What is Big Data, And How Can It Help Save The Environment?
When it comes to the business world, the infinite possibilities of big data have been well documented. Although the transformative role of advanced analytics and sophisticated insights are highly regarded across industries including finance and retail, big data has only just started gaining traction as a driver of environmental sustainability.
As Srivatsan Ramanujam, a Principal Data Scientist at Pivotal, explains: “Our environment is changing quite fast—often less predictably than anticipated and much faster than we can adapt.“ In this post, we will join Ramanujam on an expedition to Acadia National Park in Maine to explore the many ways in which big data can help mitigate one of the largest threats to the environment: climate change.
From phenology to data science
In scientific research, nature can be seen as an incredibly rewarding, yet an extremely demanding subject matter. While even the smallest grain of new information is treated as a long-lost part of a multimillion-piece puzzle, it’s difficult to determine whether – and at what pace – that piece will shift shape again. Although these rapid changes and the complex interplay between individual elements make the environment a fascinating topic to study, they also imply that scientists must be able to look at countless of data sources to find meaningful causal relationships.
Together with a group of citizen scientists from the EMC federation, Ramanujam helped Dr. Abraham Miller-Rushing and his phenology team to collect a variety of data from Acadia National Park. Ramanujam clarifies: “With phenology, scientists look at how climate changes can affect a natural ecosystem. The climate affects seasons, the life cycle of vegetation and food sources, animal migrations, and more.” He explains that: “Due to warmer temperatures, the primary food source for puffin chicks are long gone from the waters off Maine by August. As a result the puffin parents have been attempting to feed their chicks with an alternative food source, butterfish, which the chicks struggle to swallow. This has lead to a serious decline in the number of puffin chicks that have successfully fledged.“
Building a ‘Climate Data Lake’
As Miller-Rushing explains: “Birds, plants, insects, even Lyme disease. They’re connected but most of the science is separate. Big data insights combine it all so you can analyse it and act.” The ultimate objective of the expedition was to build a foundation for a ‘Climate Data Lake’ that would collect and combine a large quantity of different kinds of data. This information would then be analysed to predict, recognise and counter the biggest threats to the ecosystem. In Ramanujam’s words: “With the climate data lake initiative, we hope to build a knowledge base of these changes that integrates data from a multitude of sources, and use it to build predictive models and visualisations to mitigate the negative impact of climate change and better manage the future.”
Furthermore, Ramanujam finds it important to highlight that it doesn’t take a data scientist to help change the world: “The best part is that virtually anybody can add data, not just scientists and PhDs. Climate change impacts everybody. So we created a way to let everybody help find a solution.”
Only a year has passed from Ramanujam’s first expedition, but the climate data lake initiative has already extended far beyond Acadia National Park, Maine and North America. In fact, EMC’s Senior Vice President and Chief Sustainability Officer, Kathrin Winkler, states that: “We’re harnessing climate data captured by people anywhere in the world, and making it visual so they can see how they’re impacting important research.” In partnership with the White House Climate Data Initiative, EMC has been able to empower people from all over the world to join the fight against climate change.
Although the achievements of Acadia’s citizen scientists are already beyond impressive, it doesn’t hurt to remember that we have only just started scratching the surface of what data can do for the environment. However, with the climate data lake in place, there is no telling what the near future will bring. To borrow the words of EMC’s Michael Foley: “As they say, big data can change the world.”