From Cultivating Nature to Cultivating Data: Semantic Technology and Viticulture

It is rewarding to look at the intersection between viticulture and Semantic Technology from an etymological perspective. Such view helps us immediately understand the value semantically enriched data brings to processes and practices involved in the science, production and cultivation of grapes.

The beautiful (and highly connotated) word “culture” comes from the Latin verb “colere”, meaning “to tend, to cultivate”. With that in mind and the fact that we live in a world full of staggering amounts of data, we can see viticulture not only as growing and cultivating vines, but also as gathering and cultivating data.

Harvesting and Harnessing Data for Agriculture

Today, alongside with the cultivation of soils, goes the process where we learn to harvest and cultivate the data around these soils. As the world becomes full of sensor networks producing information, viticulture enters the fields of data processing, storage and retrieval at a fast pace. Click To Tweet

With the help of “rays” from a wide data spectrum (geo-information, soil measurements, weather forecast, chemical analyses, to mention just a few data streams), grapevine-powered industries are in a position to grow an extremely rich system of integrated Internet of Things data to power more informed decisions.

As Vassilis Protonotarios, who is working at the intersection of agriculture and information management, once shared in an interview for Ontotext addressing the question of smart farming:

Smart Farming – or Farming 4.0 – is an integrated farming approach that aims to optimize food production. It is based on data that is combined with the scientific knowledge of researchers and the practical experience of agricultural advisors and farmers. Then, through the use of innovative new technologies, farmers can be supported in activities related to the management of their crops so that they can achieve higher yields and better quality while at the same time they apply the exact amounts of inputs (e.g., irrigation water, fertilizers and pesticides) needed by their crops. This not only improves the financial benefit of farmers (thanks to the minimized production costs), but also minimizes the impact of agriculture on the environment.

Cultivating Grapes Data with Semantic Technologies

As Semantic Technology is rapidly transforming the landscape of data management, this will significantly change not only the high-tech industries, which are usually considered highly data-driven, but also sectors that up until recently weren’t so interested in considering data as an asset.

One example of such a big change is the BigDataGrapes EU-funded research project, where the science and practice of cultivating vines meet with the skills of data gathering, management and integration.

BigDataGrapes aims to help European companies in the wine, farm management and natural cosmetics industries become more competitive in the international markets. More specifically, it tries to help companies from this sector seize the opportunities that big data creates, supporting business decisions with real-time and cross-stream analysis of very large, diverse and multimodal data sources.

https://twitter.com/BigDataGrapes/status/1051778571264581633

The ultimate рromise of Semantic Technologies is to provide the equivalent of university-level knowledge and experience in an out-of-the-box machine-readable form. As Malcolm Gladwell claims, one needs to devote 10 000 hours to become an expert in something, e.g. winemaking, and this expertise is something that builds a critical mass of context.

Our estimate is that an Artificial Intelligence system needs to know 1 billion facts about 100 million concepts and entities and “read” 1 million articles in order to understand concepts and entities in the context of a specific domain. Typically, this context is provided as a sufficiently big Knowledge Graph, loaded in a semantic graph database like our enterprise-ready GraphDB.

To prove this estimate in the BigDataGrapes project, two of the world leading agriculture institutions, INRA and the University of Athens, are building a big viticulture Knowledge Graph capturing a wild range of semantically modeled knowledge, ranging from wine species, genotype information to fermentation types, yeast and vine tasting categorization. This rich context will then be made available to industry partners to become part of their decision process in farming and production plants.

https://twitter.com/BigDataGrapes/status/1028314347821457408

The potential that Big Data streams bring to the table of grape and wine production can be harnessed with the right kind of technology and incorporated into every step of the decision-making processes companies from the viticulture domain are faced with. You can see the Big Data challenges and opportunities, related to the BigDataGrapes Project outlined by our Milena Yankova in the embedded slides below:

With numerous cutting-edge technologies and companies involved, the project is a perfect example of how large volumes of diverse data from all kinds of sources – field sensors, geospatial records, field observations, rich viticulture conceptual knowledge and analyses, administrative and product data, can be integrated and put to work.

The Wine Will Always Whisper, So Will Data

It was Uncle Henry Skinner, from the movie Good Year,  who said:

Picked too early, picked too late, it matters not – the wine will always whisper into your mouth with complete, unabashed honesty every time you take a sip.

Put that in the context of an environment where a significant amount of what’s happening (satellite and weather data, environmental and geological data, phenotypic and genetic plant data, economic and financial data) is recorded, and you could well hear this as the data will always whisper. What is needed is the right kind of data integration technology to hear what it says?