Design and development of an ontology-based hazelnut databank for Turkish hazelnut cultivars using crop-specific open dataset

Agriculture is one of the oldest professions in the history, it still plays the main role in economy for almost entire countries around the world. The activities performed by farmers in agriculture domain have been changed and developed over thousands of years. There have been several challenges that agriculture sector is facing like population growing, labor migration, in addition many young people are reluctant to work in the agricultural field. By 2050 population will increase with 2 billion mean while arable land will growth with only 4%, that means lower agricultural yields versus demand, higher crop prices, and increased food security concerns if farmers continue to adopt traditional agricultural methods. The emerging technologies such as Artificial Intelligence (AI) and Internet of Things (IoT) can be used to provide robust solutions for overcoming the challenges in the context of agriculture. In addition, such technologies can help farmers for performing agricultural activities more precisely and for protecting agricultural crops from climate changes in a more effective way. The main objective of this thesis is to develop an integrated databank software system by using two different AI models to classify the Turkish Hazelnut Cultivars. While classifying the cultivars, databank is using ontology-based open data sets in different formats such as RFD/XML and RDF/JSON. Furthermore, an IoT-based device has been developed to classify the cultivars. The databank consists of a web-based and desktop-based applications. The AI models have been developed using .NET ML with the accuracy 90.34% and Python with the accuracy 85.32% respectively.