Cognitive Computing

Bringing Cognitive to Data Visualization

Share this post:

The goal of data visualization is to help explain complex data-driven trends, patterns, and correlations quickly and easily through imagery. And while traditional methods of data visualization have focused on interactive graphics, an exciting new trend is emerging that captures the movement of data in video.

In my work at IBM’s Cognitive Visualization Lab, I build tools that help people disseminate information as short videos – where the data and the visualizations are the actors. In 2016, I put some of these tools to work to build a short video to augment the work of three of my colleagues at Northeastern University, who wrote and published a paper in Nature on resilience patterns in complex networks.

In the paper, professors Jianxi Gao, Baruch Barzel, and Albert-László Barabási, explain their formula to calculate the potential impacts to networks when things are added or removed from those networks.

The video I created, Network Earth, helps illustrate their theory by visually depicting the symbiotic relationship and mutualism between a handful of ant species and the plants upon which they depend, across Australia and New Guinea.

Anonychomyrma gilbert, for example, is an ant that lives in and around 19 different types of plant. Its food comes from the juices of these plants. In return, one of these plants, the Adenia heterophylla, a vine that grows in the coastal regions, benefits from Anonychomyrma gilberti’s protection from Greta obo, the glasswing butterfly that feeds on it.

In Network Earth the visualizations fluidly illustrate the potential impact of changes to this species’ ecosystem when slight or dramatic changes in connections occur. It also depicts the potential impact to the millions of connections between the other 40 ants and 49 plants in the network – all of which would have to occur in order to maintain equilibrium.

To build the video I used our latest Network Data API and was able to plot the dynamic networks of the theoretical physics behind the resilience of complex networks, with the real world network of ants and plants of Australia.

This week, the National Science Foundation awarded Network Earth a Vizzie for best data video in 2016. As data volumes continue to grow and expand, new and exciting ways to capture the insights within that data will continue to evolve and aid man in its quest for greater understanding.

Manager, IBM Cognitive Visualization Lab; Professor of Practice, Northeastern University


Just 1 word for it…

So simple to understand such a complex network which might lead to drastic impact on an ecosystem….What about a similar comparison where the ant can be replaced by Human being and the plants (replaced with staple food like wheat, pulses, rice etc). I will be great to know the impact .

Divya Mudundi

This is great, thank you for sharing, Mauro.


Great visualization!!


And the Network Data is so complex that we would need the sheer processing power of Quantum computer to process the enormous volumes of Data that it encompasses
Very Impressive

Angelo Porcelli

It will be shocking but this video should be broadcast around the world and screened in all schools. Good work.

Bernadette Friswell

Love this! Compelling and beautiful in communicating the message. What an engaging, simple way to tell a story with complex data.

Melissa Starr

The video was very impressive! It is easy to see why it was recognized with an award. Very well done!

Chuck Kichler

Truly genius. Love the use of biological networks. I’ve argued that existing ecological network complexity exceeds that man-made networks. You also were able to deal with multiple resolution levels which often become a trap for biologist / ecologist. “Fools ignore complexity. Pragmatists suffer it. Some can avoid it. Geniuses remove it.” – Alan Perlis. Truly genius.

Marc Helsen

Very impressive video and way of presenting data!

Pratul Gupta

Hi Mauro, that is beautiful, informative, and versatile visualization. Would you point me to your other creations? Cannot wait to see them.


Veeery impressive, Mauro !!


What skillsets are required to become a data visualisation expert, does it involve coding?

Darrell Kirby

The video was a great representation of a network in nature. It showed how ants and plants share in order to survive and how the relationship protects the plants. This builds a network of survival for plants and ants. The network can assimilate to one type of ant leaving but Just as in Technology, many issues in a network can cause real problems. This was a good representation of nature and how solutions can be gained from examining these roles.


Beautiful visualizations and superbly engaging, Mauro!

Comments are closed.

More Cognitive Computing stories

A New Era of the Smart Enterprise

In 2014, Apple and IBM formed a partnership to empower the enterprise and change the way professionals work. Since then, we’ve helped numerous clients across industries, including Amica Insurance, City Furniture, and Japan Airlines, fuel their digital transformations with mobile. Today, we’re seeing an increasing number of companies interested in artificial intelligence (AI) and machine […]

Continue reading

IBM Makes Advanced AI More Accessible for Users Everywhere

Artificial intelligence will be the most disruptive class of technologies over the next decade, fueled by near-endless amounts of data, and unprecedented advances in deep learning. The rise of deep learning has been fueled by three recent trends: the explosion in the amount of training data; the use of accelerators such as graphics processing units […]

Continue reading

How Watson Assistant Helps You Treat Customers Like VIPs

Over the last few years, digital assistants have cemented their place in our homes, helping execute routine day-to-day tasks, from turning on our televisions to telling us about “this day in history.” But these devices have also accomplished something else, they have laid the groundwork for what’s next: truly intelligent AI assistants that get to […]

Continue reading