Mapping Irrigated and Rainfed Wheat Areas Using Multi-Temporal Satellite Data
Irrigation is crucial to agriculture in arid and semi-arid areas and significantly contributes to crop development, food diversity and the sustainability of agro-ecosystems. Here, we present a simple and robust method to map irrigated and rainfed wheat areas in a semi-arid region of China. We used the Normalized Difference Vegetation Index (NDVI) at a 30× 30 m spatial resolution to create a time series spanning the whole growth period of wheat. The maximum NDVI and time-integrated NDVI (TIN) were selected to establish a classification model using a support vector machine (SVM) algorithm. The overall accuracy of the Google-Earth testing samples was 96.0% (right panel) and the estimated irrigated-to-rainfed ratio was 4.4:5.6, close to the estimates in a region with survey sites (left panel). The results indicate that SVM classification model can effectively avoid empirical thresholds in supervised classification and realistically capture the magnitude and spatial patterns of rainfed and irrigated wheat areas. Potentially this approach can be applied to map irrigated/rainfed areas in other regions when field observational data are available.
Jin, N., B. Tao, W. Ren, M. Feng, R. Sun, L. He, W. Zhuang, and Q. Yu (2016), Mapping Irrigated and Rainfed Wheat Areas Using Multi-Temporal Satellite Data, Remote Sensing, 8(3), 207, doi:10.3390/rs8030207.
Zhang, J., W. Ren, P. An, Z. Pan, L. Wang, Z. Dong, D. He, J. Yang, S. Pan, and H. Tian (2015), Responses of Crop Water Use Efficiency to Climate Change and Agronomic Measures in the Semiarid Area of Northern China, Plos One, 10(9), e0137409, doi:10.1371/journal.pone.0137409
Research Area: Big Data Synthesis and Data-Model Integration for Climate-Smart Agriculture