Ontologies in Precision Agriculture—A brief Survey on Reproducibility

Combined with machine learning techniques, ontologies have recently been applied widely to enhance decision-making, reasoning, knowledge management and representation, and information retrieval in various domains. Likewise, the popularity of ontologies is increasing in the rapidly evolving field of precision agriculture due to the ability to encode general domain knowledge and specialized knowledge of farmers and utilize it within data processing and analytics pipelines. Although the research on ontologies applied to precision agriculture problems is increasing, adopting published solutions is rather cumbersome, mainly due to low reproducibility of these works. This article is intended to survey the current applied research in ontologies within the agricultural domain, by investigating the used methodologies, technologies and evaluation approaches, the availability of the data, ontologies and source codes developed. It was found that the used data sources, the developed ontologies and the developed source codes are available only in 14%, 9% and 7%, respectively, of the selected 85 articles. Additionally, it was found that the applied methodologies, in relation to the issue of reproducibility, the top-down/bottom-up, semi-automatic, seven-step and ontology matching approaches have shown greater potential, while according to the applied technologies, World Wide Web (W3C) have shown greater contribution compared to artificial intelligence (AI).