Fusion of multi-source and multi-sensor information on soil and crop for optimised crop production system

Project information

Fusion of multi-source and multi-sensor information on soil and crop for optimised crop production system

Call: ICT and Automation for a Greener Agriculture

Id: 14303

Acronym: FarmFUSE

Duration: 
1 March, 2013 to 29 February, 2016

Consortium:
No Partner Contact Country Total
1000€
Funded
1000€
Funder
1 Coord.Faculty of bioscience engineering, Ghent UniversityAbdul MouazenBelgium172.0154.8Department for Environment, Food and Rural Affairs
2Agricultural Engineering Laboratory
Department of Hydraulics, Soil Science and Agricultural Engineering
School of Agriculture
Faculty of Agriculture, Forestry and Natural Environment
Aristotle University of Thessaloniki
Dimitrios MoshouGreece166.2142.2Managing Authority of the Rural Development Plan
Ministry of Rural Development & Food
3Professorship for Geodesy and Geoinformatics
Chair of Geodesy and Geoinformatics
Faculty of Agricultural and Environmental Sciences
Rostock University
Ralf BillGermany163.3139.3Federal Ministry of Food and Agriculture
4Vocational School of Technical Science
Uludag University
Yucel TekinTurkey92.592.5Scientific and Technological Research Council of Turkey
5tec5 AG
Steffen PiechaGermany46.334.7Federal Ministry of Food and Agriculture
6Professorship for Geodesy and Geoinformatics
Chair of Geodesy and Geoinformatics
Faculty of Agricultural and Environmental Sciences
Rostock University
Jens WiebensohnGermany


Summary: 

Ignoring the inherited spatial variation in soil properties with traditional sampling methods leads to poor crop management, yield loss and excess use of input. The proposed system of FarmFuse addresses these issues in 2 ways: (a) utilising a new and innovative on-line multi-sensor platform for measuring key soil properties at an appropriate resolution. (b) Integrating this improved soil data with other information such as vehicle-borne sensing of crop growth, weather data, soil conductivity and yield maps, to develop algorithms to determine rules for variable rate application. These can then be integrated into FMIS. The vision for the final integrated system would be a server that would allow the end user to access and upload data including maps of soil, crop and yield in addition to recommendations about site specific applications. The resultant treatment maps would then be uploaded to precision agriculture compatible implements for site specific application of inputs.

Impact: 

Ignoring the inherent spatial variation in soil properties with traditional sampling methods has led through the years to poor crop management, yield loss and excess use of inputs. FarmFUSE addresses these issues by fusing a set of data on soil and crops with auxiliary data on topography and weather to delineate management zones for variable rate of nitrogen (VRN) fertilisation. Once the integrated concept is applied by a large number of farmers, a reduction in nitrate leaching into groundwater is foreseen, which supports the EU Water Framework Directive, Nitrates Directive and Integrated Pollution Prevention and Control Directive. It will also reduce fertiliser use and, hence, reduce greenhouse gas emissions and global  warming potential. The project’s specific impacts are measured as: (i) contribution to the creation of a new precision farming service provider named FarmingTruth Ltd in the UK; (ii) contribution to the development of a new visible and near infrared spectrometer produced commercially by tec5; and, (iii) contribution to the creation of a new product for VRN fertilisation, which was proven to increase farmer net income by increasing yield at reduced input cost and environmental impact.

Outputs: 

FarmFuse is based on the following two innovative technologies and approaches:

a) utilising a new and innovative on-line multi-sensor platform for measuring key soil properties at high sampling resolution.
b) Integrating this improved soil data with other information such as vehicle borne sensing of crop growth, weather data and yield maps, to develop algorithms to determine rules for variable rate N fertilisation.

The following are project output:

  • High sampling resolution (> 1000 sample per ha) maps of key soil properties
  • Data fusion algorithms based on machine learning and geospatial analysis for variable rate nitrogen fertilisation
  • Soil and crop maps and recommendations for variable rate N fertilisation are integrated into a farm management information system
Topics: 
  • Variable rate nitrogen fertilisation
  • Proximal soil and crop sensing
  • Data fusion and geospatial analyses
  • Farm management information system

Share your opinion: Add new comment