A 30-m resolution distribution map of maize for China based on Landsat and Sentinel images

As the second largest producer of maize, China contributes 23% of global  maize production and plays an important role in guaranteeing maize  markets stability. In spite of its importance, there is no 30 m spatial  resolution distribution map of maize for all of China. This study used a  time-weighted dynamic time warping method to identify planting areas of  maize by comparing the similarity of time series of a satellite-based  vegetation index at each pixel with a standard time series derived from  known maize fields and mapped maize distribution from 2016 to 2020 over  22 provinces accounting for more than 99% of the maize planting area in  China. Based on 18800 field-surveyed pixels at 30-meter spatial  resolution, the distribution map yields 76.15% and 81.59% of producer’s  and user’s accuracies averaged over the entire investigated provinces,  respectively. Municipality- and county-level census data also show a  good performance in reproducing the spatial distribution of maize. This  study provides an approach to mapping maize over large areas based on a  small volume of field survey data. 
1: maize
classification system:
0: non-maize
<br>
 Ruoque Shen, Jie Dong, Wenping Yuan, Wei Han, Tao Ye, Wenzhi Zhao, "A 30 m Resolution Distribution Map of Maize for China Based on Landsat and Sentinel Images", <em>Journal of Remote Sensing</em>, vol. 2022, Article ID 9846712, 12   pages, 2022. https://doi.org/10.34133/2022/9846712