Ontology-Based Decision Support System for the Nitrogen Fertilization of Winter Wheat

Abstract

Digital technologies are already used in several aspects of agriculture. However, decision-making in crop production is still often a manual process that relies on various heterogeneous data sources. Small-scale farmers and their local consultants are particularly burdened by increasingly complex requirements. Regional circumstances and regulations play an essential role and need to be considered. This paper presents an ontology-based decision support system for the nitrogen fertilization of winter wheat in Bavaria, Germany. Semantic Web and Linked Data technologies were employed to both reuse and model new common semantic structures for interrelated knowledge. Many relevant general and regional data sources from multiple domains were not yet available in RDF. Hence, we used several tools to transform relevant data into corresponding OWL ontologies and combined them in a central knowledge base. The GUI application of the decision support system queries it to parameterize requests to external web services and to show relevant information in an integrated view. It further uses SPARQL queries to automatically generate recommendations for farmers and their consultants.

A Digital Advisor Twin for Crop Nitrogen Management

“…This language provides a semantic vocabulary for unambiguously modeling expert knowledge and machine understandability in uniform data structures in the form of ontologies. OWL ontologies and the semantic query language SPARQL Protocol and RDF Query Language (SPARQL) are open standards of the Semantic Web for linking data [35].…”

“…Figure 5 shows a schematic of the developed DSS. From existing semantic resources, such as ontologies available online, vocabularies (e.g., AGROVOC and QUDT), SPARQL endpoints, and non-RDF data sources (e.g., DWD raster maps, BBCH monograph [36], fertilization guidelines, and regulations), several OWL ontologies have been created using different software tools (e.g., Protégé, Ontop, and GraphDB OntoRefine) [35]. Here, the individual ontologies contain the modeled data structures, general and specialized knowledge, transformed datasets from data sources from different institutions, and farm data from individual model farms.…”

“…The OWL ontologies are loaded into the central knowledge base of the DSS for storage, further processing, and querying. The knowledge base is an RDF graph database with an automatic reasoner that can infer additional facts from existing knowledge via semantic vocabulary [35]. The competence questions and decision trees are formulated as SPARQL queries so that they can be answered by the knowledge base [35].…”

“…The knowledge base is an RDF graph database with an automatic reasoner that can infer additional facts from existing knowledge via semantic vocabulary [35]. The competence questions and decision trees are formulated as SPARQL queries so that they can be answered by the knowledge base [35]. Many parameters for the SPARQL queries are automatically filled using knowledge stored in, or logically inferred from, the central knowledge base.…”

OntoCSA

“…Although the semantic modelling of agriculture has attracted researchers in recent years (Ramar & Gurunathan, 2017;Jebaraj & Sathiaseelan, 2017;Goldstein et al, 2019;Drury et al, 2019;Kessler et al, 2021;Roussey et al, 2021;Abayomi-Alli et al, 2021) and has resulted in the development of ontologies for agriculture (Hu et al, 2011;Kim et al, 2013;Jebaraj & Sathiaseelan, 2017;Ngo et al, 2018;Arnaud et al, 2020;Jachimczyk et al, 2021;Nidhi et al, 2021), no research to date has focused on building a knowledge base ontology for the CSA domain. This study attempts to fill this gap through the development of a Climate Smart Agriculture Ontology (OntoCSA).…”