Today I want to talk about the challenges of using big data to innovate in the agricultural domain and six steps to overcoming them. I’m going to describe the organizational and social contexts for using big data for agriculture. This blog is taken from my Big Data Informatics graduate coursework at Indiana University which I complete this week! In previous blogs I’ve talked about in general terms about applications of big data in agriculture including precision farming, vertical farming and reducing food waste on the farm. Today I want to delve more into the specifics of actually implementing a big data program.
With the population reaching 9 billion by 2050, there is a need to increase agricultural productivity. By 2030, the Food and Agriculture Organization of the U.N. estimates there will be a 35% increase in global food demand. Along with this increasing demand, climate change and a decreasing amount of arable land will affect the food supply. Leveraging information gained from big data analysis and implementing it in agriculture could help meet these growing demands on the food supply. Innovative solutions from big data insights will be the key to feeding the next generation
The good news is that emerging technologies continue to make it easier to collect and use large amounts of data cheaply. Big data can make a farmer more productive. This potential will drive agricultural innovation to minimize the effects of climate change, natural disasters and limited resources for society. It is essential to break down barriers so farmers can produce more with less resources and so the world has enough to eat. The stakes have never been higher for overcoming these challenges.
Three main challenges in agricultural applications include: data infrastructure, data integration and deriving value from the data.
These steps will help overcome these challenges:
- Set up an appropriate infrastructure.
- Establish partnerships to integrate data.
- Communicate across silos.
- Ask the right questions.
- Find the data’s value.
- Data experts collaborate with domain experts.
Capitalizing on big data solutions will require changes in how data in seen within and across organizations. For more details on the challenges and steps, visit my Github repo.