Industrial Experiences in Crop Cultivation Using AI for Disaster Management

Knowledge related to crop cultivation is vast and requires effective management for optimal outcomes. However, current techniques of knowledge management often exhibit deficiencies in efficiency, scalability, and applicability. To address these challenges, this research proposes the utilization of knowledge graphs as a more flexible method of knowledge management. Knowledge graphs offer a novel approach by representing information in a structured and interconnected format, enabling efficient retrieval, analysis, and utilization of agricultural knowledge. Our thesis explores the development of a comprehensive question answering system empowered by knowledge graphs to assist farmers in efficiently accessing and utilizing crop-related information. By leveraging natural language processing and graph-based reasoning, the system aims to enhance decision-making processes in crop cultivation, covering various aspects such as pest and disease management, soil health, irrigation practices, and crop-specific recommendations. Through this approach, our research endeavors to overcome limitations of traditional knowledge management techniques, offering a scalable and adaptable solution to support sustainable agricultural practices and improve crop productivity.