scaling of plant growth , 2005 .

[12]  Jordi Sardans,et al.  Ecology: Elementary factors , 2009, Nature.

[13]  Iryna Dronova,et al.  Indicators of vegetation development in restored wetlands , 2018, Ecological Indicators.

[14]  Ashish Ghosh,et al.  PCA, Kernel PCA and Dimensionality Reduction in Hyperspectral Images , 2018 .

[15]  Pablo J. Zarco-Tejada,et al.  Early Detection and Quantification of Verticillium Wilt in Olive Using Hyperspectral and Thermal Imagery over Large Areas , 2015, Remote. Sens..

[16]  H. Xie,et al.  Modeling alpine grassland forage phosphorus based on hyperspectral remote sensing and a multi-factor machine learning algorithm in the east of Tibetan Plateau, China , 2019, ISPRS Journal of Photogrammetry and Remote Sensing.

[17]  Wei Li,et al.  Analyzing the performance of statistical models for estimating leaf nitrogen concentration of Phragmites australis based on leaf spectral reflectance , 2019, Spectroscopy Letters.

[18]  Ulrich Nöth,et al.  Cartilage Development, Physiology, Pathologies, and Regeneration , 2009 .

[19]  Li Dan,et al.  Research on method for extracting vegetation information based on hyperspectral remote sensing data. , 2010 .

[20]  Y. Kuang,et al.  Biological Stoichiometry: An Ecological Perspective on Tumor Dynamics , 2003 .

[21]  Wei Li,et al.  Estimation of above-ground biomass of reed (Phragmites communis) based on in situ hyperspectral data in Beijing Hanshiqiao Wetland, China , 2018, Wetlands Ecology and Management.

[22]  Robert W. Sterner,et al.  Algal nutrient limitation and the nutrition of aquatic herbivores , 1994 .

[23]  William F. Fagan,et al.  Nutritional constraints in terrestrial and freshwater food webs , 2000, Nature.

[24]  Guijun Yang,et al.  A Comparison of Regression Techniques for Estimation of Above-Ground Winter Wheat Biomass Using Near-Surface Spectroscopy , 2018, Remote. Sens..

[25]  Onisimo Mutanga,et al.  High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[26]  Ling Wang,et al.  [Hyperspectral Estimation of Apple Tree Canopy LAI Based on SVM and RF Regression]. , 2016, Guang pu xue yu guang pu fen xi = Guang pu.

[27]  Wang Xiaoping,et al.  Spectral response characteristics and identification of typical plant species in Ebinur lake wetland national nature reserve (ELWNNR) under a water and salinity gradient , 2017 .

[28]  Kazuhide Hayakawa,et al.  NUTRIENT LIMITATION REDUCES FOOD QUALITY FOR ZOOPLANKTON: DAPHNIA RESPONSE TO SESTON PHOSPHORUS ENRICHMENT , 2001 .

[29]  Anthony F. Michaels.  The Ratios of Life , 2003, Science.

[30]  E. K. Hall,et al.  Linking Microbial and Ecosystem Ecology Using Ecological Stoichiometry: A Synthesis of Conceptual and Empirical Approaches , 2011, Ecosystems.

[31]  James S. Schepers,et al.  Detection of Phosphorus and Nitrogen Deficiencies in Corn Using Spectral Radiance Measurements , 2002 .

[32]  Ziliang Guo,et al.  Estimating leaf mercury content in Phragmites australis based on leaf hyperspectral reflectance , 2020 .

[33]  W. Ceusters,et al.  Quality assurance, infection surveillance, and hospital information systems: avoiding the Bermuda Triangle. , 1994, Infection control and hospital epidemiology.

[34]  Xu Pan,et al.  Hyperspectral inversion of Suaeda salsa biomass under different types of human activity in Liaohe Estuary wetland in north-eastern China , 2020 .

[35]  James Elser,et al.  Biological Stoichiometry: A Chemical Bridge between Ecosystem Ecology and Evolutionary Biology , 2006, The American Naturalist.

[36]  K. Moffett,et al.  Remote Sens , 2015 .

[37]  Colin S. Reynolds,et al.  The ecology of freshwater phytoplankton , 1984 .

[38]  Ben Somers,et al.  The functional characterization of grass- and shrubland ecosystems using hyperspectral remote sensing: trends, accuracy and moderating variables , 2018 .

[39]  Jordi Sardans,et al.  The C:N:P stoichiometry of organisms and ecosystems in a changing world: A review and perspectives , 2012 .

[40]  Jayme Garcia Arnal Barbedo,et al.  Detection of nutrition deficiencies in plants using proximal images and machine learning: A review , 2019, Comput. Electron. Agric..

[41]  Wei Li,et al.  Hyperspectral Estimation of the Chlorophyll Content in Short-Term and Long-Term Restorations of Mangrove in Quanzhou Bay Estuary, China , 2018 .

[42]  Hui Zhang,et al.  Latitudinal patterns of leaf N, P stoichiometry and nutrient resorption of Metasequoia glyptostroboides along the eastern coastline of China. , 2018, The Science of the total environment.

[43]  J. G. Lyon,et al.  Hyperspectral Remote Sensing of Vegetation , 2011 .

[44]  A. C. Redfield.  The biological control of chemical factors in the environment. , 1960, Science progress.