Abstract
The accurate mapping of crops can provide effective information for regional agricultural management, which is helpful to improve crop production efficiency. Recently, remote sensing data offers a comprehensive approach to achieve crop identification on a regional scale. However, the classification methods for multi-year mapping needs further study in regions with a complex planting structure, due to the mixed pixels at a spatial distribution and the high error in different years at a temporal scale. The objective of this study is to map the multi-year spatial distribution of three main crops (maize, sunflower, and wheat) in the Hetao irrigation district of China for the period 2012–2016 based on a pre-constrained classification method. The pre-constrained method integrates a parameterized phenology-based vegetation indexes classifier and two non-parametric machine learning algorithms—support vector machine (SVM) and random forest (RF). Results indicated that the performance of the pre-constrained classification method was excellent in the multi-year mapping of major crops in the study area, with absolute relative errors mainly less than 14% in the whole irrigation district and less than 20% in the five counties. The corresponding overall accuracy was 87.9%, and the Kappa coefficient was 0.80. Mapping results showed that maize is mainly distributed in Hangjinhouqi, southern Linhe, northern Wuyuan, and eastern Wulateqianqi, while wheat is relatively less and scatteredly distributed in Hangjinhouqi and Wuyuan. Moreover, the sunflower planting area increased significantly and expanded spatially from Wuyuan and western Wulateqianqi to northern Hangjinhouqi and Linhe from 2012 to 2016. In addition, the phenology-based vegetation indexes classifier was found to be effective in improving the classification accuracy based on the contribution analysis.
Highlights
Accurate mapping of major crops in irrigation districts provides essential information for agricultural water management [1], and is beneficial in improving water use efficiency, crop yield [2,3], and economic benefits [4]
The satellite images with a very coarse or extremely high spatial resolution are usually not preferable for crop identification at the field scale, which leads to a mixed pixel problem or unnecessary computational cost [13]
Pixels of several categories are all selected to calculate the mean values of fast growth phase (FGP) and NDVImax as a reference, including irrigated land, shrub, grassland, and forest, due to the variation of the spatial distribution of vegetation and crops
Summary
Accurate mapping of major crops in irrigation districts provides essential information for agricultural water management [1], and is beneficial in improving water use efficiency, crop yield [2,3], and economic benefits [4]. The input features with multi-year mapping capacity, such as phenological metrics that are less affected by inter-annual variability, should be developed and applied in the classification [22,23,24] Parametric algorithms, such as the phenological metric classifier, are used for crop identification [24,25,26]. The main objective of the current study is to develop a pre-constrained machine learning method to map heterogeneous crops accurately for multiple years based on sample data of a single year This method is applied to identify three main crops (maize, sunflower, and wheat) in the Hetao irrigation district of northwest China from 2012 to 2016, and the classification performance is evaluated and validated by statistical records and field survey data
Published Version (Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have