New way of exploring farming data could half R&D time

"You may have been looking at data in the wrong way," said Dr Matthew Smith, Chief Product Officer at Agrimetrics. "Data is normally viewed in a dataset, but this is often not the most effective way."  Traditionally, there are three ways that the links between data are viewed: 

• Dataset: such as whether the properties of one dataset make it compatible with another or appropriate to use. The view is the most common view, exemplified by Agrimetrics's Data Catalogue. 
• Spacetime: whether data can be related according to physical space and time. This view is represented through map-based services. 
• Domain: where data can be related via real-world concepts, such as a crop, cow or banana 

"The domain view is the most valuable, yet it is underused," continued Smith. "It will enable us to meet challenges such as reducing agriculture's carbon footprint, end-to-end traceability, improving and predicting yield. This gap led us to create Linked-Data Explorer."

Linked-Data Explorer intuitively illustrates how data is connected. When you perform a search, it will other information relevant to the thing you searched for. In the case of a growing crop, that could include weather forecasts from the Met Office, satellite imagery from Airbus, crop growth and drought risk calculations from researchers, soil chemistry, or social media data.

"This saves a huge amount of time for users, whilst alerting them to data they may not have known was relevant – or even exist," added Smith. "However, the most exciting benefit is for artificial intelligence (AI). In the future, AI will be able to read this data and understand the links between them. It will be able to uncover dangers and solutions that we didn't even know to look for." 

Previously, a user would need to identify the relevant datasets themselves. As datasets are rarely compatible, they would then have to manipulate the data; this process could take months or years for complex projects. Agrimetrics claim they can half these timelines in some cases.

Linked-Data Explorer includes several illustrative examples of linked-data in use. This includes a calculation for evapotranspiration, which is a vital element of assessing drought risk used by both the agricultural and insurance sectors.

"80% of the World's crop failures are water-related," said Smith. "With access to the right data, this number can be significantly reduced." Leaf Area Index (LAI) – a measurement derived by AI from satellite imagery – solar insolation, rainfall, temperature and soil type are some of the data involved in the calculation. They come from datasets owned by Natural England, The Centre for Ecology and Hydrology (CEH), Airbus, The Environment Agency and Agrimetrics itself.

"Without Agrimetrics and Linked-Data Explorer, a grower or researcher or broker would have to identify what data he or she needed, tracked the individual datasets – which are often poorly advertised, negotiate with the owner, and then transform all of that data into something usable. This process could take months – we've reduced it to hours or even minutes."