Crop Identification by Using Seasonal Parameters Extracted from Time Series Landsat Images in a Mountainous Agricultural County of Eastern Qinghai Province, China

• DOI: 10.5539/jas.v9n4p116
• Publication Date: 2017-03-14T04:30:25Z
• Authors: Xia Zhao; Xingchuan Wang; Guangchao Cao; Kelong Chen; Wenjia Tang; Zhijun Zhang
• Keywords: 2. Zero hunger; 0401 agriculture, forestry, and fisheries; 04 agricultural and veterinary sciences; 15. Life on land

Time series vegetable indexes (Vis) have been evidenced a useful data to extract phenology and identify crop types. This paper conducted such research in Qinghai Province by using Landsat TM images, via four steps, i) sampling single-crop plots extracting spectrums based on pure signle-crop pixels; ii) building time-series 8 images (2013-2014); iii) seasonal parameters according algorithms defined TIMESAT program; vi) generating decision tree for identifying types validate classification accuracy ground investigation. The results indicate that crops planted larger continuous range, as spring wheat, potato rapeseed, achieved an acceptable of above 70%, while too dispersedly (like broad bean, which is often inter-planted with other crops) or smaller planting range barley), remained poor recognition rates (below 50%). value this work lies it displayed not only the region methodology, but also feasibility integrating VIs calculation, parameter generation into one computer program, highly desired region.