There are many discussions around the identification, registration and description of big datasets for agriculture, food and environment; but moving on from such introductory or academic exercises, how is big data actually used in practice for serving actual causes and solving real problems? An article on Wired shows a number of examples; however, we were looking for something bigger than that.
We recently came across the collaboration between IBM and Mars, which is expected to change the way that food safety is perceived; what these two giants (in technology and food context, respectively) are actually working on an index that will be a gold standard for food and health officials globally to understand what triggers contamination and the spread of foodborne diseases. The potential of this research effort is huge, as the outcomes will allow the food sector to safely work in contexts that were not clear before; therefore they might induce food-related diseases.
How will they do that? Mars food scientists are extracting DNA and RNA of simple food samples and test it with common organisms or genes, toxins, and heavy metals to determine where anomaly and mutations occur when combining them. The process is complex and involves the use of data already produced by Mars researchers throughout the years. At the same time, IBM researchers are implementing big data informatics infrastructure and analytics processes in order to facilitate the analysis of huge volumes of data (we’re talking about TBs of data here!) produced by the former researchers. The expected outcomes will be innovative tests and protocols for different food and health processes.
How important is the issue of food borne diseases that IBM and Mars aim to tackle?
Let the numbers highlight the importance of this issue; you can access the full infographic here.
So how is the work of Agro-Know related to such big (huge, to be more precise) effort, led by global leaders in their fields? Our Big Data Europe Horizon 2020 project is already working in this direction, aiming to record all players in the agrifood big data sector. Through this process, Agro-Know is working towards the identification of the organizations producing such big datasets, the attributes of these datasets (in terms of type, format, volume etc.), the issues related to their management and analysis etc. This is just the first step of a process designed and (to be) implemented by the project; after all…
Head image – From the portfolio of Monica Esquivel