According to the estimates of the United Nations, in 2050 the world population will be over 10 billion. This will lead to approximately 50 percent increase in food need compared to 2013. In order to meet this demand, agricultural production needs to increase.
Feeding the growing world population
To feed the growing world population, it is necessary to increase the yield from the unit area by 1.5 times by 2050. The 4th agricultural revolution that we stand on the brink of today, or in other words the digital transformation in agriculture and information technologies based on the use of big data, plays a key role in the solution to this problem.
To establish a smart agricultural system, three factors need to be rendered together:
▪ Technology which can collect and process data
▪ Algorithms that can convert the obtained data into decisions to accelerate food production, processing, and distribution
▪ Big data can analyze thousands of details and tell what is actually happening
By means of big data, the collected large data sets will enable farmers to monitor their agricultural activities and the status of the fields in real time. Thus, it will be possible to gather essential information and increase yields significantly. Two examples:
▪ Adding more data layers
If datasets with decision-useful information such as rainfall, drought, weather and vegetation index are added, it can be determined better in which sort of fields the crops can be grown. It is also possible to make forecasts based on the information obtained from big data and notify farmers about how to handle their fields better to help them increase their productivity.
▪ Creating super farmers with big data
Another way of applying big data for agriculture is by collecting the data from successful farmers. If one of two farmers who plant the same crop in the same village obtains twice the yield of the other, the main difference between these two farmers is that one of them is doing the right operations at the right time and size. The other farmer has done these operations incorrectly or incompletely. In this case, all the facts of the successful farmer can be identified using agricultural sensors and big data and the mathematical expression of success can be explored. When a sampling of 30,000 farmers is done with data monitoring and analysis, a super farmer profile can be created with deep machine learning.