Ontology-Based Knowledge Modeling for Rice Crop Production

In recent times, smart farming based on Internet of Thing (IoT) technologies has enabled the farmers to enhance productivity of their farms and reduce the waste. However, the heterogeneity of the connecting devices in IoTs has invited several challenges such as the lack of understanding between devices when sharing data acquired from heterogeneous data sources. To overcome the interoperability issues, semantic-based technologies are used to makes devices understand and share heterogeneous data among various devices in an IoT system. In this paper, an existing farming ontology has been extended by adding several crucial classes taking rice crop as a case study. The appended classes include water, pesticide, nutrients, and seed-related classes. Based on all the classes of the ontology, SWRL rules have been defined to infer knowledge with the help of Jess rule engine. In this work, a total of 63 rules reason on 101 classes and its associated properties, thereby, inferring several new results including the management of water and nutrients in yield, continuously at each growth stage of the rice crop production. It also maintains the pesticide use throughout the crop life-cycle along with identifying the seed of specific rice crop type. This results in assisting the farmers in daily and phase-wise decision-making related to their rice crops.