Coincidence Analysis of the Cropland Distribution of Multi-Sets of Global Land Cover Products

Abstract

Modern global cropland products have been widely used to assess the impact of land use and cover change (LUCC) on carbon budgets, climate change, terrestrial ecosystems, etc. However, each product has its own uncertainty, and inconsistencies exist among different products. Understanding the reliability of these datasets is essential for knowing the uncertainties that exist in the study of global change impact forced by cropland reclamation. In this paper, we propose a set of coincidence assessments to identify where reliable cropland distribution is by overlaying ten widely used global land cover/cropland datasets around 2000 AD. A quantitative assessment for different spatial units is also performed. We further discuss the spatial distribution characteristics of different coincidence degrees and explain the reasons. The results show that the high-coincidence proportion is only 40.5% around the world, and the moderate-coincidence and low-coincidence proportion is 18.4% and 41.1%, respectively. The coincidence degrees among different continents and countries have large discrepancies. The coincidence is relatively higher in Europe, South Asia and North America, while it is very poor in Latin America and Africa. The spatial distribution of high and moderate coincidence roughly corresponds to the regions with suitable agricultural conditions and intensive reclamation. In addition to the random factors such as the product's quality and the year it represented, the low coincidence is mainly caused by the inconsistent land cover classification systems and the recognition capability of cropland pixels with low fractions in different products.

Keywords: coincidence; cropland cover; global; multi-products; overlay; uncertainty.

Figure A1

Administrative divisions adopted in this article: Asia is abbreviated as AS; Europe is abbreviated as EU; Oceania is abbreviated as OA; Africa is abbreviated as AF; North America is abbreviated as NA; and Latin America is abbreviated as LA. East is abbreviated as E; West is abbreviated as W; Central is abbreviated as C; North is abbreviated as N; and South is abbreviated as S. The original administrative boundaries and their spatial divisions are drawn according to GADM data (http://gadm.org).

Figure A2

The percentages of different degrees of coincidence of the cropland spatial distribution at the national scale (the land area of country >100 km²), where (a) is Asia, (b) is Africa, (c) is the Americas, (d) is Europe, and (e) is Oceania.

Figure 1

Coincidence degree of the cropland distribution around the world. The three different coincidence levels are shown separately. (a) is the high coincidence of cropland distribution, (b) is the moderate coincidence of cropland distribution, and (c) is the low coincidence of cropland distribution.

Figure 2

The percentage of different coincidence degrees of the cropland spatial distribution at the subcontinental scale.

Figure 3

High-coincidence percentage of the cropland spatial distribution at the national scale (the exact percentage of high coincidence for each country is given in Appendix B Figure A2).