Performance Evaluation of Machine Learning Methods for Leaf Area Index Retrieval from Time-Series MODIS Reflectance Data

Leaf area index (LAI) is an important biophysical parameter and the retrieval of LAI from remote sensing data is the only feasible method for generating LAI products at regional and global scales. However, most LAI retrieval methods use satellite observations at a specific time to retrieve LAI. Because of the impacts of clouds and aerosols, the LAI products generated by these methods are spatially incomplete and temporally discontinuous, and thus they cannot meet the needs of practical applications. To generate high-quality LAI products, four machine learning algorithms, including back-propagation neutral network (BPNN), radial basis function networks (RBFNs), general regression neutral networks (GRNNs), and multi-output support vector regression (MSVR) are proposed to retrieve LAI from time-series Moderate Resolution Imaging Spectroradiometer (MODIS) reflectance data in this study and performance of these machine learning algorithms is evaluated. The results demonstrated that GRNNs, RBFNs, and MSVR exhibited low sensitivity to training sample size, whereas BPNN had high sensitivity. The four algorithms performed slightly better with red, near infrared (NIR), and short wave infrared (SWIR) bands than red and NIR bands, and the results were significantly better than those obtained using single band reflectance data (red or NIR). Regardless of band composition, GRNNs performed better than the other three methods. Among the four algorithms, BPNN required the least training time, whereas MSVR needed the most for any sample size.

[1]  H. S. Wolff,et al.  iRun: Horizontal and Vertical Shape of a Region-Based Graph Compression , 2022, Sensors.

[2]  Karin S. Fassnacht,et al.  Relationships between leaf area index and Landsat TM spectral vegetation indices across three temperate zone sites , 1999 .

[3]  O. Hagolle,et al.  LAI, fAPAR and fCover CYCLOPES global products derived from VEGETATION: Part 1: Principles of the algorithm , 2007 .

[4]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[5]  S. Karsoliya,et al.  Approximating Number of Hidden layer neurons in Multiple Hidden Layer BPNN Architecture , 2012 .

[6]  Hongliang Fang,et al.  Retrieving leaf area index with a neural network method: simulation and validation , 2003, IEEE Trans. Geosci. Remote. Sens..

[7]  Luis Alonso,et al.  Multioutput Support Vector Regression for Remote Sensing Biophysical Parameter Estimation , 2011, IEEE Geoscience and Remote Sensing Letters.

[8]  Fernando Pérez-Cruz,et al.  SVM multiregression for nonlinear channel estimation in multiple-input multiple-output systems , 2004, IEEE Transactions on Signal Processing.

[9]  Jorge J. Moré,et al.  The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[10]  J. Townshend,et al.  Spatially and temporally continuous LAI data sets based on an integrated filtering method: Examples from North America , 2008 .

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

[12]  Ranga B. Myneni,et al.  Estimation of global leaf area index and absorbed par using radiative transfer models , 1997, IEEE Trans. Geosci. Remote. Sens..

[13]  Candan Gokceoglu,et al.  Estimation of rock modulus: For intact rocks with an artificial neural network and for rock masses with a new empirical equation , 2006 .

[14]  Juan J. Flores,et al.  The application of artificial neural networks to the analysis of remotely sensed data , 2008 .

[15]  Qiang Liu,et al.  Inversion of a Radiative Transfer Model for Estimating Forest LAI From Multisource and Multiangular Optical Remote Sensing Data , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[16]  F. Baret,et al.  Neural network estimation of LAI, fAPAR, fCover and LAI×Cab, from top of canopy MERIS reflectance data : Principles and validation , 2006 .

[17]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[18]  Frédéric Baret,et al.  Training a neural network with a canopy reflectance model to estimate crop leaf area index , 2003 .

[19]  Fernando Pérez-Cruz,et al.  Multi-dimensional Function Approximation and Regression Estimation , 2002, ICANN.

[20]  Giles M. Foody Thematic mapping from remotely sensed data with neural networks: MLP, RBF and PNN based approaches , 2001, J. Geogr. Syst..

[21]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[22]  Alessandro Anav,et al.  Global Data Sets of Vegetation Leaf Area Index (LAI)3g and Fraction of Photosynthetically Active Radiation (FPAR)3g Derived from Global Inventory Modeling and Mapping Studies (GIMMS) Normalized Difference Vegetation Index (NDVI3g) for the Period 1981 to 2011 , 2013, Remote. Sens..

[23]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[24]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[25]  J. Hogg Quantitative remote sensing of land surfaces , 2004 .

[26]  Yuehjen E. Shao,et al.  Mining the breast cancer pattern using artificial neural networks and multivariate adaptive regression splines , 2004, Expert Syst. Appl..

[27]  Hengchang Dai,et al.  Automatic picking of seismic arrivals in local earthquake data using an artificial neural network , 1995 .

[28]  S. Durbha,et al.  Support vector machines regression for retrieval of leaf area index from multiangle imaging spectroradiometer , 2007 .

[29]  A. Skidmore,et al.  Inversion of a radiative transfer model for estimating vegetation LAI and chlorophyll in a heterogeneous grassland , 2008 .

[30]  J. Tenhunen,et al.  On the relationship of NDVI with leaf area index in a deciduous forest site , 2005 .

[31]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[32]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[33]  C. Bacour,et al.  Comparison of four radiative transfer models to simulate plant canopies reflectance: direct and inverse mode. , 2000 .

[34]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[35]  Kenlo Nishida Nasahara,et al.  Two separate periods of the LAI–VIs relationships using in situ measurements in a deciduous broadleaf forest , 2013 .

[36]  Colin MacBeth,et al.  Effects of Learning Parameters on Learning Procedure and Performance of a BPNN , 1997, Neural Networks.

[37]  Jindi Wang,et al.  Advanced remote sensing : terrestrial information extraction and applications , 2012 .

[38]  Jindi Wang,et al.  Long-Time-Series Global Land Surface Satellite Leaf Area Index Product Derived From MODIS and AVHRR Surface Reflectance , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[39]  Frédéric Baret,et al.  GEOV1: LAI and FAPAR essential climate variables and FCOVER global time series capitalizing over existing products. Part1: Principles of development and production , 2013 .

[40]  J. Privette,et al.  Inversion methods for physically‐based models , 2000 .

[41]  J. Chen,et al.  Defining leaf area index for non‐flat leaves , 1992 .

[42]  Jindi Wang,et al.  Use of General Regression Neural Networks for Generating the GLASS Leaf Area Index Product From Time-Series MODIS Surface Reflectance , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[43]  Chuntian Cheng,et al.  Using support vector machines for long-term discharge prediction , 2006 .

[44]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .