A prototype system for farm decision making based on a commercially available Geographic Information

1
Very High Resolution Satellite Images (VHRSI) in
Precision Nitrogen Management A prototype
system for farm decision making
Visi García Cidad1, Els Brems2, Els Vrindts1,
Josse De Baerdemaeker1
1Laboratory of Agro-Machinery and Processing
Katholieke Universiteit Leuven Kardinaal
Mercierlaan 92, 3001 Heverlee, Belgium 2G.I.M.
Geographic Information Management N.V.
Interleuvenlaan 5, 3001 Heverlee, Belgium

• INTRODUCTION
• A prototype system for farm decision making
  (based on a commercially available Geographic
  Information System (GIS) ArcView) was developed
  allowing satellite images to be properly
  displayed and combined with land parcel data. As
  a part of this prototype system, an Algorithm was
  developed for the partial automation of the
  decision process to formulate N-fertilisation
  recommendations, in the form of a ready-to-apply
  Nitrogen Application Map. This algorithm uses
  historical information, a N-index expert system
  and satellite data during the growing season. It
  has a structure with an open architecture that
  allows for external input from the user. The
  objective is to adapt the treatment as much as
  possible to the specific field conditions in a
  simplified but optimised way.
• Key words Farm Management Information System,
  GIS, Very High Resolution Satellite Images,
  Nitrogen Fertilisation, Precision Farming,
  N-index expert system

PROTOTYPE The FarMis extension The developed
prototype is as such an extension to the
ArcView Software (FarMis extension). Once the
FarMis extension is loaded two additional menus
are added to the menu bar (Basic FarMis
and Advanced FarMis).
Basic Functionality Visualisation and manipulation
Advanced Functionality Production of a Fertiliser
Application Map (SABRES advanced product)
ALGORITHM An Algorithm was developed to
automatically produce a Fertiliser Application
Map using input Very High Resolution Satellite
Images.
1. Derive Management zones Based on Soil Type
and Field History
5. Calculate Apparent N-need
Soil map
Soil Type Management Zones
Recent Field history
Satellite Image IKONOS-2, Multispectral
Image Pixel size 4m. False color
Vegetation Indices NDVI
Crop biomass
APPARENT N-NEED
4. Derive Advised Application Map

• FINAL COMMENTS
• The model used to translate NDVI to biomass
  values is still under a validation process.
• The presented prototype facilitates the
  production of a nitrogen recommendation map
  enormously.
• At present user input and analysis (user
  expertise) is fundamental to derive the final
  adopted nitrogen recommendation.