Hostname: page-component-7b7567c8c-fvjsw Total loading time: 0 Render date: 2026-11-16T11:26:42.692Z Has data issue: false hasContentIssue false

An uncertainty-based comprehensive decision support system for site-specific crop management

Published online by Cambridge University Press:  01 June 2017

V. Adamchuk*
Affiliation:
McGill University, Ste-Anne-de-Bellevue, QC, H9X 3V9, Canada
R. Lacroix
Affiliation:
Valacta, Ste-Anne-de-Bellevue, QC, H9X 3R4, Canada
S. Shinde
Affiliation:
McGill University, Ste-Anne-de-Bellevue, QC, H9X 3V9, Canada
N. Tremblay
Affiliation:
Agriculture and Agri-Food Canada, Saint-Jean-sur-Richelieu, QC, J3B 3E6, Canada
H. Huang
Affiliation:
McGill University, Ste-Anne-de-Bellevue, QC, H9X 3V9, Canada

Abstract

This paper presents a framework for the implementation of a decision support system that considers spatial, temporal and managerial factors in assessing the potential impact of crop amendments on the cost of a given production scenario. The proposed system includes a database and a numeric simulation model. The database is linked to previously recorded crop responses for a given agricultural input under different conditions while the numeric simulation model determines the probability of different levels of profit for each decision option. This system then determines the optimal uniform rate of application of an amendment to maximize profits, or to define the range of such rates for a case of variable rate application. Uncertainty-based treatment of each model input allows for a balance between the potential results of under-application or over-application.

Information

Type
Information and Decision Support Systems
Copyright
© The Animal Consortium 2017. This is a work of the U.S. Government and is not subject to copyright protection in the United States 
Figure 0

Figure 1Architecture of the proposed decision support system.

Figure 1

Figure 2Example of a quadratic-plateau yield response model.

Figure 2

Figure 3Distributions of the price of yield (a) and cost of fertilization (b) model inputs.

Figure 3

Figure 4Distributions of zero fertilization yield (a and b), maximum yield (c and d) and minimum N application rate to achieve maximum yield (e and d) for fine-textured (a, c, and e) and coarse-textured (b, d, and f) soil production scenarios.

Figure 4

Figure 5Expected NRCNF for two different soil conditions.

Figure 5

Figure 6NRCNF probability for an array of possible application rates and a specific management scenario.

Figure 6

Figure 7Probabilities of classes of profits for fine and coarse texture soils.