A Comparison of Machine Learning Algorithms for Mapping of Complex Surface-Mined and Agricultural Landscapes Using ZiYuan-3 Stereo Satellite Imagery

Land cover mapping (LCM) in complex surface-mined and agricultural landscapes could contribute greatly to regulating mine exploitation and protecting mine geo-environments. However, there are some special and spectrally similar land covers in these landscapes which increase the difficulty in LCM when employing high spatial resolution images. There is currently no research on these mixed complex landscapes. The present study focused on LCM in such a mixed complex landscape located in Wuhan City, China. A procedure combining ZiYuan-3 (ZY-3) stereo satellite imagery, the feature selection (FS) method, and machine learning algorithms (MLAs) (random forest, RF; support vector machine, SVM; artificial neural network, ANN) was proposed and first examined for both LCM of surface-mined and agricultural landscapes (MSMAL) and classification of surface-mined land (CSML), respectively. The mean and standard deviation filters of spectral bands and topographic features derived from ZY-3 stereo images were newly introduced. Comparisons of three MLAs, including their sensitivities to FS and whether FS resulted in significant influences, were conducted for the first time in the present study. The following conclusions are drawn. Textures were of little use, and the novel features contributed to improve classification accuracy. Regarding the influence of FS: FS substantially reduced feature set (by 68% for MSMAL and 87% for CSML), and often improved classification accuracies (with an average value of 4.48% for MSMAL using three MLAs, and 11.39% for CSML using RF and SVM); FS showed statistically significant improvements except for ANN-based MSMAL; SVM was most sensitive to FS, followed by ANN and RF. Regarding comparisons of MLAs: for MSMAL based on feature subset, RF achieved the greatest overall accuracy of 77.57%, followed by SVM and ANN; for CSML, SVM had the highest accuracies (87.34%), followed by RF and ANN; based on the feature subsets, significant differences were observed for MSMAL and CSML using any pair of MLAs. In general, the proposed approach can contribute to LCM in complex surface-mined and agricultural landscapes.

[1]  Karl Pearson F.R.S..  LIII. On lines and planes of closest fit to systems of points in space , 1901 .

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

[3]  W. Dulaney,et al.  Normalized difference vegetation index measurements from the Advanced Very High Resolution Radiometer , 1991 .

[4]  P. Sellers.  Remote sensing of the land surface for studies of global change , 1993 .

[5]  Arthur S. Lieberman,et al.  Landscape Ecology , 1994, Springer New York.

[6]  Vladimir Naumovich Vapni.  The Nature of Statistical Learning Theory , 1995 .

[7]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[8]  Giles M. Foody,et al.  An evaluation of some factors affecting the accuracy of classification by an artificial neural network , 1997 .

[9]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[10]  Christina Gloeckner,et al.  Modern Applied Statistics With S , 2003 .

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

[12]  Ting Wang,et al.  Application of Breiman's Random Forest to Modeling Structure-Activity Relationships of Pharmaceutical Molecules , 2004, Multiple Classifier Systems.

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

[14]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[15]  M. Alrababah,et al.  Land use/cover classification of arid and semi‐arid Mediterranean landscapes using Landsat ETM , 2006 .

[16]  J. Wickham,et al.  The effect of Appalachian mountaintop mining on interior forest , 2007, Landscape Ecology.

[17]  Nikolaos M. Avouris,et al.  EVALUATION OF CLASSIFIERS FOR AN UNEVEN CLASS DISTRIBUTION PROBLEM , 2006, Appl. Artif. Intell..

[18]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[19]  S. Butler,et al.  Farmland Biodiversity and the Footprint of Agriculture , 2007, Science.

[20]  A. Yüksel,et al.  Using ASTER Imagery in Land Use/cover Classification of Eastern Mediterranean Landscapes According to CORINE Land Cover Project , 2008, Sensors.

[21]  Jonathan Cheung-Wai Chan,et al.  Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery , 2008 .

[22]  Giles M. Foody,et al.  Sample size determination for image classification accuracy assessment and comparison , 2009 .

[23]  Clayton C. Kingdon,et al.  Changes in the extent of surface mining and reclamation in the Central Appalachians detected using a 1976-2006 Landsat time series , 2009 .

[24]  Tiho Ancev,et al.  Improving the Accuracy of Land Use and Land Cover Classification of Landsat Data Using Post-Classification Enhancement , 2009, Remote. Sens..

[25]  Zhi Zhang,et al.  Comparison of fusion imageries with spectral fidelity using SPOT5 , 2009, International Symposium on Multispectral Image Processing and Pattern Recognition.

[26]  G. Likens,et al.  Mountaintop Mining Consequences , 2010, Science.

[27]  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 .

[28]  Rick E. Landenberger,et al.  Seasonal Trends in Separability of Leaf Reflectance Spectra for Ailanthus altissima and Four Other Tree Species , 2011 .

[29]  K. Harashina,et al.  Land use/cover classification of a complex agricultural landscape using single-dated very high spatial resolution satellite-sensed imagery , 2010 .

[30]  Patricia Gober,et al.  Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery , 2011, Remote Sensing of Environment.

[31]  Jungho Im,et al.  Support vector machines in remote sensing: A review , 2011 .

[32]  A. Karnieli,et al.  Comparison of methods for land-use classification incorporating remote sensing and GIS inputs , 2011 .

[33]  B. Kleinschmit,et al.  Testing the red edge channel for improving land-use classifications based on high-resolution multi-spectral satellite data , 2012 .

[34]  Yang Shao,et al.  Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points , 2012 .

[35]  Steven E. Franklin,et al.  Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests , 2012 .

[36]  Steven E. Franklin,et al.  A comparison of pixel-based and object-based image analysis with selected machine learning algorithms for the classification of agricultural landscapes using SPOT-5 HRG imagery , 2012 .

[37]  P. Atkinson,et al.  Random Forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture , 2012 .

[38]  Michael Epprecht,et al.  A Texture-Based Land Cover Classification for the Delineation of a Shifting Cultivation Landscape in the Lao PDR Using Landscape Metrics , 2013, Remote. Sens..

[39]  Hankui K. Zhang,et al.  Finer resolution observation and monitoring of global land cover: first mapping results with Landsat TM and ETM+ data , 2013 .

[40]  Jordi Cristóbal,et al.  Enhanced land use/cover classification of heterogeneous tropical landscapes using support vector machines and textural homogeneity , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[41]  Kurt Hornik,et al.  Misc Functions of the Department of Statistics (e1071), TU Wien , 2014 .

[42]  O. Mutanga,et al.  Evaluating the impact of red-edge band from Rapideye image for classifying insect defoliation levels , 2014 .

[43]  Weitao Chen,et al.  Forested landslide detection using LiDAR data and the random forest algorithm: A case study of the Three Gorges, China , 2014 .

[44]  Weitao Chen,et al.  Extraction and application analysis of landslide influential factors based on LiDAR DEM: a case study in the Three Gorges area, China , 2014, Natural Hazards.

[45]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[46]  Aaron E. Maxwell,et al.  Comparison of NAIP orthophotography and RapidEye satellite imagery for mapping of mining and mine reclamation , 2014 .

[47]  Matthew J. Cracknell,et al.  Geological mapping using remote sensing data: A comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information , 2014, Comput. Geosci..

[48]  J. Niemeyer,et al.  Contextual classification of lidar data and building object detection in urban areas , 2014 .

[49]  Aaron E. Maxwell,et al.  Combining RapidEye Satellite Imagery and Lidar for Mapping of Mining and Mine Reclamation , 2014 .

[50]  Liangpei Zhang,et al.  Quality Assessment of Panchromatic and Multispectral Image Fusion for the ZY-3 Satellite: From an Information Extraction Perspective , 2014, IEEE Geoscience and Remote Sensing Letters.

[51]  Huili Gong,et al.  Topographic Correction of ZY-3 Satellite Images and Its Effects on Estimation of Shrub Leaf Biomass in Mountainous Areas , 2014, Remote. Sens..

[52]  Henning Buddenbaum,et al.  Comparison of Feature Reduction Algorithms for Classifying Tree Species With Hyperspectral Data on Three Central European Test Sites , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[53]  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 .

[54]  D. Smiraglia,et al.  Unraveling Landscape Complexity: Land Use/Land Cover Changes and Landscape Pattern Dynamics (1954–2008) in Contrasting Peri-Urban and Agro-Forest Regions of Northern Italy , 2015, Environmental Management.

[55]  Cornelius Senf,et al.  Mapping land cover in complex Mediterranean landscapes using Landsat: Improved classification accuracies from integrating multi-seasonal and synthetic imagery , 2015 .

[56]  Timothy A. Warner,et al.  Differentiating mine-reclaimed grasslands from spectrally similar land cover using terrain variables and object-based machine learning classification , 2015 .

[57]  Wai Yeung Yan,et al.  Urban land cover classification using airborne LiDAR data: A review , 2015 .

[58]  Matti Mottus,et al.  Classification of crops across heterogeneous agricultural landscape in Kenya using AisaEAGLE imaging spectroscopy data , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[59]  K. Moffett,et al.  Remote Sens , 2015 .

[60]  Gang Chen,et al.  Identification of Forested Landslides Using LiDar Data, Object-based Image Analysis, and Machine Learning Algorithms , 2015, Remote. Sens..

[61]  D. Goodin,et al.  Mapping land cover and land use from object-based classification: an example from a complex agricultural landscape , 2015 .

[62]  Timothy A. Warner,et al.  Assessing machine-learning algorithms and image- and lidar-derived variables for GEOBIA classification of mining and mine reclamation , 2015 .

[63]  Alfred Stein,et al.  Use of Binary Partition Tree and energy minimization for object-based classification of urban land cover , 2015 .

[64]  Weitao Chen,et al.  Assessment of orthoimage and DEM derived from ZY-3 stereo image in Northeastern China , 2016 .

[65]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[66]  Wolfgang Schramm,et al.  Team , 2018, Spaces of Intensity.