Estimating time-series leaf area index based on recurrent nonlinear autoregressive neural networks with exogenous inputs

The leaf area index (LAI) is a key parameter in many meteorological, environmental and agricultural models. At present, global LAI products from several sensors have been released. These single sensor-based LAI products are generally discontinuous in time and cannot characterize the status of natural vegetation growth very well. In this study, by fusing Moderate Resolution Imaging Spectroradiometer (MODIS) and Satellite Pour l'Observation de la Terre (SPOT) VEGETATION products, time-series LAIs were used to train recurrent nonlinear autoregressive neural networks with exogenous inputs (NARXNNs) for six typical vegetation types. The exogenous inputs included time-series reflectances in the red, near-infrared and shortwave infrared bands as well as the corresponding sun-viewing angles. These NARXNNs subsequently served to predict the time-series LAI. The validation results show that the predicted LAI of the NARXNN is not only more continuous and stable than the MODIS LAI as a function of time but is also much closer to the ground truth. Thus, the proposed method may be helpful for improving the quality of the MODIS LAI.

[1]  Peng Gong,et al.  Inverting a canopy reflectance model using a neural network , 1999 .

[2]  Meng Joo Er,et al.  NARMAX time series model prediction: feedforward and recurrent fuzzy neural network approaches , 2005, Fuzzy Sets Syst..

[3]  William Remus,et al.  Neural Network Models for Time Series Forecasts , 1996 .

[4]  Hubert Cardot,et al.  A new boosting algorithm for improved time-series forecasting with recurrent neural networks , 2008, Inf. Fusion.

[5]  Peter A. Noble,et al.  Neuroet: An easy-to-use artificial neural network for ecological and biological modeling , 2007 .

[6]  Gordon B. Bonan,et al.  Importance of leaf area index and forest type when estimating photosynthesis in boreal forests , 1993 .

[7]  A. Huete,et al.  A comparison of vegetation indices over a global set of TM images for EOS-MODIS , 1997 .

[8]  Dirk Pflugmacher,et al.  BigFoot Land Cover Surfaces for North and South American Sites, 2000-2003 , 2006 .

[9]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.

[10]  S. Leblanc,et al.  A Shortwave Infrared Modification to the Simple Ratio for LAI Retrieval in Boreal Forests: An Image and Model Analysis , 2000 .

[11]  S. T. Gower,et al.  Direct and Indirect Estimation of Leaf Area Index, fAPAR, and Net Primary Production of Terrestrial Ecosystems , 1999 .

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

[13]  S. Running,et al.  MODIS Leaf Area Index (LAI) And Fraction Of Photosynthetically Active Radiation Absorbed By Vegetation (FPAR) Product , 1999 .

[14]  Jindi Wang,et al.  A Temporally Integrated Inversion Method for Estimating Leaf Area Index From MODIS Data , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[15]  D. Diner,et al.  Estimation of vegetation canopy leaf area index and fraction of absorbed photosynthetically active radiation from atmosphere‐corrected MISR data , 1998 .

[16]  R. Dickinson,et al.  The land surface climatology of the community land model coupled to the NCAR community climate model , 2002 .

[17]  Piers J. Sellers,et al.  Remote sensing of the land biosphere and biogeochemistry in the EOS era: science priorities, methods and implementation—EOS land biosphere and biogeochemical cycles panels , 1993 .

[18]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[19]  P. Curran,et al.  LIBERTY—Modeling the Effects of Leaf Biochemical Concentration on Reflectance Spectra , 1998 .

[20]  N. Q. Dinh,et al.  Evaluation of seasonal variation of MODIS derived leaf area index at two European deciduous broadleaf forest sites , 2005 .

[21]  S. Liang,et al.  Retrieving leaf area index using a genetic algorithm with a canopy radiative transfer model , 2003 .

[22]  Paulo J. G. Lisboa,et al.  Financial time series prediction using polynomial pipelined neural networks , 2008, Expert Syst. Appl..

[23]  K. Ranson,et al.  Forest vertical structure from GLAS : An evaluation using LVIS and SRTM data , 2008 .

[24]  Michel M. Verstraete,et al.  Potential and limitations of information extraction on the terrestrial biosphere from satellite remote sensing , 1996 .

[25]  F. Baret,et al.  Performances of neural networks for deriving LAI estimates from existing CYCLOPES and MODIS products , 2008 .

[26]  Stephen E. Reichenbach,et al.  Two-dimensional cubic convolution , 2003, IEEE Trans. Image Process..

[27]  J. Pisek,et al.  Comparison and validation of MODIS and VEGETATION global LAI products over four BigFoot sites in North America , 2007 .

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

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

[30]  Charles L. Walthall,et al.  A study of reflectance anisotropy and canopy structure using a simple empirical model , 1997 .

[31]  A. Kuusk.  A two-layer canopy reflectance model , 2001 .

[32]  Martha C. Anderson,et al.  A comparison of empirical and neural network approaches for estimating corn and soybean leaf area index from Landsat ETM+ imagery ☆ , 2004 .

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

[34]  S. Ustin,et al.  Multi-temporal vegetation canopy water content retrieval and interpretation using artificial neural networks for the continental USA , 2008 .

[35]  Joaquin Melia,et al.  Prototyping of Land-SAF leaf area index algorithm with VEGETATION and MODIS data over Europe , 2009 .

[36]  T. Sakamoto,et al.  A crop phenology detection method using time-series MODIS data , 2005 .

[37]  Kin Keung Lai,et al.  A neural-network-based nonlinear metamodeling approach to financial time series forecasting , 2009, Appl. Soft Comput..

[38]  Jindi Wang,et al.  A Bayesian network algorithm for retrieving the characterization of land surface vegetation , 2008 .

[39]  Hongliang Fang,et al.  Mapping plant functional types from MODIS data using multisource evidential reasoning , 2008 .

[40]  Eugen Diaconescu,et al.  The use of NARX neural networks to predict chaotic time series , 2008 .

[41]  F. Baret,et al.  LAI and fAPAR CYCLOPES global products derived from VEGETATION. Part 2: validation and comparison with MODIS collection 4 products , 2007 .

[42]  Ronggao Liu,et al.  Application of a new leaf area index algorithm to China's landmass using MODIS data for carbon cycle research. , 2007, Journal of environmental management.

[43]  L. Kergoat.  A model for hydrological equilibrium of leaf area index on a global scale , 1998 .

[44]  Guoqiang Peter Zhang,et al.  A neural network ensemble method with jittered training data for time series forecasting , 2007, Inf. Sci..

[45]  T. Geisel,et al.  Hierarchical training of neural networks and prediction of chaotic time series , 1991 .

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

[47]  Peter Tiño,et al.  Learning long-term dependencies in NARX recurrent neural networks , 1996, IEEE Trans. Neural Networks.

[48]  F. Baret,et al.  PROSPECT: A model of leaf optical properties spectra , 1990 .

[49]  James V. Hansen,et al.  Neural networks and traditional time series methods: a synergistic combination in state economic forecasts , 1997, IEEE Trans. Neural Networks.