Chen Xuehong

Global cultivated land mapping at 30 m spatial resolution

Cultivated land is one of the most important types of land cover in the global mapping of land cover, and its variation influences economic development, food security, and ecological environment protection. Existing products of global cultivated land mapping have a low resolution, and high spatial resolution products are in demand. This study uses global remote sensing image datasets in 2000/2010 with a spatial resolution of 30 m (Landsat TM/ETM+, HJ-1), MODIS 250 m NDVI time-serial data, and many types of reference data. An three-layer extraction method based on pixels, objects, and knowledge (POK) was adopted to ease cultivated land extraction in global-scale 30 m images, i.e., cultivated land classification based on pixel-scale multi-feature optimization, cultivated land automatic identification based on objects, and interactive object processing based on information service and priori knowledge. Global 30 m cultivated land mapping was accomplished for the two reference years (2000 and 2010), and statistical analysis was conducted on the data. Results showed that the total cultivated land area was 1.903 billion ha and 1.960 billion ha, respectively. Accuracy assessments showed that overall accuracy of global cultivated land mapping are higher than 92% for both the two reference years. The global cultivated land products in 2000/2010 developed in this research are superior to their international counterparts in terms of spatial resolution and classification accuracy. They also provide significant basic data on global food security, ecological environment supervision, and global change.

Method for land cover classification accuracy assessment considering edges

Land cover, as the direct description of the Earth surface, has close relationships to the circle of global substances and energy, climate change, and economic activities of human society. The acquisition of land cover products is usually based on image classification. The accuracy of image classification is highly important to the monitoring and investigation of global environment as well as in decision-making support. Thus, classification accuracy assessment of land cover products is an important procedure. Given that many mixed pixels are located in between different classes, the accuracy of edge pixels tend to be lower than that of interior pixels. This scenario leads to the increment of heterogeneity to the classification accuracy of each class and to the increase of uncertainty of accuracy assessment. This study presents a method named stratified sampling considering edges (SSCE) based on traditional stratified sampling (SS) to optimize the process of classification accuracy assessment. Theoretical derivations and experimental results indicate that SSCE has high stability and accuracy on the estimation of overall accuracy and kappa. SSCE has high accuracy on estimating classification accuracy when only a few sampling points exist. SSCE needs less sampling points than SS under the same tolerance of error. The higher the difference on accuracy is and the more equal the areas between edge regions and interior regions are, the more accurate SSCE is on accuracy assessment. In a word, SSCE costs minimal sampling points. It also has high accuracy and stability on the assessment of land cover classification accuracy.