Development of an Information Research Platform for Data-Driven Agriculture

Abstract

Comprehensive research data are acknowledged as a necessity for research acceleration. Research institutes and universities are engaged in developing research data management systems. The National Agriculture and Food Research Organization of Japan (NARO) developed NARO-linked databases (Narolin DBs) in addition to a supercomputer. In the Narolin DB various research data on agriculture are cataloged using common metadata. The relationship between complicated data in natural science is described in RDF, property graph, or RDB format to facilitate the application of statistical analysis and machine learning. Our system is unique in that it is connected to a data catalog, a private cloud database, a supercomputer for data analysis, and a data/service portal for business applications, such as a data pipeline. Through the development of agricultural information research platforms, NARO will accelerate data-driven agricultural research at various stages in the agricultural supply chain, ranging from genome analysis to plant breeding, cultivation, food processing, and food distribution.