Estimation of paddy rice leaf area index using machine learning methods based on hyperspectral data from multi-year experiments

The performance of three machine learning methods (support vector regression, random forests and artificial neural network) for estimating the LAI of paddy rice was evaluated in this study. Traditional univariate regression models involving narrowband NDVI with optimized band combinations as well as linear multivariate calibration partial least squares regression models were also evaluated for comparison. A four year field-collected dataset was used to test the robustness of LAI estimation models against temporal variation. The partial least squares regression and three machine learning methods were built on the raw hyperspectral reflectance and the first derivative separately. Two different rules were used to determine the models’ key parameters. The results showed that the combination of the red edge and NIR bands (766 nm and 830 nm) as well as the combination of SWIR bands (1114 nm and 1190 nm) were optimal for producing the narrowband NDVI. The models built on the first derivative spectra yielded more accurate results than the corresponding models built on the raw spectra. Properly selected model parameters resulted in comparable accuracy and robustness with the empirical optimal parameter and significantly reduced the model complexity. The machine learning methods were more accurate and robust than the VI methods and partial least squares regression. When validating the calibrated models against the standalone validation dataset, the VI method yielded a validation RMSE value of 1.17 for NDVI(766,830) and 1.01 for NDVI(1114,1190), while the best models for the partial least squares, support vector machine and artificial neural network methods yielded validation RMSE values of 0.84, 0.82, 0.67 and 0.84, respectively. The RF models built on the first derivative spectra with mtry = 10 showed the highest potential for estimating the LAI of paddy rice.

[1]  Biochar amendment reduces paddy soil nitrogen leaching but increases net global warming potential in Ningxia irrigation, China , 2017, Scientific Reports.

[2]  Kabir Peerbhay,et al.  Comparison of partial least squares and support vector regressions for predicting leaf area index on a tropical grassland using hyperspectral data , 2016 .

[3]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[4]  Weiwei Liu,et al.  Estimation and Mapping of Winter Oilseed Rape LAI from High Spatial Resolution Satellite Data Based on a Hybrid Method , 2017, Remote. Sens..

[5]  A. Gitelson,et al.  Informative spectral bands for remote green LAI estimation in C3 and C4 crops , 2016 .

[6]  Ruiliang Pu,et al.  Estimation of forest leaf area index using vegetation indices derived from Hyperion hyperspectral data , 2003, IEEE Trans. Geosci. Remote. Sens..

[7]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[8]  Guangxin Li,et al.  Extraction of Sensitive Bands for Monitoring the Winter Wheat (Triticum aestivum) Growth Status and Yields Based on the Spectral Reflectance , 2017, PloS one.

[9]  Xin-gang Xu,et al.  Assessment of the AquaCrop Model for Use in Simulation of Irrigated Winter Wheat Canopy Cover, Biomass, and Grain Yield in the North China Plain , 2014, PloS one.

[10]  Fuan Tsai,et al.  Derivative Analysis of Hyperspectral Data , 1998 .

[11]  J. Qi,et al.  A comparative analysis of broadband and narrowband derived vegetation indices in predicting LAI and CCD of a cotton canopy , 2007 .

[12]  Alexander F. H. Goetz,et al.  Three decades of hyperspectral remote sensing of the Earth: a personal view. , 2009 .

[13]  Frédéric Baret,et al.  Review of methods for in situ leaf area index determination Part I. Theories, sensors and hemispherical photography , 2004 .

[14]  L. Alonso,et al.  A red-edge spectral index for remote sensing estimation of green LAI over agroecosystems , 2013 .

[15]  Clement Atzberger,et al.  LAI and chlorophyll estimation for a heterogeneous grassland using hyperspectral measurements , 2008 .

[16]  S. Ustin,et al.  Hyperspectral canopy sensing of paddy rice aboveground biomass at different growth stages , 2014 .

[17]  M. Feng,et al.  Hyperspectral prediction of leaf area index of winter wheat in irrigated and rainfed fields , 2017, PloS one.

[18]  Xulin Guo,et al.  Remote Sensing of Leaf Area Index (LAI) and a Spatiotemporally Parameterized Model for Mixed Grasslands , 2014 .

[19]  P. M. Hansena,et al.  Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression , 2003 .

[20]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[21]  P. Atkinson,et al.  Introduction Neural networks in remote sensing , 1997 .

[22]  José Luis Rojo-Álvarez,et al.  Robust support vector regression for biophysical variable estimation from remotely sensed images , 2006, IEEE Geoscience and Remote Sensing Letters.

[23]  Huanhuan Yuan,et al.  Retrieving Soybean Leaf Area Index from Unmanned Aerial Vehicle Hyperspectral Remote Sensing: Analysis of RF, ANN, and SVM Regression Models , 2017, Remote. Sens..

[24]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[25]  Tian Xia,et al.  Estimating the crop leaf area index using hyperspectral remote sensing , 2016 .

[26]  G. Pazour,et al.  Ror2 signaling regulates Golgi structure and transport through IFT20 for tumor invasiveness , 2017, Scientific Reports.

[27]  Byun-Woo Lee,et al.  Using canopy reflectance and partial least squares regression to calculate within-field statistical variation in crop growth and nitrogen status of rice , 2006, Precision Agriculture.

[28]  Lei Wang,et al.  Assimilation of the leaf area index and vegetation temperature condition index for winter wheat yield estimation using Landsat imagery and the CERES-Wheat model , 2017 .

[29]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[30]  Nigel P. Fox,et al.  Progress in Field Spectroscopy , 2006 .

[31]  Fan Yang,et al.  Estimating grassland LAI using the Random Forests approach and Landsat imagery in the meadow steppe of Hulunber, China , 2017 .

[32]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[33]  Guang Zheng,et al.  Retrieving Leaf Area Index (LAI) Using Remote Sensing: Theories, Methods and Sensors , 2009, Sensors.

[34]  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 .

[35]  Kurt Hornik,et al.  kernlab - An S4 Package for Kernel Methods in R , 2004 .

[36]  D. Mulla.  Twenty five years of remote sensing in precision agriculture: Key advances and remaining knowledge gaps , 2013 .

[37]  Yu Huang,et al.  Evaluation of Six Algorithms to Monitor Wheat Leaf Nitrogen Concentration , 2015, Remote. Sens..

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

[39]  Hamideh Noory,et al.  Improving crop yield estimation by assimilating LAI and inputting satellite-based surface incoming solar radiation into SWAP model , 2018 .

[40]  Andrew K. Skidmore,et al.  Estimation of green grass/herb biomass from airborne hyperspectral imagery using spectral indices and partial least squares regression , 2007, Int. J. Appl. Earth Obs. Geoinformation.

[41]  Ron Wehrens,et al.  The pls Package: Principal Component and Partial Least Squares Regression in R , 2007 .

[42]  Zhang-hua Lou,et al.  A comparison of three methods for estimating leaf area index of paddy rice from optimal hyperspectral bands , 2011, Precision Agriculture.

[43]  R. Kokaly,et al.  Characterizing canopy biochemistry from imaging spectroscopy and its application to ecosystem studies , 2009 .

[44]  Kazuaki Yoshida,et al.  Spectral Index for Quantifying Leaf Area Index of Winter Wheat by Field Hyperspectral Measurements: A Case Study in Gifu Prefecture, Central Japan , 2015, Remote. Sens..