KTA on Bayesian Networks to support Greenhouse Gas Emission reduction in the Agricultural Sector
Dates
Start date: 7 June 2010
End date: 6 December 2010
Summary
Over the last two years we have developed Bayesian Network (BN) models for the estimation of Greenhouse Gas (GHG) emissions in the agricultural sector. These capture a corpus of experience on the impact that farm management processes have on GHG emissions, in compliance with the IPCC guidelines. The models' predictions of the farm's total annual CO2 emissions validate well against the total emissions attributed to the UK agricultural sector according to the NAEI records. So far, however, it has not been possible to carry out a more thorough analysis on the reliability of these results given the absence of actual emissions figures at farm level in the UK Agricultural sector.
Funding
EPSRC (EP/H500189/1)
Details
These preliminary results show that access to UK or, ideally, Europe wide data on emission figures would enable us to refine the models into a usable tool that would have significant value in aiding the agriculture sector to identifying recommendations for individual farms to optimise their businesses with regard to GHG emissions. Currently the only tool available is CALM provided (FoC) by the Country Land & Business Association (CLA), with support from EEDA & Crown Estates. This assists land managers identify the scale and source of land emissions as part of their corporate and social responsibility. It has been well received as "an excellent first step". However, our BN models can extend this in a number of important ways, such as adding a measure of the potential for carbon sequestration in the farm, and a measure of the costs to the farmer that result from the volumes of GHG emitted as a result of their farming practices.
This 6 month project will involve collection of data, evaluation and refinement of the BN models. Support will come from Simon Ward of the CLA and Profs Norman Fenton and Martin Neil of Agena Ltd. Simon Ward will be involved in the user evaluation of the models and data collection. He will facilitate contact with additional agricultural consultants. Agena Ltd will evaluate the models from the perspective of best practice in developing BNs, and advise on their optimization.