Recognizing Patterns Within Cropland Vegetation: A Crop Anomaly Classification System

Authors

Paul G. Carter
Christian J. Johannsen
Bernard A. Engel

Abstract

The framework for a national classification system for agricultural cropland anomalies utilizing remote sensing information is presented. Cropland anomalies in Midwest USA have been identified in field crops of corn (Zea mays), soybeans (Glycine max), wheat (Triticum), and miscellaneous hay crops such as alfalfa (Medicago sativa). By identifying cropland anomalies through ground observations and describing the characteristics associated with them, it is possible to group them according to common casual properties such as water, nutrition, weeds, insects, disease, and management, leading to the development of a Cropland Anomaly Classification System. This system advances understanding of specific anomalies and provides an environment for standardization of anomaly characteristics while allowing the possibility for producers and managers to make sound economic decisions. The introductions of new technologies in remote sensing such as increased spatial, spectral, and temporal resolution will cause continual development and improvement of the proposed Anomaly Classification System.

Recommended Citation

Carter, Paul G.; Johannsen, Christian J.; and Engel, Bernard A. (2008) "Recognizing Patterns Within Cropland Vegetation: A Crop Anomaly Classification System," Journal of Terrestrial Observation: Vol. 1 : Iss. 1, Article 5.
Available at: https://docs.lib.purdue.edu/jto/vol1/iss1/art5