Visualizing Data | Illah Nourbakhsh & Matthew C. Hansen

From watching solar flares and plants grow, to tracking deforestation and income inequalities, big data can help us see the world in intimate detail. In this presentation for the World Economic Forum, Illah Nourbakhsh, professor of robotics from Carnegie Mellon and Matthew Hansen, a remote sensing specialist at the University of Maryland, show how visualizing big data can revolutionize the way we understand and imagine the world. Click on the video link above to watch the full presentation, or read extracts below. On interactive learning “Our relationship with data is changing due to advances in storing information, in being able to use graphics processors on computers, and smart use of internet bandwidth. The ability to do this with a static image has recently been supplanted by the ability to do this to any moving image.” “Take the question of the biology of plants. I can present plant behavior to a student in a way that was not possibly even a few years ago. I can take a billion pixel picture of brassica rapa every 15 minutes for a month. Then the student can zoom into the plant at 15 minute intervals seeing the plant grow.” “It's a time lapse, but with an unbounded amount of resolution detail behind the time lapse. So that the learner can watch the plant falling over and trying to get up, and they can see gravity and light fight an epic battle for the plant's future.” On tracking changes over time “The fact that we can now take any exploration through the space and time of data, reveals to us the possibility of thinking about data very differently than we did ten years ago, when we had to put it in a table and look for trends over time. This applies to any quantitative data source. One application of using earth observation or satellite imagery is to track a particular dynamic, such as forest cover change. This is a sequence of images from the Landsat sensor. Different versions of it have been up in orbit since the early 1970s.” “Here we are in Brazil. In 30 years of record you see a fine grain deforestation pattern occurring in the appropriation of rainforest converted to pasture land and row crops. Initially a lot of these clearings are very fine scale colonizers from the south of the country, coming up to establish a very modest subsistence lifestyle. And when we look at this pattern in Rondônia, this is the famous fish bone pattern of a forest cover change by individual landholders.” “Later on we start to start to see big clearings in Mato Grosso which are related to agro industry - big soybean fields, big industrial cattle ranches. As we zoom out to the continental scale, we see what we call the arc of deforestation along the front of the Amazon rainforest, going from the coast all the way around Mato Grosso to Rondônia. This is this is just an incredible record of human change on top of a landscape.” On big data for public good “When we show the time-lapse sequences those are raw pictures or images, and we need to turn those into quantitative estimates. For example when you look at the changes across Brazil. How much forest was lost and how much force grew back? We have to have very clean inputs of imagery to turn that into a biophysical estimate of forest cover.” “Big data and its use for societal good is based on progressive data policies. The Landsat sensor has forty years of data in the archive and it's available to anyone on the planet. So I can make my maps, and the European Space Agency can make their maps with Landsat data.” “It’s very important that providers have this type of mentality, where they’re tasking these instruments, storing the data and then letting the data free. If we do that we can engage everyone - from civil society, to private industry, to government - to come and look at the data and come up with a consensus understanding of what's happening to the planet.”