Neural network application for cloud detection in SPOT VEGETATION images

SPOT VEGETATION is a recent sensor at 1 km resolution for land surface studies. Cloud detection based on this sensor is complicated by the absence of a thermal band. An artificial neural network was thus trained for the cloud detection on atmospherically corrected S1 daily data and on top of the atmosphere reflectance P data, from the SPOT VEGETATION system. It consists of a multi‐layer perceptron with one hidden sigmoid layer, trained with the Levenberg–Marquardt back‐propagation algorithm and generalized by the Bayesian regularization. Two neural networks allowed optimal cloud detections to be obtained. The first used all four bands of S1 data with 13 hidden nodes, and the second employed all four bands of P data with 11 hidden nodes. The multiple‐layer perceptrons lead to a cloud detection accuracy of 98.0% and 97.6% for S1 and P data, respectively, when trained to map three predefined values that classify cloud, water and land. The network was further evaluated using three SPOT VEGETATION images taken at different dates. The network detected not only bright thick clouds but also thin or less bright clouds. The analysis demonstrated the superior classification of the network over the standard cloud masks provided with the data.

[1]  Kun Shan Chen,et al.  LAND-COVER CLASSIFICATION OF MULTISPECTRAL IMAGERY USING A DYNAMIC LEARNING NEURAL-NETWORK , 1995 .

[2]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[3]  Brent N. Holben,et al.  Extracting forest age in a Pacific Northwest Forest from thematic mapper and topographic data , 1996 .

[4]  R. R. Rhinehart,et al.  A method to determine the required number of neural-network training repetitions , 1999, IEEE Trans. Neural Networks.

[5]  G. Dedieu,et al.  SMAC: a simplified method for the atmospheric correction of satellite measurements in the solar spectrum , 1994 .

[6]  Edit J. Kaminsky,et al.  Textural neural network and version space classifiers for remote sensing , 1997 .

[7]  Timothy Masters,et al.  Advanced algorithms for neural networks: a C++ sourcebook , 1995 .

[8]  Lutz Prechelt,et al.  Automatic early stopping using cross validation: quantifying the criteria , 1998, Neural Networks.

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

[10]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[11]  M. Derrien,et al.  Automatic cloud detection applied to NOAA-11 /AVHRR imagery , 1993 .

[12]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[13]  Yonghong Tan,et al.  Neural-network-based d-step-ahead predictors for nonlinear systems with time delay , 1999 .

[14]  L. Keiner,et al.  Estimating oceanic chlorophyll concentrations with neural networks , 1999 .

[15]  Hugh G. Lewis,et al.  Determination of spatial and temporal characteristics as an aid to neural network cloud classification , 1997 .

[16]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[17]  Thierry Faure,et al.  Neural network retrieval of cloud parameters of inhomogeneous and fractional clouds , 2001 .

[18]  Mahmood R. Azimi-Sadjadi,et al.  Comparison of two different PNN training approaches for satellite cloud data classification , 2001, IEEE Trans. Neural Networks.

[19]  Jason I. Gobat,et al.  Improved cloud detection for daytime AVHRR scenes over land , 1996 .

[20]  Mahmood R. Azimi-Sadjadi,et al.  Temporal updating scheme for probabilistic neural network with application to satellite cloud classification , 2000, IEEE Trans. Neural Networks Learn. Syst..

[21]  Sibbo van der Veen,et al.  Cloud Detection Using Meteosat Imagery and Numerical Weather Prediction Model Data , 2000 .

[22]  R. Holyer,et al.  Coastal bathymetry from hyperspectral observations of water radiance , 1998 .

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

[24]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[25]  James J. Simpson,et al.  Application of neural networks to AVHRR cloud segmentation , 1995, IEEE Trans. Geosci. Remote. Sens..

[26]  R. Saunders,et al.  An improved method for detecting clear sky and cloudy radiances from AVHRR data , 1988 .

[27]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[28]  Warren S. Sarle,et al.  Stopped Training and Other Remedies for Overfitting , 1995 .

[29]  François Anctil,et al.  Impact of the length of observed records on the performance of ANN and of conceptual parsimonious rainfall-runoff forecasting models , 2004, Environ. Model. Softw..

[30]  John N. Tsitsiklis,et al.  Neuro-Dynamic Programming , 1996, Encyclopedia of Machine Learning.

[31]  A. Strahler,et al.  Classification of ASAS multiangle and multispectral measurements using artificial neural networks , 1996 .

[32]  William J. Emery,et al.  An Automated Neural Network Cloud Classifier for Use over Land and Ocean Surfaces , 1997 .

[33]  A. Strahler,et al.  Artificial neural network response to mixed pixels in coarse-resolution satellite data , 1996 .

[34]  Ronald M. Welch,et al.  A neural network approach to cloud classification , 1990 .

[35]  Johannes R. Sveinsson,et al.  Feature extraction for multisource data classification with artificial neural networks , 1997 .

[36]  J. Cihlar.  Identification of contaminated pixels in AVHRR composite images for studies of land biosphere , 1996 .

[37]  Jason I. Gobat,et al.  Improved cloud detection in GOES scenes over land , 1995 .

[38]  V. Krasnopolsky,et al.  A neural network as a nonlinear transfer function model for retrieving surface wind speeds from the special sensor microwave imager , 1995 .

[39]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[40]  X. Passot.  VEGETATION image processing methods in the CTIV , 2000 .

[41]  James J. Simpson,et al.  Automated cloud screening of AVHRR imagery using split-and-merge clustering☆ , 1991 .

[42]  Sigeru Omatu,et al.  Neural network approach to land cover mapping , 1994, IEEE Trans. Geosci. Remote. Sens..