Smart Information Reconstruction via Time-Space-Spectrum Continuum for Cloud Removal in Satellite Images

Cloud contamination is a big obstacle when processing satellite images retrieved from visible and infrared spectral ranges for application. Although computational techniques including interpolation and substitution have been applied to recover missing information caused by cloud contamination, these algorithms are subject to many limitations. In this paper, a novel smart information reconstruction (SMIR) method is proposed, in order to reconstruct cloud contaminated pixel values from the time-space-spectrum continuum with the aid of a machine learning tool, namely extreme learning machine (ELM). For the purpose of demonstration, the performance of SMIR is evaluated by reconstructing the missing remote sensing reflectance values derived from the Moderate Resolution Imaging Spectroradiometer (MODIS) on board the Terra satellite over Lake Nicaragua, where is a very cloudy area year round. For comparison, the traditional backpropagation neural network algorithms will also be implemented to reconstruct the missing values. Experimental results show that the ELM outperforms the BP algorithms by an enhanced machine learning capacity with simulated memory effect embedded in MODIS due to linking the complex time-space-spectrum continuum between cloud-free and cloudy pixels. The ELM-based SMIR practice presents a correlation coefficient of 0.88 with root mean squared error of 7.4E - 04sr-1 between simulated and observed reflectance values. Finding suggests that the SMIR method is effective to reconstruct all the missing information providing visually logical and quantitatively assured images for further image processing and interpretation in environmental applications.

[1]  Julien Clinton Sprott,et al.  A method for approximating missing data in spatial patterns , 2004, Comput. Graph..

[2]  H. Gordon,et al.  Clear water radiances for atmospheric correction of coastal zone color scanner imagery. , 1981, Applied optics.

[3]  D. Antoine,et al.  Bidirectional reflectance of oceanic waters: accounting for Raman emission and varying particle scattering phase function. , 2002, Applied optics.

[4]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[5]  Ni-Bin Chang,et al.  Change detection of land use and land cover in an urban region with SPOT-5 images and partial Lanczos extreme learning machine , 2010 .

[6]  M. Herman,et al.  Cloud detection and derivation of cloud properties from POLDER , 1997 .

[7]  Chao-Hung Lin,et al.  Cloud Removal From Multitemporal Satellite Images Using Information Cloning , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Ni-Bin Chang,et al.  Exploring spatiotemporal patterns of phosphorus concentrations in a coastal bay with MODIS images and machine learning models , 2013 .

[9]  F. Muller‐Karger,et al.  Monitoring turbidity in Tampa Bay using MODIS/Aqua 250-m imagery , 2007 .

[10]  Chao Zeng,et al.  Recovering missing pixels for Landsat ETM + SLC-off imagery using multi-temporal regression analysis and a regularization method , 2013 .

[11]  Brian Moon,et al.  Automated text classification using a dynamic artificial neural network model , 2012, Expert Syst. Appl..

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

[13]  Michael T. Manry,et al.  Upper Bound on Pattern Storage in Feedforward Networks , 2007, 2007 International Joint Conference on Neural Networks.

[14]  William J. Emery,et al.  An automated, dynamic threshold cloud-masking algorithm for daytime AVHRR images over land , 2002, IEEE Trans. Geosci. Remote. Sens..

[15]  Jin Chen,et al.  A new geostatistical approach for filling gaps in Landsat ETM+ SLC-off images , 2012 .

[16]  Feng Gao,et al.  A simple and effective method for filling gaps in Landsat ETM+ SLC-off images , 2011 .

[17]  Marguerite Madden,et al.  Closest Spectral Fit for Removing Clouds and Cloud Shadows , 2009 .

[18]  Ryutaro Tateishi,et al.  Cloud Removal of Optical Image Using SAR Data for ALOS Applications. Experimenting on Simulated ALOS Data , 2009 .

[19]  David G. Long,et al.  A cloud-removal algorithm for SSM/I data , 1999, IEEE Trans. Geosci. Remote. Sens..

[20]  Steven Platnick,et al.  Spatially complete global spectral surface albedos: value-added datasets derived from Terra MODIS land products , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Dong Zhao.  Automated Recognition of Wood Damages Using Artificial Neural Network , 2009, 2009 International Conference on Measuring Technology and Mechatronics Automation.

[22]  Xiaoxiong Xiong,et al.  An overview of the Earth Observing System MODIS instrument and associated data systems performance , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[23]  D P Edwards,et al.  Cloud Detection and Clearing for the Earth Observing System Terra Satellite Measurements of Pollution in the Troposphere (MOPITT) Experiment. , 2001, Applied optics.

[24]  G. Asner,et al.  Cloud cover in Landsat observations of the Brazilian Amazon , 2001 .

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

[26]  K. Gnana Sheela,et al.  Review on Methods to Fix Number of Hidden Neurons in Neural Networks , 2013 .

[27]  C. R. Rao,et al.  Generalized Inverse of Matrices and its Applications , 1972 .

[28]  Derek C. Rose,et al.  Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier] , 2010, IEEE Computational Intelligence Magazine.

[29]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[30]  Guang-Bin Huang,et al.  Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions , 1998, IEEE Trans. Neural Networks.

[31]  Keshav Prasad Paudel,et al.  Monitoring snow cover variability in an agropastoral area in the Trans Himalayan region of Nepal using MODIS data with improved cloud removal methodology , 2011 .

[32]  Zhe Zhu,et al.  Object-based cloud and cloud shadow detection in Landsat imagery , 2012 .

[33]  Compton J. Tucker,et al.  Satellite observed seasonal and inter-annual variation of vegetation over the Kalahari, the Great Victoria Desert, and the Great Sandy Desert - 1979-1984 , 1987 .

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

[35]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[36]  Michael T. Manry,et al.  Upper bound on pattern storage in feedforward networks , 2008, Neurocomputing.

[37]  Farid Melgani,et al.  Contextual reconstruction of cloud-contaminated multitemporal multispectral images , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[38]  Farid Melgani,et al.  Contextual Spatiospectral Postreconstruction of Cloud-Contaminated Images , 2008, IEEE Geoscience and Remote Sensing Letters.

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

[40]  R. D'adamo,et al.  Hydrological heterogeneity, nutrient dynamics and water quality of a non-tidal lentic ecosystem (Lesina Lagoon, Italy). , 2009 .

[41]  M. Mazari-Hiriart,et al.  Spatial Heterogeneity of Water Quality in a Highly Degraded Tropical Freshwater Ecosystem , 2009, Environmental management.

[42]  Jing Wang,et al.  The Bounded Capacity of Fuzzy Neural Networks (FNNs) Via a New Fully Connected Neural Fuzzy Inference System (F-CONFIS) With Its Applications , 2014, IEEE Transactions on Fuzzy Systems.

[43]  Ke Yan,et al.  A new cloud removal algorithm for multi-spectral images , 2005, International Symposium on Multispectral Image Processing and Pattern Recognition.

[44]  Peter J. Angeline,et al.  Genetic programming: On the programming of computers by means of natural selection,: John R. Koza, A Bradford Book, MIT Press, Cambridge MA, 1992, ISBN 0-262-11170-5, xiv + 819pp., US$55.00 , 1994 .

[45]  Martti Hallikainen,et al.  Water quality classification of lakes using 250-m MODIS data , 2004, IEEE Geoscience and Remote Sensing Letters.

[46]  S. Ustin,et al.  Water content estimation in vegetation with MODIS reflectance data and model inversion methods , 2003 .

[47]  Kay Chen Tan,et al.  Estimating the Number of Hidden Neurons in a Feedforward Network Using the Singular Value Decomposition , 2006, IEEE Trans. Neural Networks.

[48]  K. S. Banerjee.  Generalized Inverse of Matrices and Its Applications , 1973 .

[49]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[50]  Chao-Hung Lin,et al.  Patch-Based Information Reconstruction of Cloud-Contaminated Multitemporal Images , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[51]  Menghua Wang,et al.  Retrieval of water-leaving radiance and aerosol optical thickness over the oceans with SeaWiFS: a preliminary algorithm. , 1994, Applied optics.

[52]  Soroosh Sorooshian,et al.  Estimation of daily cloud‐free, snow‐covered areas from MODIS based on variational interpolation , 2012 .

[53]  J. Brock,et al.  Assessment of estuarine water-quality indicators using MODIS medium-resolution bands: initial results from Tampa Bay, FL , 2004 .

[54]  Steven A. Ackerman,et al.  Cloud Detection with MODIS. Part II: Validation , 2008 .

[55]  Richard A. Frey,et al.  Cloud Detection with MODIS. Part I: Improvements in the MODIS Cloud Mask for Collection 5 , 2008 .

[56]  D. Roy,et al.  An overview of MODIS Land data processing and product status , 2002 .

[57]  U. C. Kothyari,et al.  Modeling of the daily rainfall-runoff relationship with artificial neural network , 2004 .

[58]  Hyeungu Choi,et al.  Cloud detection in Landsat imagery of ice sheets using shadow matching technique and automatic normalized difference snow index threshold value decision , 2004 .

[59]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[60]  W. Paul Menzel,et al.  Nighttime polar cloud detection with MODIS , 2004 .

[61]  Peter J. Minnett,et al.  An overview of MODIS capabilities for ocean science observations , 1998, IEEE Trans. Geosci. Remote. Sens..

[62]  Young-Seuk Park,et al.  Patterning and predicting aquatic macroinvertebrate diversities using artificial neural network. , 2003, Water research.

[63]  Robert Eckardt,et al.  Removal of Optically Thick Clouds from Multi-Spectral Satellite Images Using Multi-Frequency SAR Data , 2013, Remote. Sens..

[64]  David B. Fogel,et al.  An Introduction to Evolutionary Programming , 1995, Artificial Evolution.

[65]  Darrell Whitley,et al.  A genetic algorithm tutorial , 1994, Statistics and Computing.

[66]  Ni-Bin Chang,et al.  Comparative Sensor Fusion Between Hyperspectral and Multispectral Satellite Sensors for Monitoring Microcystin Distribution in Lake Erie , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[67]  András Bárdossy,et al.  Cloud removal methodology from MODIS snow cover product , 2009 .

[68]  Mehdi Khashei,et al.  An artificial neural network (p, d, q) model for timeseries forecasting , 2010, Expert Syst. Appl..

[69]  Chun-Liang Chien,et al.  Automatic cloud removal from multi-temporal SPOT images , 2008, Appl. Math. Comput..