Classification of Vegetation Type in Iraq Using Satellite-Based Phenological Parameters

Primary information of great importance to various grand challenges such as sustainable agricultural intensification, food insecurity, and climate change impacts, can be obtained indirectly from land cover monitoring. However, in arid-to-semiarid regions, such as Iraq, accurate discrimination of different vegetation types is challenging due to their similar spectral responses. Moreover, Iraq has been subjected to major disturbances, both natural and anthropogenic which have affected the distribution of land cover types through space and time. Reliable information about croplands and natural vegetation in such regions is generally scarce. This research aimed to develop a phenology-based classification approach using support vector machines for the assessment of space-time distribution of the dominant vegetation land cover (VLC) types in Iraq, particularly croplands, from 2002 to 2012. Thirteen successive years of 8-day composites of MODISNDVI data at a spatial resolution of 250 m were employed to estimate 11 phenological parameters. The classification methodology was assessed using reference samples taken from fine spatial resolution imagery and independent testing data obtained through fieldwork. Overall accuracies were generally >85 %, with relatively high Kappa coefficients (>0.86) across the classified land cover types. The predicted cropland class area and the Global MODIS land cover product were compared with ground statistical data at the governorate level, revealing a significantly larger coefficient of determination for the present phenology-based approach (R2 = 0.70 against R2 = 0.33 for MODIS, p<; 0.05). The resulting maps delimit for the first time, at a fine spatial resolution, the spatial and interannual variability in the dominant VLC classes across Iraq.

[1]  Hamid Reza Matinfar,et al.  Detection of soil salinity changes and mapping land cover types based upon remotely sensed data , 2011, Arabian Journal of Geosciences.

[2]  Robert A. Schowengerdt,et al.  A detailed comparison of backpropagation neural network and maximum-likelihood classifiers for urban land use classification , 1995, IEEE Trans. Geosci. Remote. Sens..

[3]  Damien Sulla-Menashe,et al.  MODIS Collection 5 global land cover: Algorithm refinements and characterization of new datasets , 2010 .

[4]  William L. Pan,et al.  Extension Education for Dryland Cropping Systems in Iraq , 2009 .

[5]  Luciano Vieira Dutra,et al.  Land use/cover classification in the Brazilian Amazon using satellite images. , 2012, Pesquisa Agropecuaria Brasileira.

[6]  Mary Ann Fajvan,et al.  A Comparison of Multispectral and Multitemporal Information in High Spatial Resolution Imagery for Classification of Individual Tree Species in a Temperate Hardwood Forest , 2001 .

[7]  Joydeep Ghosh,et al.  Investigation of the random forest framework for classification of hyperspectral data , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Victor F. Rodriguez-Galiano,et al.  Evaluation of different machine learning methods for land cover mapping of a Mediterranean area using multi-seasonal Landsat images and Digital Terrain Models , 2014, Int. J. Digit. Earth.

[9]  Guangxing Wang,et al.  Phenology-based classification of vegetation cover types in Northeast China using MODIS NDVI and EVI time series , 2015 .

[10]  H. Eva,et al.  Monitoring 25 years of land cover change dynamics in Africa: A sample based remote sensing approach , 2009 .

[11]  Janet Franklin,et al.  Mapping land-cover modifications over large areas: A comparison of machine learning algorithms , 2008 .

[12]  Terry L. Sohl,et al.  Regional characterization of land cover using multiple sources of data , 1998 .

[13]  Len Reynolds,et al.  Country Pasture/Forage Resource Profiles: Malawi , 2014 .

[14]  Paul M. Mather,et al.  Support vector machines for classification in remote sensing , 2005 .

[15]  Geoff Smith,et al.  An evaluation of per-parcel land cover mapping using maximum likelihood class probabilities , 2003 .

[16]  Ying Zhang,et al.  Classification of land-cover types in muddy tidal flat wetlands using remote sensing data , 2014 .

[17]  Brian G. Wolff,et al.  Forecasting Agriculturally Driven Global Environmental Change , 2001, Science.

[18]  Terry L. Kastens,et al.  Image masking for crop yield forecasting using AVHRR NDVI time series imagery , 2005 .

[19]  F. Akinyemi,et al.  An assessment of land-use change in the Cocoa Belt of south-west Nigeria , 2013 .

[20]  Chi-Farn Chen,et al.  A Phenology-Based Classification of Time-Series MODIS Data for Rice Crop Monitoring in Mekong Delta, Vietnam , 2013, Remote. Sens..

[21]  Juan J. Flores,et al.  The application of artificial neural networks to the analysis of remotely sensed data , 2008 .

[22]  Wfp,et al.  The State of Food Insecurity in the World , 2011 .

[23]  H. G. Baker,et al.  A new classification for plant phenology based on flowering patterns in lowland tropical rain forest trees at La Selva, Costa Rica , 1994 .

[24]  R. Wynne,et al.  Three Decades of War and Food Insecurity in Iraq , 2012 .

[25]  Steven W. Running,et al.  A vegetation classification logic-based on remote-sensing for use in global biogeochemical models , 1994 .

[26]  Timothy G. F. Kittel,et al.  Regional Analysis of the Central Great Plains , 1991 .

[27]  Jesslyn F. Brown,et al.  Measuring phenological variability from satellite imagery , 1994 .

[28]  M. Claussen,et al.  Effects of anthropogenic land cover change on the carbon cycle of the last millennium , 2009 .

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

[30]  P. Gong,et al.  A phenology-based approach to map crop types in the San Joaquin Valley, California , 2011 .

[31]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[32]  Siamak Khorram,et al.  Regional Scale Land Cover Characterization Using MODIS-NDVI 250 m Multi-Temporal Imagery: A Phenology-Based Approach , 2006 .

[33]  Andrew Jarvis,et al.  Hole-filled SRTM for the globe Version 4 , 2008 .

[34]  Milap Punia,et al.  Comparison of MODIS derived land use and land cover with Ministry of Agriculture reported statistics for India , 2013 .

[35]  Bas Eickhout,et al.  Impacts of future land cover changes on atmospheric CO2 and climate , 2005 .

[36]  L. S. Davis,et al.  An assessment of support vector machines for land cover classi(cid:142) cation , 2002 .

[37]  Christopher Conrad,et al.  Impact of feature selection on the accuracy and spatial uncertainty of per-field crop classification using Support Vector Machines , 2013 .

[38]  Dirk Pflugmacher,et al.  Comparison and assessment of coarse resolution land cover maps for Northern Eurasia , 2011 .

[39]  B. Wardlow,et al.  Large-area crop mapping using time-series MODIS 250 m NDVI data: An assessment for the U.S. Central Great Plains , 2008 .

[40]  Ryutaro Tateishi,et al.  Use of phenological features to identify cultivated areas in Asia , 2011 .

[41]  P. Gong,et al.  Phenology-based Crop Classification Algorithm and its Implications on Agricultural Water Use Assessments in California’s Central Valley , 2012 .

[42]  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 .

[43]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

[44]  Eric F. Lambin,et al.  Categorization of land‐cover change processes based on phenological indicators extracted from time series of vegetation index data , 2007 .

[45]  D. Tilman,et al.  Global food demand and the sustainable intensification of agriculture , 2011, Proceedings of the National Academy of Sciences.

[46]  Tomoaki Miura,et al.  Phenological Classification of the United States: A Geographic Framework for Extending Multi-Sensor Time-Series Data , 2010, Remote. Sens..

[47]  Conghe Song,et al.  Monitoring forest succession with multitemporal Landsat images: factors of uncertainty , 2003, IEEE Trans. Geosci. Remote. Sens..

[48]  L. Lu,et al.  Large-scale land cover mapping with the integration of multi-source information based on the Dempster–Shafer theory , 2012, Int. J. Geogr. Inf. Sci..

[49]  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 .

[50]  J. Cihlar,et al.  Multitemporal, multichannel AVHRR data sets for land biosphere studies—Artifacts and corrections , 1997 .

[51]  Kiaran K. K. Lawson,et al.  Determining crop acreage estimates for specific winter crops using shape attributes from sequential MODIS imagery , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[52]  D. Roy,et al.  Monitoring conterminous United States (CONUS) land cover change with Web-Enabled Landsat Data (WELD) , 2014 .

[53]  Chen Zhongxin,et al.  Crop discrimination in Northern China with double cropping systems using Fourier analysis of time-series MODIS data , 2008 .

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

[55]  Nancy F. Glenn,et al.  Multitemporal spectral analysis for cheatgrass (Bromus tectorum) classification , 2009 .

[56]  R. Schnepf.  Iraq Agriculture and Food Supply: Background and Issues , 2004 .

[57]  Graeme G. Wilkinson,et al.  Results and implications of a study of fifteen years of satellite image classification experiments , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[58]  S. Griffin.  DATA FUSION/INTEGRATION OF HIGH AND MEDIUM RESOLUTION IMAGERY FOR CROP ANALYSIS , 2009 .

[59]  Jihua Meng,et al.  Crop classification using multi-configuration SAR data in the North China Plain , 2012 .

[60]  P. Atkinson,et al.  Inter-comparison of four models for smoothing satellite sensor time-series data to estimate vegetation phenology , 2012 .

[61]  Wenquan Zhu,et al.  Using phenological metrics and the multiple classifier fusion method to map land cover types , 2014 .

[62]  France Gerard,et al.  Exploring the Use of MODIS NDVI-Based Phenology Indicators for Classifying Forest General Habitat Categories , 2012, Remote. Sens..

[63]  Peter M. Atkinson,et al.  Spatiotemporal variation in the terrestrial vegetation phenology of Iraq and its relation with elevation , 2015, Int. J. Appl. Earth Obs. Geoinformation.