Classification of irrigated and non-irrigated cropland using object-based image analysis: A case study in south-central Nebraska

Detailed and accurate delineation of irrigated and non-irrigated land is critical to water resource management in arid and semi-arid areas, where dependence on groundwater irrigation is high. However, there is no such information available in the national land use and land cover databases such as National Land Cover Dataset and Cropland Data Layer. This study proposed an object-based image classification method to delineate the irrigated and non-irrigated cropland using remote sensing indices, evapotranspiration and other supplemental information. The method has been tested in South-Central Nebraska, and the results showed that the method produced accurate account of irrigated and non-irrigated land classification. The method is expected to be applicable in other arid and semi-arid areas.