Surface Heterogeneity-Involved Estimation of Sample Size for Accuracy Assessment of Land Cover Product from Satellite Imagery

Sample size estimation is a key issue for validating land cover products derived from satellite images. Based on the fact that present sample size estimation methods account for the characteristics of the Earth’s subsurface, this study developed a model for estimating sample size by considering the scale effect and surface heterogeneity. First, we introduced a watershed with different areas to indicate the scale effect on the sample size. Then, by employing an all-subsets regression feature selection method, three landscape indicators describing the aggregation and diversity of the land cover patches were selected (from 14 indicators) as the main factors for indicating the surface heterogeneity. Finally, we developed a multi-level linear model for sample size estimation using explanatory variables, including the estimated sample size (n) calculated from the traditional statistical model, size of the test region, and three landscape indicators. As reference data for developing this model, we employed a case study in the Jiangxi Province using a 30 m spatial resolution global land cover product (Globeland30) from 2010 as a classified map, and national 30 m land use/cover change (LUCC) data from 2010 in China. The results showed that the adjusted square coefficient of R2 is 0.79, indicating that the joint explanatory ability of all predictive variables in the model to the sample size is 79%. This means that the predictability of this model is at a good level. By comparing the sample size NS obtained by the developed multi-level linear model and n as calculated from the statistics model, we find that NS is much smaller than n, which mainly contributes to the concerns regarding surface heterogeneity in this study. The validity of the established model is tested and is proven as effective in the Anhui Province. This indicates that the estimated sample size from considering the scale effect and spatial heterogeneity in this study achieved the same accuracy as that calculated from a probability statistical model, while simultaneously saving more time, labour, and money in the accuracy assessment of a land cover dataset.

[1]  Wang Changyou,et al.  Spatial Pattern Change of Land Use in China in Recent 10 Years , 2002 .

[2]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[3]  James D. Wickham,et al.  Pixels, blocks of pixels, and polygons: Choosing a spatial unit for thematic accuracy assessment , 2011 .

[4]  Si-Yuan Wang,et al.  Study on spatial pattern and change of land use in recent ten years, China , 2002, IGARSS.

[5]  T. Esch,et al.  Breaking new ground in mapping human settlements from space – The Global Urban Footprint , 2017, 1706.04862.

[6]  ACCURACY ASSESSMENT OF THE GLOBELAND30 DATASET IN JIANGXI PROVINCE , 2018 .

[7]  Paul J. Curran,et al.  Simple size for ground and remotely sensed data , 1986 .

[8]  Stephen V. Stehman,et al.  Sampling designs for accuracy assessment of land cover , 2009 .

[9]  Kevin McGarigal,et al.  Behavior of class-level landscape metrics across gradients of class aggregation and area , 2004, Landscape Ecology.

[10]  Jin Chen,et al.  Global land cover mapping at 30 m resolution: A POK-based operational approach , 2015 .

[11]  Liu Jiyuan,et al.  Study on spatial pattern and change of land use in recent ten years, China , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[12]  Ioan Vasile Abrudan,et al.  Carbon implications of forest restitution in post-socialist Romania , 2011 .

[13]  Robert Kabacoff,et al.  R in Action: Data Analysis and Graphics with R , 2015 .

[14]  Martin Herold,et al.  A global land-cover validation data set, II: augmenting a stratified sampling design to estimate accuracy by region and land-cover class , 2012 .

[15]  Jun Chen,et al.  The First Comprehensive Accuracy Assessment of GlobeLand30 at a National Level: Methodology and Results , 2015, Remote. Sens..

[16]  Alan H. Strahler,et al.  Global land cover mapping from MODIS: algorithms and early results , 2002 .

[17]  David J. Selkowitz,et al.  A spatially stratified, multi-stage cluster sampling design for assessing accuracy of the Alaska (USA) National Land Cover Database (NLCD) , 2010 .

[18]  Jeff W. Johnson.  Factors Affecting Relative Weights: The Influence of Sampling and Measurement Error , 2004 .

[19]  Yang Gao,et al.  City block-based assessment of land cover components’ impacts on the urban thermal environment , 2019, Remote Sensing Applications: Society and Environment.

[20]  René R. Colditz,et al.  Landscape Complexity and Remote Classification in Eastern Coastal Mexico: Applications of Landsat‐7 ETM+ Data , 2004 .

[21]  Alejandro Martínez-Abraín,et al.  Are there any differences? A non-sensical question in ecology , 2007 .

[22]  Giles M. Foody,et al.  Harshness in image classification accuracy assessment , 2008 .

[23]  Giles M. Foody,et al.  Good practices for estimating area and assessing accuracy of land change , 2014 .

[24]  Siamak Khorram,et al.  Correspondence analysis for detecting land cover change , 2006 .

[25]  Stephen V. Stehman,et al.  Impact of sample size allocation when using stratified random sampling to estimate accuracy and area of land-cover change , 2012 .

[26]  He Chao-ying,et al.  Higher Resolution Global Land Cover Mapping , 2011 .

[27]  S. de Bruin,et al.  Assessing global land cover reference datasets for different user communities , 2015 .

[28]  Jun Zhang,et al.  A landscape shape index-based sampling approach for land cover accuracy assessment , 2016, Science China Earth Sciences.

[29]  J. Benedetto,et al.  Nonlinear Dimensionality Reduction via the ENH-LTSA Method for Hyperspectral Image Classification , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[30]  Curtis E. Woodcock,et al.  Mapping and estimating land change between 2001 and 2013 in a heterogeneous landscape in West Africa: Loss of forestlands and capacity building opportunities , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[31]  Alan H. Strahler,et al.  Validation of the global land cover 2000 map , 2006, IEEE Transactions on Geoscience and Remote Sensing.

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

[33]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[34]  Javier Gallego Jrc.  Comparing CORINE Land Cover with a more detailed database in Arezzo (Italy). , 2000 .

[35]  Xuezhi Feng,et al.  Accuracy assessment of seven global land cover datasets over China , 2017 .

[36]  Weiwei Sun,et al.  Quantifying Sub-Pixel Surface Water Coverage in Urban Environments Using Low-Albedo Fraction from Landsat Imagery , 2017, Remote. Sens..

[37]  Thomas Esch,et al.  The Global Urban Footprint , 2018 .

[38]  Zhenhua Wang,et al.  Designing a two-rank acceptance sampling plan for quality inspection of geospatial data products , 2011, Comput. Geosci..

[39]  Martin Herold,et al.  Some challenges in global land cover mapping : An assessment of agreement and accuracy in existing 1 km datasets , 2008 .

[40]  A. Hay.  Sampling designs to test land-use map accuracy , 1979 .

[41]  C. Woodcock,et al.  Making better use of accuracy data in land change studies: Estimating accuracy and area and quantifying uncertainty using stratified estimation , 2013 .

[42]  Sun Qun,et al.  Accuracy Assessment and Comparative Analysis of GlobeLand30 Dataset in Henan Province , 2016 .

[43]  A. Winsor.  Sampling techniques. , 2000, Nursing times.

[44]  Peng Gong,et al.  Global land cover mapping using Earth observation satellite data: Recent progresses and challenges , 2015 .

[45]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .