Loading...
An Evaluation of Cross-Year Crop Classification for the State of Kansas Using Time-Series MODIS 250m Vegetation Index Data
Bishop, Christopher Ryan
Bishop, Christopher Ryan
Citations
Altmetric:
Abstract
In many cases, when classifying satellite imagery, training sites and sample data are not available on a yearly basis. Therefore, it would be beneficial if accurate training data from a single year could be applied to other years.The objectives of this research were to: 1) utilize time-series MODIS 250m NDVI data to identify and map unique crop types for the state of Kansas and the surrounding Kansas River watershed and 2) test the level of accuracy when conducting cross-year classifications by applying a library of NDVI time-series curves to imagery from other years. MODIS 250m NDVI data were used to classify seven unique crop cover types for 2005. An overall accuracy of 82% was achieved. MODIS 250m time-series NDVI data and training and validation data from 2001 and 2005 were used to conduct the cross-year classifications. Overall accuracies were between 68% (2001) and 74% (2005) were achieved.
Description
Date
2010-06-14
Journal Title
Journal ISSN
Volume Title
Publisher
University of Kansas
Files
Archive Status
Research Projects
Organizational Units
Journal Issue
Keywords
Remote sensing, Geographic information sciences, Agriculture, Cropland, Kansas, Modis, NDVI, Satellite