Spectral-spatial multi-feature classification of remote sensing big data based on a random forest classifier for land cover mapping

Supplementary information, such as multi-temporal spectral data and textural features, has the potential to improve land cover classification accuracy. However, given the larger volumes of remote sensing data, it is difficult to utilize all the features of remote sensing big data having different times and spatial resolutions. Inefficiency is also a large problem when dealing with large area land cover mapping. In this study, a new mode of incorporating spatial and temporal dependencies in a complex region employing the random forests (RFs) classifier was utilized. To map land covers, spring and autumn spectral images and their spectral indexes, textural features obtained from Landsat 5 were selected, and an importance measure variable was used to reduce the data’s dimension. In addition to randomly selecting the variable, we used random sampling to furthest decrease the generalization error in RF. The results showed that utilizing random sampling, multi-temporal spectral image and texture features, the classification of the Wuhan urban agglomeration, China, using RF performed well. The RF algorithm yielded an overall accuracy of 89.2% and a Kappa statistic of 0.8522, indicating high model performance. In addition, the variable importance measures demonstrated that the type of textural features was extremely important for intra-class separability. The RF model has transitivity. The algorithm can be extended by choosing a set of appropriate features for signature extension over large areas or in time-series of Landsat imagery. Land cover mapping might be more economical and efficient if no-cost imagery is used.

[1]  Mario Chica-Olmo,et al.  Computing geostatistical image texture for remotely sensed data classification , 2000 .

[2]  M. A. Aguilar,et al.  Using texture analysis to improve per-pixel classification of very high resolution images for mapping plastic greenhouses , 2008 .

[3]  A. Huete,et al.  A feedback based modification of the NDVI to minimize canopy background and atmospheric noise , 1995 .

[4]  J. A. Schell,et al.  Monitoring vegetation systems in the great plains with ERTS , 1973 .

[5]  Qiusheng Wu,et al.  Improved Wetland Classification Using Eight-Band High Resolution Satellite Imagery and a Hybrid Approach , 2014, Remote. Sens..

[6]  Mahesh Pal,et al.  Random forest classifier for remote sensing classification , 2005 .

[7]  Giorgos Mountrakis,et al.  A meta-analysis of remote sensing research on supervised pixel-based land-cover image classification processes: General guidelines for practitioners and future research , 2016 .

[8]  Aniruddha Ghosh,et al.  A comparison of selected classification algorithms for mapping bamboo patches in lower Gangetic plains using very high resolution WorldView 2 imagery , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[9]  Thomas G. Dietterich.  An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization , 2000, Machine Learning.

[10]  D. Gianelle,et al.  Using the MIR bands in vegetation indices for the estimation of grassland biophysical parameters from satellite remote sensing in the Alps region of Trentino (Italy) , 2008 .

[11]  Maggi Kelly,et al.  Challenges and opportunities in synthesizing historical geospatial data using statistical models , 2016, Ecol. Informatics.

[12]  R. Hall,et al.  Incorporating texture into classification of forest species composition from airborne multispectral images , 2000 .

[13]  Hanqiu Xu.  Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery , 2006 .

[14]  Weixing Cao,et al.  Detection of rice phenology through time series analysis of ground-based spectral index data , 2016 .

[15]  Scott N. Miller,et al.  High-resolution landcover classification using Random Forest , 2014 .

[16]  Gérard Dedieu,et al.  Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas , 2016 .

[17]  Kim-Kwang Raymond Choo,et al.  Spectral–spatial multi-feature-based deep learning for hyperspectral remote sensing image classification , 2016, Soft Computing.

[18]  Jin Chen,et al.  Analysis of NDVI and scaled difference vegetation index retrievals of vegetation fraction , 2006 .

[19]  Zhe Zhu,et al.  Optimizing selection of training and auxiliary data for operational land cover classification for the LCMAP initiative , 2016 .

[20]  M. Keller,et al.  Remote sensing of selective logging in Amazonia: Assessing limitations based on detailed field observations, Landsat ETM+, and textural analysis , 2002 .

[21]  Keith C. Clarke,et al.  Toward accountable land use mapping: Using geocomputation to improve classification accuracy and reveal uncertainty , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[22]  N. Silleos,et al.  Vegetation Indices: Advances Made in Biomass Estimation and Vegetation Monitoring in the Last 30 Years , 2006 .

[23]  Chaowei Yang,et al.  Utilizing Cloud Computing to address big geospatial data challenges , 2017, Comput. Environ. Urban Syst..

[24]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[25]  Kenichi Tatsumi,et al.  Crop classification of upland fields using Random forest of time-series Landsat 7 ETM+ data , 2015, Comput. Electron. Agric..

[26]  Xiang Li,et al.  On the study of fusion techniques for bad geological remote sensing image , 2015, J. Ambient Intell. Humaniz. Comput..

[27]  D. D. Krezhova,et al.  Development and testing of a statistical texture model for land cover classification of the Black Sea region with MODIS imagery , 2010 .

[28]  Ribana Roscher,et al.  Shapelet-Based Sparse Representation for Landcover Classification of Hyperspectral Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[29]  Peng Liu,et al.  Link the remote sensing big data to the image features via wavelet transformation , 2016, Cluster Computing.

[30]  William J. Emery,et al.  A neural network approach using multi-scale textural metrics from very high-resolution panchromatic imagery for urban land-use classification , 2009 .

[31]  Jennifer A. Miller,et al.  Contextual land-cover classification: incorporating spatial dependence in land-cover classification models using random forests and the Getis statistic , 2010 .

[32]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[33]  Ribana Roscher,et al.  Shapelet-based sparse image representation for landcover classification of hyperspectral data , 2014, 2014 8th IAPR Workshop on Pattern Reconition in Remote Sensing.

[34]  Rajiv Ranjan,et al.  IK-SVD: Dictionary Learning for Spatial Big Data via Incremental Atom Update , 2014, Computing in Science & Engineering.

[35]  Mario Chica-Olmo,et al.  An assessment of the effectiveness of a random forest classifier for land-cover classification , 2012 .

[36]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[37]  J. Townshend,et al.  Global discrimination of land cover types from metrics derived from AVHRR pathfinder data , 1995 .

[38]  Anne H. Schistad Solberg,et al.  Texture attributes for detection of salt , 2013 .

[39]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[40]  Ruimin Hu,et al.  HRM graph constrained dictionary learning for face image super-resolution , 2015, Multimedia Tools and Applications.

[41]  John R. Miller,et al.  Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture , 2004 .

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

[43]  Johannes R. Sveinsson,et al.  Random Forests for land cover classification , 2006, Pattern Recognit. Lett..

[44]  Onisimo Mutanga,et al.  Land-use/cover classification in a heterogeneous coastal landscape using RapidEye imagery: evaluating the performance of random forest and support vector machines classifiers , 2014 .