Carbofarm: data integration and knowledge generation for agricultural GHG inventories

Abstract

Global warming and climate change have been topics of great interest in recent years, as it is related to greenhouse gas (GHG) emissions. The agricultural sector suffers the consequences of these changes. However, it is also one of the top global emitters of GHG. Agricultural is a complex sector in its environmental, social, and economic aspects. There is a need to propose new solutions that provide more sustainable agriculture. In the farm environment, an important step is the generation of GHG inventories. Based on the knowledge generated by inventories, problems can be identified, and solutions can be searched for that aim to increase carbon sequestration and reduce emissions. A positive carbon balance enables the generation of carbon credits with potential economic return. Public datasets and datasets collected on rural properties, when available, can contribute to the generation of inventories and the promotion of more sustainable agricultural practices. This study presents an architectural proposal containing an ontological model called CarbOnto, with the objective of syntactically and semantically integrating sets of heterogeneous data related to agriculture. Using machine learning techniques from integrated datasets, we generate knowledge to support rural owners' decision-making. We offer alternatives for using land with a focus on positive GHG balance, which contributes to the generation of carbon credits.