Skip to main content
ARS Home » Research » Publications at this Location » Publication #119403
Title: SPRING WHEAT CLASSIFICATION IN AN AVHRR IMAGE BY SIGNATURE EXTENSION FROM ALANDSAT TM CLASSIFIED IMAGE

Author
item Stern, Alan
item Doraiswamy, Paul
item COOK, PAUL - USDA-NASS SPATIAL RES

Submitted to: Photogrammetric Engineering and Remote Sensing
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 2/15/2001
Publication Date: 3/7/2001
Citation: N/A

Interpretive Summary: Landuse/Landcover classification is a technique that allows a person to visit a small area within a satellite image and based on that information, ascertain what ground types are in the rest of the image. We have developed a technique that allows us to use this idea to create a Landuse/Landcover classification using low resolution satellite data (NOAA AVHRR) using a high resolution (Landsat TM) classification within part of the image. The study was done in the state of North Dakota and our attempt was to assess the acreage of spring wheat in each county. Overall the study was a success, however, because our high resolution image was not centrally located within the state, it was necessary to use ancillary data to improve acreage estimates.

Technical Abstract: Landsat TM imagery data has been used for the classification of crops in small areas, however NOAA AVHRR imagery is more appropriate for regional and continental scales for few specific categories of vegetation. The USDA is interested in assessing crop acreage at the County and State levels. The objective in this study was to conduct the feasibility of using AVHRR to classify spring wheat in North Dakota. Two methods were developed to categorize large areas using AVHRR data and a minimal amount of Landsat TM. Areas of intense agriculture were used to perform an unsupervised classification with AVHRR data. Differences in precipitation and climatic conditions between the eastern and western parts of the State created some difficulties in proper classification and to improve classification accuracy, additional ancillary data was needed. The number of Landsat TM spring wheat pixels in the overlapping AVHRR pixels provided a means of predicting the percentages of spring wheat for each AVHRR class. The accuracy of the spring wheat acreage at the State level closely matched the USDA State report for 1994.