Search

This paper describes a framework for an image processing procedure for operational agricultural crop area estimation. This operational framework has been conceived within the development of an Advanced Agricultural Information System (AAIS) for the “Regione del Veneto “ (RdV - Veneto Region) in northeastern Italy. The objective of this program is to develop the ability to generating timely and accurate area estimates and production information for four major agricultural crops: soybeans, sugar beets, corn, and small grains. AAIS uses state of the art methods in remote sensing and geographic information systems (GIS) technology and integrates a variety of data types including satellite imagery. This paper describes the methodology developed for image and ancillary data processing for the production of crop area statistics. Using a combination of standard unsupervised classification and GIS operations that incorporate knowledge about the agricultural system, a “sequential masking” classification procedure was derived. This sequential masking procedure yielded crop classification accuracies that at the study site level range between 76% and 99% depending on the crop under study. We believe that classification accuracies will improve with full system implementation, along with the incorporation of new and/or improved thematic information and operational experience using AAIS-based estimation.

The Regione del Veneto (Italy) is cooperating with the University of California, Santa Barbara and other researchers in Italy and the U.S.A. to develop a system of econometric crop production modeling. Five crops are to be included in this project: small grains (wheat and barley), corn, sugar beets, soybeans, orchards and vineyards. A critical part of the crop yield modeling process is the identification of crops using multispectral satellite data. This paper explores two strategies to improve crop classification accuracies: (1) use of ancillary data stored in digital format and (2) use of multitemporal data. Ancillary information stored on digital files were used in this research to remove (mask) non-agricultural areas from satellite image data. Comparison between the classification of masked and unmasked images showed that improvement ranged from 3% to 26% depending on crop type. The multidate classification was performed by compiling an image of transformed spectral bands and three TM-5 bands. The transformed bands were TM band 4 over TM band 3. Based on the work conducted in this study it is clear that crop type determination from satellite imagery is possible for small field agricultural areas such as those found in Italy.